This directory is created automatically and some papers may be mislabeled. Only document within the CiteSeer database are listed. The directory is intended to provide entry points for browsing the database and is not intended to be authoritative. Papers may not appear in all relevant categories. For example, papers in a sub-category may not appear in higher level categories.
684.0 Reinforcement Learning: A Survey - Kaelbling, Littman, Moore (1996)(Correct)
This paper surveys the field of reinforcement learning from a computer-science perspective. It
is written to be accessible to researchers familiar with machine learning. Both the historical basis
of t... / are closely related to search and planning issues in artificial br through a graph of states. Planning operates in a similar manner but
638.2 Boosting the Margin: A New Explanation for the Effectiveness of.. - Schapire, Freund, al. (1997)(Correct)
One of the surprising recurring phenomena
observed in experiments with boosting is that the test error
of the generated hypothesis usually does not increase as its
size becomes very large, and often... / On the left of AT T Labs is planning to move from Murray Hill. The new br Machine Learning Proceedings of the Fourteenth
614.4 LEDA - A Platform for Combinatorial and Geometric Computing - Mehlhorn, Näher (1995)(Correct)
LEDA is a library of efficient data types and algorithms in combinatorial and
geometric computing. The main features of the library are its wide collection
of data types and algorithms, the precise an... / VLSI design robot motion planning traffic scheduling machine br code optimization motion planning logic synthesis scheduling
553.1 Using CSP Look-Back Techniques to Solve Real-World SAT Instances - Bayardo (1997)(Correct)
We report on the performance of an enhanced version of the "Davis-Putnam" (DP) proof procedure for propositional satisfiability (SAT) on large instances derived from realworld problems in planning, sc... / from realworld problems in planning scheduling and circuit br from real-world problems in planning scheduling and circuit
529.4 Intelligence without representation - Brooks (1991)(Correct)
Artificial intelligence research has foundered on the issue of representation. When intelligence is approached in an incremental manner, with strict reliance on interfacing to the real world through p... / techniques could then be used for planning within this well-understood br complex domains such as trip planning going to a restaurant medical
518.8 Learning to Act using Real-Time Dynamic Programming - Barto, Bradtke, Singh (1995)(Correct)
Learning methods based on dynamic programming (DP) are receiving increasing attention in artificial intelligence. Researchers have argued that DP provides the appropriate basis for compiling planning ... / appropriate basis for compiling planning results into reactive strategies br between AI research on real-time planning and learning and relevant
367.0 Retrieving And Integrating Data From Multiple Information Sources - Arens, Chee, Hsu, Knoblock (1993)(Correct)
With the current explosion of data, retrieving and integrating information
from various sources is a critical problem. Work in multidatabase systems
has begun to address this problem, but it has prima... / been tested in a transportation planning domain using nine Oracle br server multidatabases planning query reformulation knowledge
353.0 An Introduction to Least Commitment Planning - Weld (1994)(Correct)
Recent developments have clarified the process of generating partially
ordered, partially specified sequences of actions whose execution
will achive an agent's goal. This paper summarizes a progressio... / Introduction to Least Commitment Planning Daniel S. Weld br a progression of least commitment planners starting with one that handles
345.4 A Survey of Agent-Oriented Methodologies - Iglesias, Garijo, Gonzalez (1999)(Correct)
This article introduces the current agent-oriented methodologies. It discusseswhat approacheshave been followed (mainly extending existing objectoriented and knowledge engineering methodologies), th... / carry out their inferences their planning process etc. Finally agents br actuators world knowledge and planning abilities. Then a suitable agent
314.2 Modeling Web Sources for Information Integration - Knoblock, Minton, Ambite, Ashish.. (1998)(Correct)
The Web is based on a browsing paradigm that makes
it difficult to retrieve and integrate data from multiple
sites. Today, the only way to do this is to build
specialized applications, which are time-... / machine learning and automated planning. The resulting system called br large database. Ariadne's query planner decomposes these queries into a
304.3 RoboCup: The Robot World Cup Initiative - Kitano, Asada, Kuniyoshi, Noda, Osawa (1995)(Correct)
The Robot World Cup Initiative (RoboCup)
is an attempt to foster AI and intelligent
robotics research by providing a standard problem
where wide range of technologies can be
integrated and examined. T... / acquisition learning real-time planning multi-agent systems context br cooperative distributed real-time planning scheme embedded in a highly
266.6 The Role of Emotion in Believable Agents - Bates (1994)(Correct)
Artificial intelligence researchers attempting to create engaging, apparently living
creatures may find important insight in the work of artists who have explored the
idea of believable character. In ... / The action system does no planning and almost no world modeling but br act autonomously think learn enjoy hate and which liked to
254.3 Acting Optimally in Partially Observable Stochastic Domains - Cassandra, Kaelbling, Littman (1994)(Correct)
In this paper, we describe the partially observable
Markov decision process (pomdp) approach to finding
optimal or near-optimal control strategies for partially
observable stochastic environments, giv... / and provides a formal basis for planning problems that have been of br and effects into their planners Moore These solutions
252.1 The Parti-game Algorithm for Variable Resolution Reinforcement.. - Moore, Atkeson (1995)(Correct)
Parti-game is a new algorithm for learning feasible trajectories to goal regions in
high dimensional continuous state-spaces. In high dimensions it is essential that learning does not
plan uniformly... / including mazes path planning non-linear dynamics and planar br computational effort required for planning and the physical amount of data
238.2 Multiagent Systems: A Survey from a Machine Learning Perspective - Stone, Veloso (1997)(Correct)
Distributed Artificial Intelligence (DAI) has existed as a subfield of AI for less than two decades. DAI is concerned with systems that consist of multiple independent entities that interact in a doma... / by the DARPA RL Knowledge Based Planning and Scheduling Initiative under br Understanding each other ffl Planning communicative acts ffl
228.8 Experimental Results on the Crossover Point in Satisfiability Problems - Crawford, Auton (1993)(Correct)
Determining whether a propositional theory is satisfiable is a prototypical example of an NPcomplete problem. Further, a large number of problems that occur in knowledge representation, learning, plan... / representation learning planning and other areas of AI are br representation learning planning and other areas of AI are known
227.1 Operations for Learning with Graphical Models - Buntine (1994)(Correct)
This paper is a multidisciplinary review of empirical, statistical learning from a graphical
model perspective. Well-known examples of graphical models include Bayesian networks,
directed graphs repre... / systems and more recently in planning and control Dean Wellman br Dean T.Wellman M. Planning and Control. San Mateo
218.1 Evolving Artificial Neural Networks - Yao (1999)(Correct)
Learning and evolution are two fundamental forms of adaptation. There has been a great
interest in combining learning and evolution with artificial neural networks (ANNs) in recent
years. This paper (... / neural network for robot path planning in Proceedings of the br N. Noguchi and H. Terao Path planning of an agricultural mobile robot
205.7 Hierarchical Reinforcement Learning with the MAXQ Value Function.. - Dietterich (1998)(Correct)
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ
decomposition of the value function. The MAXQ decomposition has both a procedural semantics---
as a subrouti... / much recent work on probabilistic planning and learning. Formally a br discounted case. In probabilistic planning it is assumed that the agent
205.7 The Interactive Museum Tour-Guide Robot - Burgard, Cremers, Fox, Hähnel.. (1998)(Correct)
This paper describes the software architecture of an autonomous
tour-guide/tutor robot. This robot was recently
deployed in the "Deutsches Museum Bonn," were it guided
hundreds of visitors through the... / mapping localization path planning mission planning and user br path planning mission planning and user interface control. The
204.2 The RoboCup Synthetic Agent Challenge 97 - Kitano, Tambe, Stone (1997)(Correct)
RoboCup Challenge offers a set of challenges for intelligent agent researchers using a friendly competition in a dynamic, real-time, multiagent domain. While RoboCup in general envisions longer range ... / and teams ii multi-agent team planning and plan-execution in service of br opportunity for machine learning planning and multi-agent researchers -
202.8 Experimental results on the crossover point in random 3sat - Crawford, Auton (1996)(Correct)
Determining whether a propositional theory is satisfiable is a prototypical example
of an NP-complete problem. Further, a large number of problems that occur in
knowledge-representation, learning, pla... / learning planning and other ares of AI are br learning planning and other ares of AI are known
200.0 Mean Field Theory for Sigmoid Belief Networks - Saul, Jaakkola, Jordan (1996)(Correct)
We develop a mean field theory for sigmoid belief networks based on ideas from statistical mechanics. Our mean field theory provides a tractable approximation to the true probability distribution in t... / now widely used as models of planning reasoning and uncertainty. br for Biological and Computational Learning Massachusetts Institute of
197.0 A Robot Exploration and Mapping Strategy Based on a Semantic.. - Kuipers, Byun (1991)(Correct)
this paper is to overcome the fragility of purely metrical methods.
Several researchers use various types of graph model or topological model to represent the connectivity
of the environment. Laumond ... / it can be used to optimize route-planning or to resolve topological br hypothesis by traveling along the planned route. . However it reaches a
188.4 Cooperative Mobile Robotics: Antecedents and Directions - Cao, Fukunaga, Kahng, Meng (1995)(Correct)
There has been increased research interest in systems composed of multiple
autonomous mobile robots exhibiting collective behavior. Groups of
mobile robots are constructed, with an aim to studying suc... / From another perspective path planning must be performed taking into br this multiple-robot path planning is an intrinsically geometric
187.6 Teleo-Reactive Programs for Agent Control - Nilsson (1994)(Correct)
A formalism is presented for computing and organizing actions for autonomous agents
in dynamic environments. We introduce the notion of teleo-reactive (T-R) programs whose
execution entails the constr... / that is compatible with automatic planning and learning methods. We briefly br is forced to postpone most of its planning until run time when situations
182.8 Map Learning and High-Speed Navigation in RHINO - Thrun, Bücken, Burgard, Fox.. (1998)(Correct)
This chapter surveys basic methods for learning maps and high speed autonomous navigation for indoor
mobile robots. The methods have been developed in our lab over the past few years, and most of them... / constructed that facilitate fast planning. . Localization. Localization br Approaches to global path planning exploration and reactive
181.8 The CMUnited-98 Champion Simulator Team - Stone, Veloso, Riley (1999)(Correct)
The CMUnited-98 simulator team became the 1998 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a total of 66--0. CMUnited-98 builds upon the successful CMUni... / by the DARPA RL Knowledge Based Planning and Scheduling Initiative under br players. However for strategic planning it is very useful to have a
178.7 Learning Topological Maps with Weak Local Odometric Information - Shatkay, Kaelbling (1997)(Correct)
Topological maps provide a useful abstraction
for robotic navigation and planning. Although
stochastic maps can theoretically be learned using
the Baum-Welch algorithm, without strong
prior constraint... / for robotic navigation and planning. Although stochastic maps can br sound method for localization and planning Simmons and Koenig
163.6 A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov .. - Kearns, Mansour, Ng (1999)(Correct)
An issue that is critical for the application of
Markov decision processes (MDPs) to realistic
problems is how the complexity of planning
scales with the size of the MDP. In stochastic
environments wi... / Algorithm for Near-Optimal Planning in Large Markov Decision br problems is how the complexity of planning scales with the size of the MDP.
157.1 Constructive Neural Network Learning Algorithms for Pattern.. - Parekh, Yang, Honavar (2000)(Correct)
Constructive learning algorithms offer an attractive
approach for the incremental construction of near-minimal
neural-network architectures for pattern classification. They help
overcome the need for ... / is with Allstate Research and Planning Center Menlo Park CA USA br at the Allstate Research and Planning Center Menlo Park CA. His
154.6 Database Mining: A Performance Perspective - Agrawal, Imielinski, Swami (1993)(Correct)
We present our perspective of database mining as the confluence of machine learning
techniques and the performance emphasis of database technology. We describe three classes
of database mining problem... / single time as a transaction. The planning department may be interested in br factor of the rule. Usually the planner will be interested not in a
154.5 MINERVA: A Second-Generation Museum Tour-Guide Robot - Thrun, Bennewitz, Burgard, Cremers.. (1999)(Correct)
This paper describes an interactive tour-guide robot, which
was successfully exhibited in a Smithsonian museum. During
its two weeks of operation, the robot interacted with
more than 50,000 people, tr... / collision avoidance path planning and global mission planning. br path planning and global mission planning. The interaction modules
145.6 Randomized Preprocessing of Configuration Space for Fast Path Planning - Kavraki, Latombe (1994)(Correct)
This paper presents a new approach to path planning
for robots with many degrees of freedom (dof) operating
in known static environments. The approach consists of a
preprocessing and a planning stage.... / Configuration Space for Fast Path Planning Lydia Kavraki br presents a new approach to path planning for robots with many degrees of
137.1 Learning Maps for Indoor Mobile Robot Navigation - Thrun (1998)(Correct)
Autonomous robots must be able to learn and maintain models of their environments.
Research on mobile robot navigation has produced two major paradigms for mapping indoor
environments: grid-based and ... / often prohibits efficient planning and problem solving in br approaches a they permit fast planning b they facilitate interfacing
137.1 Learning Evaluation Functions for Global Optimization and Boolean.. - Boyan, Moore (1998)(Correct)
This paper describes Stage, a learning approach to automatically improving search performance on optimization problems. Stage learns an evaluation function which predicts the outcome of a local search... / bin-packing medical treatment planning and Bayes net structure finding br average. Radiotherapy Treatment Planning Radiation therapy is a method
129.3 Artificial Life and Real Robots - Brooks (1992)(Correct)
The first part of this paper explores the general issues in using Artificial Life techniques to program actual mobile robots. In particular it explores the difficulties inherent in transferring progra... / perception world modeling planning and execution the new approach br its own perceptual modeling and planning requirements. An arbitration or
125.7 Learning to Coordinate Behaviors - Maes, Brooks (1990)(Correct)
We describe an algorithm which allows a behavior-based robot to learn on the basis of positive and negative feedback
when to activate its behaviors. In accordance with the philosophy of behavior-based... / such as perception modeling and planning figure the architecture is br architectures for learning planning and reacting based on
123.4 Ten Challenges in Propositional Reasoning and Search - Selman, Kautz, McAllester (1997)(Correct)
The past several years have seen much progress
in the area of propositional reasoning and satisfiability
testing. There is a growing consensus
by researchers on the key technical challenges
that need ... / encode real-world problems such as planning and diagnosis. Contributions to br real-world problems such as planning and diagnosis with others on the
121.7 Knowledge Compilation and Theory Approximation - Selman, Kautz (1996)(Correct)
Computational efficiency is a central concern in the design of knowledge
representation systems. In order to obtain efficient systems, it has been
suggested that one should limit the form of the state... / and certain classes of planning problems Kautz and Selman br our propositional formulation of planning cited above. General
119.9 Active Markov Localization for Mobile Robots - Fox, Burgard, Thrun (1998)(Correct)
Localization is the problem of determining the position of a mobile robot from sensor data. Most existing
localization approaches are passive, i.e., they do not exploit the opportunity to control the ... / with robot control e.g.the planning community assumes that the br In our implementation a global planning module uses dynamic programming
118.8 Passive Distance Learning for Robot Navigation - Koenig, Simmons (1996)(Correct)
Autonomous mobile robots need good models of
their environment, sensors and actuators to navigate
reliably and efficiently. While this information
can be supplied by humans, or learned
from scratch th... / head. Control perception and planning are all carried out ontwo br Improved POMDP Model Planning and Navigation Components
118.1 Experiences with an Interactive Museum Tour-Guide Robot - Burgard, Cremers, Fox, Hähnel.. (1999)(Correct)
This article describes the software architecture of an autonomous, interactive tour-guide
robot. It presents a modular and distributed software architecture, which integrates localization,
mapping, co... / mapping collision avoidance planning and various modules concerned br reasoning localization mapping planning collision avoidance logic
115.9 Query Processing in the SIMS Information Mediator - Arens, Hsu, Knoblock (1996)(Correct)
A critical problem in building an information
mediator is how to translate a domain-level
query into an efficient query plan for accessing
the required data. We have built a flexible
and efficient inf... / have to date is a transportation planning domain with information about br model in the transportation planning domain. In this figure circles
114.2 Learning DFA from Simple Examples - Parekh, Honavar (2001)(Correct)
Efficient learning of DFA is a challenging research problem in grammatical inference. It is known that both exact and approximate (in the PAC sense) identifiability of DFA is hard. Pitt, in his semina... / Allstate Research and Planning Center Middlefield Road br Learning DFA from Simple Examples
109.0 Sequential Optimality and Coordination in Multiagent Systems - Boutilier (1999)(Correct)
Coordination of agent activities is a key problem in multiagent systems. Set in a larger decision theoretic context, the existence of coordination problems leads to difficulty in evaluating the utilit... / activities ranging from logistics planning to robotic soccer. An obvious br and S. Hanks. Decision theoretic planning Structural assumptionsand
109.0 Approximate Planning in Large POMDPs via Reusable Trajectories - Kearns, Mansour, Ng (1999)(Correct)
We consider the problem of reliably choosing a near-best strategy from a restricted class of strategies \Pi in a partially observable Markov decision process (POMDP). In particular, we are interested ... / Approximate Planning in Large POMDPs via Reusable br discuss a number of practical planning algorithms for POMDPs that arise
107.2 Provably bounded optimal agents - Russell, Subramanian, Parr (1993)(Correct)
A program is bounded optimal for a given computational device for a given environment, if the expected utility of the program running on the device in the environment is at least as high as that of al... / in the context of logical planning have been extremely valuable in br view such cognitive faculties' as planning and reasoning as occurring in
101.4 The BATmobile: Towards a Bayesian Automated Taxi - Forbes, Huang, Kanazawa, Russell (1995)(Correct)
The problem of driving an autonomous vehicle in
normal traffic engages many areas of AI research
and has substantial economic significance. We describe
work in progress on a new approach to this
probl... / in charge of overall trip planning and parameters such as desired br for making decisions lookahead planning explicit policy
98.7 Experimental Results on the Application of Satisfiability Algorithms.. - Crawford, Baker (1994)(Correct)
Considerable progress has been made in recent years in understanding and solving propositional satisfiability problems. Much of this work has been based on experiments on randomly generated 3SAT probl... / representation learning planning and other areas of AI are known br In Artificial Intelligence Planning Systems Proceedings of the
98.5 Issues and Approaches in the Design of Collective Autonomous Agents - Mataric (1995)(Correct)
The problem of synthesizing and analyzing collective autonomous agents has only recently begun to be practically studied by the robotics community. This paper overviews the most prominent directions o... / framework and apply a traditional planner-based control architecture to a br the difficulty of multi-agent planning and control in abstract
98.5 Reinforcement Learning with Soft State Aggregation - Singh, Jaakkola, Jordan (1995)(Correct)
It is widely accepted that the use of more compact representations
than lookup tables is crucial to scaling reinforcement learning (RL)
algorithms to real-world problems. Unfortunately almost all of t... / to solve a wide variety of search planning and control problems. br Reinforcement Learning with Soft State Aggregation
95.6 A Randomized Roadmap Method for Path and Manipulation Planning - Amato, Wu (1996)(Correct)
This paper presents a new randomized roadmap method
for motion planning for many dof robots that can be used
to obtain high quality roadmaps even when C-space is
crowded. The main novelty in our appro... / Method For Path And Manipulation Planning Nancy M. Amato Yan br roadmap method for motion planning for many dof robots that can be
95.6 Fast Sequential and Parallel Algorithms for Association Rule Mining.. - Mueller (1995)(Correct)
The field of knowledge discovery in databases, or "Data Mining", has received increasing attention during recent years as large organizations have begun to realize the potential value of the informati... / like marketing product planning store layout advertisement and br . . Meta-Learning and Multi-Strategy-Learning
93.1 A Theory Of Learning Classification Rules - Buntine (1992)(Correct)
The main contributions of this thesis are a Bayesian theory of learning classification rules, the
unification and comparison of this theory with some previous theories of learning, and two extensive
a... / immediately encouraged me to start planning an overseas trip. The Turing br A Theory Of Learning Classification Rules A
92.7 COLLAGEN: When Agents Collaborate with People - Rich, Sidner (1996)(Correct)
We take the position that autonomous agents, when they interact with people, should be governed by the same principles that underlie human collaboration. These principles come from research in computa... / B might collaborate. Finally planning coming to hold the beliefs and br Boston-based sales representative planning your trip home from San
92.7 Finding Structure in Reinforcement Learning - Thrun, Schwartz (1995)(Correct)
Reinforcement learning addresses the problem of learning to select actions in order to
maximize one's performance in unknown environments. To scale reinforcement learning
to complex real-world tasks, ... / comprises a family of incremental planning algorithms that construct br the case with unstructured planning algorithms is that in large
91.4 High-Level Planning and Control with Incomplete Information Using.. - Geffner, Bonet (1998)(Correct)
We develop an approach to planning with incomplete
information that is based on three elements:
1. a high-level language for describing the effects of
actions on both the world and the agent's beliefs... / High-Level Planning and Control with Incomplete br We develop an approach to planning with incomplete information that
91.4 Integrating User Interface Agents with Conventional Applications - Lieberman (1998)(Correct)
In most experiments with user interface agents to date, it
has been necessary either to implement both the agent and
the application from scratch, or to modify the code of an
existing application to e... / only a minimum of advance planning on the part of the application br We present another kind of learning agent Tatlin that compares
91.4 High-Level Planning and Control with Incomplete Information Using.. - Geffner, Bonet (1998)(Correct)
We develop an approach to planning with incomplete
information that is based on three elements:
1. a high-level language for describing the effects of
actions on both the world and the agent's beliefs... / High-Level Planning and Control with Incomplete br We develop an approach to planning with incomplete information that
89.3 Behavior-Based Control: Examples from Navigation, Learning, and Group .. - Mataric (1997)(Correct)
This paper describes the main properties of
behavior-based approaches to control. Different
approaches to designing and using behaviors
as basic units for control, representation,
and learning are ill... / autonomous agent control reactive plannerbased and hybrid. Section br spectrum lie traditional top-down planner-based or deliberative
89.3 Agents for Information Gathering - Knoblock, Ambite (1997)(Correct)
pear in an evolutionary fashion, driven by the market forces of applications that can benefit from using them. We believe that this bottom-up approach can lead more realistically to the development of... / agents in the Logistics Planning application domain. In order to br Agent Transportation Logistics Planning Agent Agent Geographic Agent
86.9 Getting to Know Each Other - Artificial Social Intelligence for.. - Dautenhahn (1995)(Correct)
This paper proposes a research direction to study the development of `artificial
social intelligence' of autonomous robots which should result in `individualized
robot societies'. The approach is high... / the fifth level the programming is planned by the imitator who changes br intelligence' is located in the planning and scheduling routines of the
85.7 Learning Optimal Dialogue Strategies: A Case Study of a Spoken.. - Walker, Fromer, Narayanan (1998)(Correct)
This paper describes a novel method by which a dialogue
agent can learn to choose an optimal dialogue
strategy. While it is widely agreed that dialogue
strategies should be formulated in terms of comm... / Meeting.Decision theoretic planning can be applied to the problem of br . M.T. Maybury. . Planning multi-media explanations using
85.7 Learning First-Order Acyclic Horn Programs from Entailment - Reddy, Tadepalli (1998)(Correct)
In this paper, we consider learning first-order Horn programs
from entailment. In particular, we show that any subclass of first-order
acyclic Horn programs with constant arity is exactly learnable ... / the computational hardness of planning. One kind of control knowledge br clauses are ideally suited in planning one needs to keep track of time.
85.7 Cooperative Multiagent Robotic Systems - Arkin, Balch (1998)(Correct)
Introduction
Teams of robotic systems at first glance might appear to be more trouble than they are worth. Why
not simply build one robot that is capable of doing everything we need? There are severa... / operate without conventional planning or the use of global world br through the use of high-level planners or adaptive learning systems.
84.0 An Active Testing Model for Tracking Roads in Satellite Images - Geman, Jedynak (1996)(Correct)
We present a new approach for tracking roads from satellite images, and thereby
illustrate a general computational strategy ("active testing") for tracking 1D structures
and other recognition tasks in... / use such as cartography urban planning or resource management the raw br in coding CART and machine learning is off-line nonparametric and
83.9 Cooperating Agents for Information Retrieval - Knoblock, Arens, Hsu (1994)(Correct)
With the vast number of information resources available today, a critical problem is how to locate, retrieve and process information. It would be impractical to build a single unified system that comb... / to information for transportation planning. Introduction With the br Source Selection Query Access Planning Semantic Query Reformulation
82.4 Efficient Learning and Planning Within the Dyna Framework - Peng, Williams (1993)(Correct)
Sutton's Dyna framework provides a novel and computationally appealing way to integrate learning, planning, and reacting in autonomous agents. Examined here is a class of strategies designed to enhanc... / Efficient Learning and Planning Within the Dyna Framework Jing br way to integrate learning planning and reacting in autonomous
81.4 Solution Reuse in Dynamic Constraint Satisfaction Problems - Verfaillie, Schiex (1994)(Correct)
Many AI problems can be modeled as constraint
satisfaction problems (CSP), but many of them
are actually dynamic: the set of constraints to
consider evolves because of the environment, the
user or oth... / of real time applications planning scheduling etc.where the br of an interactive design or a planning activity if some work has been
80.8 Connectionist Theory Refinement: Genetically Searching the Space of.. - Opitz, al. (1997)(Correct)
An algorithm that learns from a set of examples should ideally be able to exploit the
available resources of (a) abundant computing power and (b) domain-specific knowledge to
improve its ability to ge... / accuracy. Analogous to anytime planning techniques Dean Boddy br these criteria were created for planning and scheduling algorithms they
79.9 Learning Models for Robot Navigation - Shatkay (1998)(Correct)
Hidden Markov models (hmms) and partially observable Markov decision processes (pomdps)
provide a useful tool for modeling dynamical systems. They are particularly useful for representing
environments... / typical for robot navigation and planning. The work presented here br sound method for localization and planning SK NPB CKK Most other
79.9 Adaptive Behavior in Autonomous Agents - Ziemke (1998)(Correct)
This paper gives an overview of the bottom-up approach to artificial intelligence
(AI), commonly referred to as behavior-oriented AI. The behavior-oriented approach,
with its focus on the interaction ... / cognitive capacities such as planning problem solving or game br into a central world model. A planner based on this internal
79.9 Dynamic Hypertext Catalogues: Helping Users to Help Themselves - Milosavljevic, Oberlander (1998)(Correct)
Electronic hypertext catalogues provide an important channel
for information provision. However, static hypertext documents
cannot be dynamically adapted to help the user find
what he/she is looking f... / It can be viewed as a goal-driven planning process involving the br are borrowed from conventional planning techniques developed within
78.2 On the Complexity of Solving Markov Decision Problems - Littman, Dean, Kaelbling (1995)(Correct)
Markov decision problems (MDPs) provide
the foundations for a number of problems
of interest to AI researchers studying automated
planning and reinforcement learning.
In this paper, we summarize resul... / AI researchers studying automated planning and reinforcement learning. In br for decision-theoretic planning reinforcement learning and
76.5 A Layered Approach to Learning Client Behaviors in the RoboCup Soccer .. - Stone, Veloso (1997)(Correct)
In the past few years, Multiagent Systems (MAS) has emerged as an active subfield of Artificial Intelligence (AI). Because of the inherent complexity of MAS, there is much interest in using Machine Le... / namely RoboCup and MIROSOT planned for the near future br by the DARPA RL Knowledge Based Planning and Scheduling Initiative under
76.5 Steve: An Animated Pedagogical Agent for Procedural Training in.. - Rickel, al. (1997)(Correct)
Jeff Rickel and W. Lewis Johnson
Information Sciences Institute & Computer Science Department
University of Southern California
4676 Admiralty Way, Marina del Rey, CA 90292-6695
(310) 822-1511
Fax: ... / method analogous to partial order planning to keep track of which steps br with pedagogical agents. We are planning a set of evaluations within USC
75.3 Evolutionary Algorithms for Neural Network Design and Training - Branke (1995)(Correct)
Neural networks and genetic algorithms are two relatively young research areas
that were subject to a steadily growing interest during the past years. Both models
are inspired by nature, but whereas n... / neural networks are concerned with learning of an individual phenotypic br of an individual phenotypic learning evolutionary algorithms deal
74.0 Representing Time in Multimedia Systems - Wahl, Rothermel (1994)(Correct)
1
As multimedia system integrate a variety of temporally
interrelated media items, synchronization is an important
issue in those systems. One part of synchronization is the
representation of tempora... / by the user presentation planning by the system and storing br during the specification and planning process when not all events are
69.5 Evolutionary Robotics: the Sussex Approach - Harvey, Husbands, Cliff, Thompson.. (1996)(Correct)
this paper is primarily an overview of our work at Sussex. We discuss what artificial evolutionary techniques are appropriate, followed by discussion of which classes unknown Evolutionary Robotics: th... / decomposition into Perception Planning and Action modules. Many people br the classical Perception Planning Action decomposition of robot
69.5 Evolutionary Design of Neural Architectures - A Preliminary Taxonomy.. - Balakrishnan, Honavar (1995)(Correct)
This report briefly motivates current research on evolutionary design of neural
architectures (EDNA) and presents a short overview of major research issues in
this area. It also includes a preliminary... / inference adaptive control planning robotics etc Evolutionary br Fuzzy Critic for Robotic Motion Planning by Genetic Algorithm in
69.5 High-Performance Job-Shop Scheduling With A Time-Delay TD(lambda).. - Zhang, Dietterich (1995)(Correct)
Job-shop scheduling is an important task for manufacturing industries.
We are interested in the particular task of scheduling payload
processing for NASA's space shuttle program. This paper summarizes... / Control Navigation and Planning Reinforcement Learning br for solution by the reinforcement learning algorithm TD A shortcoming
68.0 Using and combining predictors that specialize - Freund, Schapire, Singer, Warmuth (1997)(Correct)
We study online learning algorithms that predict by combining
the predictions of several subordinate prediction algorithms,
sometimes called "experts." These simple algorithms belong to the
multipli... / making a pre- AT T Labs is planning to move from Murray Hill in . br Abstract. We study online learning algorithms that predict by
68.0 Towards Collaborative and Adversarial Learning: A Case Study in.. - Stone, Veloso (1997)(Correct)
Soccer is a rich domain for the study of multi-agent
learning issues. Not only must the players learn to
adapt to the behavior of different opponents, but they
must learn to work together. We are usin... / real and simulated events of the planned RoboCup event at IJCAI br of this paper the only path planning needed is the ability to steer
66.6 Transportable Information Agents - Gray, Rus, Kotz (1996)(Correct)
We have designed and implemented autonomous software agents. Autonomous software
agents navigate independently through a heterogeneous network. They are capable of sensing
the network configuration, m... / virtual effectors. Classical AI planning techniques are used to synthesize br and Weld EW use classical AI planning techniques to synthesize agents
64.1 Linkability: Examining Causal Link Commitments in Partial-Order.. - Veloso (1994)(Correct)
Recently, several researchers have demonstrated domains where partially-ordered planners outperform totally-ordered planners. In (Barrett & Weld 1994), Barrett and Weld build a series of artificial do... / Link Commitments in Partial-Order Planning Manuela Veloso and Jim br International Conference on AI Planning Systems June . Abstract
63.8 AuRA: Principles and Practice in Review - Arkin, Balch (1997)(Correct)
This paper reviews key concepts of the Autonomous Robot Architecture (AuRA). Its structure, strengths, and roots in biology are presented. AuRA is a hybrid deliberative/reactive robotic architecture t... / a deliberative or hierarchical planner based on traditional artificial br depicted in Figure . Two major planning and execution components are
63.8 Using output codes to boost multiclass learning problems - Schapire (1997)(Correct)
This paper describes a new technique for solving
multiclass learning problems by combining Freund and
Schapire's boosting algorithm with the main ideas of Dietterich
and Bakiri's method of error-cor... / and others. AT T Labs is planning to move from Murray Hill. The new br Machine Learning Proceedings of the Fourteenth
63.8 Adding Animated Presentation Agents to the Interface - Thomas Rist, Elisabeth André, .. (1997)(Correct)
A growing number of research projects both in academia
and industries have started to investigate the use of animated
agents in the interface. Such agents, either based on
real video, cartoon-style dr... / work on multimedia presentation planning. This core approach is br that we sketch the approach for planning dynamic presentations and provide
63.8 Towards a Bayesian Model for Keyhole Plan Recognition in Large Domains - Albrecht, Zuckerman, al. (1997)(Correct)
We present an approach to keyhole plan recognition which uses a Dynamic Belief
Network to represent features of the domain that are needed to identify users' plans
and goals. The structure of this n... / generated the mental state and planning process of the agent and the br by Huber et al. to map planning actions to a Bayesian network.
63.8 Learning Roles: Behavioral Diversity in Robot Teams - Tucker Balch (1997)(Correct)
This paper describes research investigating behavioral
specialization in learning robot teams. Each agent is
provided a common set of skills (motor schema-based
behavioral assemblages) from which it b... / design integrates deliberative planning at a top level with br Learning Roles Behavioral Diversity in
63.7 Planning and Reformulating Queries for Semantically-Modeled.. - Arens (1992)(Correct)
With vast amounts of information available from various
sources, integrating data from multiple databases
is an important problem. The SIMS project attacks
this problem using a variety of Artificial I... / Planning and Reformulating Queries for br techniques including planning knowledge representation
63.7 Landmark-Based Autonomous Navigation in Sewerage Pipes - Hertzberg, Kirchner (1996)(Correct)
We describe a method for an autonomous mobile
robot to navigate through a system of sewerage pipes.
Landmarks signalling positions in the pipe system have
to be detected and classified, where classifi... / and other landmarks so path planning is reduced to graph search in the br and provided that prior path planning has determined that shaft as a
63.7 Pac-learning Recursive Logic Programs: Negative Results - Cohen (1995)(Correct)
In a companion paper it was shown that the class of constant-depth determinate k-ary recursive clauses is efficiently learnable. In this paper we present negative results showing that any natural gene... / paper we suggest that readers planning to read both papers begin with br published Pac-learning Recursive Logic Programs
63.6 Background to Qualitative Decision Theory - Doyle, Thomason (1999)(Correct)
This paper provides an overview of the field of qualitative
decision theory: its motivating tasks and issues, its
antecedents, and its prospects. Qualitative decision theory
studies qualitative approa... / . Decision-theoretic planning . br . . Sympathetic planning .
63.6 Real-time Collision Detection for Virtual Surgery - Lombardo, Cani, Neyret (1999)(Correct)
We present a simple method for performing real-time
collision detection in a virtual surgery environment. The
method relies on the graphics hardware for testing the interpenetration
between a virtual ... / are often required in motion planning application. In our background br the operation onto a screen. Learning to coordinate the motion of the
61.8 Representing Time in Multimedia-Systems - Wahl, Rothermel (1993)(Correct)
As multimedia systems deal with a variety of temporally interrelated media items, synchronization
is an important issue in those systems. One part of synchronization is the representation of
temporal ... / viewing by the user presentation planning by the system and storing br during the specification and planning process when not all events are
60.8 Selecting Input Variables Using Mutual Information and Nonparametric.. - Bonnlander, Weigend (1996)(Correct)
In learning problems where a connectionist network is trained with a finite sized training
set, better generalization performance is often obtained when unneeded weights in the network
are eliminated.... / A necessary assumption if we are planning to estimate the relevance of br Abstract In learning problems where a connectionist
59.5 Complexity Analysis of Real-Time Reinforcement Learning Applied to.. - Koenig, Simmons (1997)(Correct)
This report analyzes the complexity of on-line reinforcement learning algorithms,
namely asynchronous real-time versions of Q-learning and value-iteration, applied to
the problems of reaching any goal... / Search Real-Time Search Planning Path Planning Abstract br Real-Time Search Planning Path Planning Abstract This report
59.5 Complexity Analysis of Real-Time Reinforcement Learning - Koenig, Simmons (1997)(Correct)
This paper analyzes the complexity of on-line reinforcement
learning algorithms, namely asynchronous realtime
versions of Q-learning and value-iteration, applied
to the problem of reaching a goal stat... / cannot be used to solve the path planning tasks since the topology of the br their effects. Thus the path planning tasks have to be solved on-line.
59.5 XBarnacle: Making Theorem Provers More Accessible - Helen Lowe (1997)(Correct)
Introduction
XBarnacle was built to meet the challenge of incorporating interactive features in the
automated theorem prover CLAM whilst preserving the advantages of automation.
Many people are not a... / limitations of the CLAM proof planning system and describe how br CLAM theorem prover . Proof planning CLAM is based on the
59.2 Towards a Principled Representation of Discourse Plans - Young, Moore, Pollack (1994)(Correct)
We argue that discourse plans must capture the intended causal and decompositional relations between communicative actions. We present a planning algorithm, DPOCL, that builds plan structures that pro... / actions. We present a planning algorithm DPOCL that builds br that plagued previous discourse planners and allow a system to
57.9 Parametric Appearance Representation - Nayar, Murase (1996)(Correct)
In contrast to the traditional approach, the recognition problem is formulated
as one of matching appearance rather than shape. For any given
vision task, all possible appearance variations define its... / complex objects an illumination planning technique for robust object br recognition such as illumination planning for robust recognition
57.9 Learning First-Order Definitions of Functions - Quinlan (1996)(Correct)
First-order learning involves finding a clause-form definition of a relation from examples of the relation and relevant background information. In this paper, a particular first-order learning system ... / that improve efficiency in planning applications has a similar br description of the current planning state and goals. As the amount of
57.4 Learning Sequential Decision Rules Using Simulation Models and.. - Grefenstette (1990)(Correct)
The problem of learning decision rules for sequential tasks is addressed,
focusing on the problem of learning tactical decision rules from a simple flight
simulator. The learning method relies on th... / to reactive rather than projective planning Agre Chapman The br Learning Sequential Decision Rules Using
57.1 Bayesian Models for Keyhole Plan Recognition in an Adventure Game - Albrecht, Zukerman, Nicholson (1998)(Correct)
We present an approach to keyhole plan recognition which uses a dynamic belief (Bayesian)
network to represent features of the domain that are needed to identify users' plans and goals. The
applicat... / acquisition of information about planning in an effort to overcome this br generated the mental state and planning process of the agent and the
57.1 Programmable Pattern Generators - Schaal, Sternad (1998)(Correct)
This paper explores the idea to create complex
human-like arm movements from movement primitives
based on nonlinear attractor dynamics. Each degree-offreedom
of an arm is assumed to have two indepen... / potential field approaches for planning e.g.Koditschek and br in one framework task specific planning that can exploit both intrinsic
57.1 Learning from Ambiguity - Maron (1998)(Correct)
There are many learning problems for which the examples given by the teacher are
ambiguously labeled. In this thesis, we will examine one framework of learning from
ambiguous examples known as Multipl... / it on the MUSK dataset. I had been planning to do that eventually but it br Learning from Ambiguity by Oded
57.1 TRIPS: An Integrated Intelligent Problem-Solving Assistant - Ferguson, Allen (1998)(Correct)
We discuss what constitutes an integrated system in AI, and why AI researchers should be interested in building and studying them. Taking integrated systems to be ones that integrate a variety of comp... / dialogue to collaboratively solve planning problems. We discuss how the br processing and in interactive planning and problem solving and consider
56.8 Landmark-Based Robot Navigation - Lazanas, Latombe (1992)(Correct)
Achieving goals despite uncertainty in control and sensing may require robots to
perform complicated motion planning and execution monitoring. This paper describes
a reduced version of the general pla... / to perform complicated motion planning and execution monitoring. This br a reduced version of the general planning problem in the presence of
56.7 Passive Real-World Interface Props for Neurosurgical Visualization - Hinckley (1994)(Correct)
We claim that physical manipulation of familiar real-world
objects in the user's real environment is an important technique
for the design of three-dimensional user interfaces.
These real-world passiv... / world. We present neurosurgical planning as a driving application and br domain is the pre-operative planning of neurosurgical procedures.
55.3 The Origins of Syntax in Visually Grounded Robotic Agents - Steels (1997)(Correct)
The paper proposes a set of principles and a
general architecture that may explain how language
and meaning may originate and complexify
in a group of physically grounded distributed
agents. An experi... / of intelligent behavior such as planning problem solving natural br other cognitive activities like planning cooperation problem solving
55.3 Robot Learning From Demonstration - Atkeson, Schaal (1997)(Correct)
The goal of robot learning from demonstration
is to have a robot learn from watching a
demonstration of the task to be performed.
In our approach to learning from demonstration
the robot learns a rewa... / to perform this task a task planner can use a learned model and br policy this modelbased planning process supports rapid learning
55.0 Coordination Of Multiple Intelligent Software Agents - Sycara, Zeng (1996)(Correct)
this paper we present the distributed system architecture, agent collaboration interactions, and a reusable set of software components for structuring agents. The system architecture has three types o... / agent architecture and discusses planning control and execution br agents continually interleave planning scheduling coordination and
54.5 Accelerating EM: An Empirical Study - Luis Ortiz (1999)(Correct)
Many applications require that we learn the parameters
of a model from data. EM (ExpectationMaximization)
is a method for learning the parameters
of probabilistic models with missing or
hidden data. T... / Fellowship and by DARPA Rome Labs Planning Initiative grant br in part by DARPA Rome Labs Planning Initiative grant
52.1 TD Models: Modeling the World at a Mixture of Time Scales - Sutton (1995)(Correct)
Temporal-difference (TD) learning can be
used not just to predict rewards, as is commonly
done in reinforcement learning, but
also to predict states, i.e., to learn a model
of the world's dynamics. We... / Markov models. This enables planning at higher and varied levels of br for hierarchical or multi-level planning and reinforcement learning. In
52.1 Motion Planning for Car-like Robots using a Probabilistic Learning.. - Petr Svestka (1995)(Correct)
In this paper a recently developed learning approach for robot motion
planning is extended and applied to two types of car-like robots: normal
ones and robots which can only move forwards. In this lea... / Motion Planning for Car-like Robots using a br Tel. - Motion Planning for Car-like Robots using a
51.8 Interaction and Intelligent Behavior - Mataric (1994)(Correct)
This thesis addresses situated, embodied agents interacting in complex domains. It
focuses on two problems: 1) synthesis and analysis of intelligent group behavior, and
2) learning in complex group en... / efficient abstraction for control planning and learning for situated br spectrum lie traditional top-down planner-based deliberative strategies
51.4 Genetic Generation Of Both The Weights And Architecture For A Neural.. - Koza, Rice (1991)(Correct)
This paper shows how to find both the weights and architecture for a neural network (including the number of layers, the number of processing elements per layer, and the connectivity between process... / -multiplexer function planning e.g. navigating an artificial br artificial intelligence machine learning and symbolic processing.
51.4 Choosing Good Distance Metrics and Local Planners for Probabilistic.. - Nancy Amato (1998)(Correct)
This paper presents a comparative evaluation of different distance metrics and local planners within the context
of probabilistic roadmap methods for motion planning. Both C-space and Workspace distan... / Good Distance Metrics and Local Planners for Probabilistic Roadmap br distance metrics and local planners within the context of
51.0 Software Agents: A review - Green, Hurst, Nangle, Cunningham.. (1997)(Correct)
this document.
5 unknown Software Agents: A review
27 May 1997
Trinity College Dublin
Broadcom Éireann Research Ltd.
Shaw Green
Leon Hurst
Brenda Nangle
Dr. Pádraig Cunningham
Fergal Somers
Dr. Ri... / . . Multi-Agent Planning for br Net Protocol . . Multi-Agent Planning for coordination More
49.2 An incremental approach to developing intelligent neural network.. - Meeden (1995)(Correct)
By beginning with simple reactive behaviors and gradually building up to more memorydependent
behaviors, it may be possible for connectionist systems to eventually achieve the
level of planning. This ... / eventually achieve the level of planning. This paper focuses on an br to perform require some kind of planning. If the connectionist approach
49.2 Moving Furniture with Teams of Autonomous Robots - Rus, Donald, Jennings (1995)(Correct)
We wish to organize furniture in a room with a team
of robots that can push objects. We show how coordinated
pushing by robots can change the pose (position
and orientation) of objects and then we ask... / objects and then we ask whether planning global control and explicit br Can we do reorientations without planning iii Can we do reorientations
47.0 Lamarckian Learning in Multi-agent Environments - Grefenstette (1991)(Correct)
Genetic algorithms gain much of their power from
mechanisms derived from the field of population
genetics. However, it is possible, and in some
cases desirable, to augment the standard mechanisms
with... / In such domains traditional AI planning approaches are usually br Unlike an agent in a typical AI planning program our agent generally
46.9 DPOCL: A Principled Approach to Discourse Planning - Young (1994)(Correct)
Research in discourse processing has identified two representational requirements for discourse planning systems. First, discourse plans must adequately represent the intentional structure of the utte... / A Principled Approach to Discourse Planning R. Michael Young br requirements for discourse planning systems. First discourse plans
46.9 A self-organizing representation of sensor space for mobile robot.. - Kröse, Eecen (1994)(Correct)
The paper describes a sensor based navigation
scheme which makes use of a global representation
of the environment by means of a self-organizing
map or Kohonen network. In contrast to existing
methods... / exploration. A conventional path planning technique now gives a path from br are detected and used in the path planning. Results from a simulation show
46.8 A Crash Course in Arrow Logic - Venema (1997)(Correct)
Modal
Logic
'
&
$
%
b
T
T
T
T
TT
c
a
It has manifestations for a manifold of logical formalisms; for instance, in the case of classical
propositional logic (which we may see as a degenerate ... /
46.5 A Theory of Abstraction - Giunchiglia (1992)(Correct)
ion Mappings. In Proc. 10th IJCAI
conference, pages 1011--1014. International Joint Conference on Artificial Intelligence, 1987.
[Ten88] J.D. Tenenberg. Abstraction in Planning. PhD thesis, Computer S... / Developing an abstraction for planning the unfolding of definitions. In br J.D. Tenenberg. Abstraction in Planning. PhD thesis Computer Science
45.7 Learning to Take Actions - Khardon (1998)(Correct)
We formalize a model for supervised learning of action strategies in dynamic stochastic
domains and show that PAC-learning results on Occam algorithms hold in this model
as well. We then identify a cl... / to what is done in the study of planning Allen Hendler Tate br action strategies in small planning domains that have been studied
45.7 Individual Learning of Coordination Knowledge - Sen, Sekaran (1998)(Correct)
Social agents, both human and computational, inhabiting a world containing
multiple active agents, need to coordinate their activities. This is
because agents share resources, and without proper coord... / like knowledge representation planning learning non-monotonic br Simon ffl multi-agent planning Durfee and Lesser
45.7 Theoretical Results on Reinforcement Learning with Temporally.. - Precup, Sutton, Singh (1998)(Correct)
Behaviors
Doina Precup
1
, Richard S. Sutton
1
, and Satinder Singh
2
1
Department of Computer Science
University of Massachusetts
Amherst, MA 01003-4610
http://www.cs.umass.edu/f~dprecupj~richg... / present new theoretical results on planning within the framework of br making system that involves planning and prediction. In temporally
45.7 Remembering to Add: Competence-preserving Case-Addition Policies for.. - Zhu, Yang (1998)(Correct)
Case-base maintenance is gaining increasing
recognition in research and the practical applications
of case-based reasoning (CBR). This
intense interest is highlighted by Smyth and
Keane's research on ... / an experiment in case-based planning. Introduction Case-base br we demonstrate through case-based planning how to construct high-quality
45.7 Landmark-Based Navigation for a Mobile Robot - Owen, Nehmzow (1998)(Correct)
In this paper we present a landmark based navigation
mechanism for a mobile robot. The system uses
a self-organising mechanism to map the environment
as the robot is led around that environment by an
... / for use with the various path planning algorithms that have been br map. . Map interpretation -path planning and execution. These two
45.5 Broad Agents - Bates, Loyall, Reilly (1991)(Correct)
The Oz project at Carnegie Mellon is developing
technology for dramatic virtual worlds.
1
One requirement
of such worlds is the presence of broad,
though perhaps shallow, agents. To support our
need... / to provide reactivity by using a planner in the background feeding a br reacting against the classical planning execution paradigm have
45.4 Learning Action Strategies for Planning Domains - Khardon (1999)(Correct)
This paper reports on experiments where techniques of supervised machine learning are
applied to the problem of planning. The input to the learning algorithm is composed
of a description of a planning... / Learning Action Strategies for Planning Domains Roni Khardon br are applied to the problem of planning. The input to the learning
45.4 ADORE: Adaptive Object Recognition - Draper, Bins, Baek (1999)(Correct)
Many modern computer vision systems are built by chaining
together standard vision procedures, often in graphical programming
environments such as Khoros, CVIPtools or IUE. Typically, these procedur... / have applied AI-style planning technology to infer control br C. Ying and S. Hsiao. Integrated Planning for Automated Image Processing
45.3 SHARE: A Methodology and Environment for Collaborative Product.. - Toye, Cutkosky, Leifer, al. (1993)(Correct)
The SHARE project seeks to apply information
technologies in helping design teams gather, organize,
re-access, and communicate both informal and formal
design information to establish a "shared unders... / for simulation analysis and planning e.g.cost estimation dynamics br as of the Design Review Planning Scheduling References people
44.4 Decomposition and Causality in Partial-Order Planning - Young, Pollack, Moore (1994)(Correct)
We describe DPOCL, a partial-order causal link planner
that includes action decomposition. DPOCL
builds directly on the SNLP algorithm (McAllester &
Rosenblitt 1991), and hence is clear and simple, an... / nd International Conference on AI Planning Systems AIPS pp. - br and Causality in Partial-Order Planning R. Michael Young y and
44.4 The Need for Different Domain-Independent Heuristics - Stone, Veloso, Blythe (1994)(Correct)
PRODIGY's planning algorithm uses domain-independent search heuristics. In this paper, we support our belief that there is no single search heuristic that performs more efficiently than others for all... / Abstract prodigy's planning algorithm uses domain-independent br the main conclusion of this paper planning algorithms need to use different
43.4 Model-Based Learning for Mobile Robot Navigation from the Dynamical.. - Tani (1996)(Correct)
This paper discusses how a behavior-based robot can construct a "symbolic process
" that accounts for its deliberative thinking processes using models of the environment.
The paper focuses on two esse... / account for the cognitive tasks of planning or mental simulation can be br of chaotic dynamics to the planning process and discuss its
43.4 Imitative Learning Mechanisms in Robots and Humans - Demiris, Hayes (1996)(Correct)
We do not exist alone. Humans and most other animal species live in societies
where the behaviour of an individual influences and is influenced by other members of the
society. Within societies, an ... / technologies such as sensing planning action and learning Connell br Imitative Learning Mechanisms in Robots and Humans
43.4 Continuous Localization Using Evidence Grids - Alan Schultz (1996)(Correct)
Evidence grids provide a uniform representation for
fusing temporally and spatially distinct sensor readings.
However, the use of evidence grids requires that
the robot be localized within its environ... / such as navigation and path planning. Fig. shows an evidence grid br for localization have looked at learning and recognizing landmarks in the
43.4 Building and Refining Abstract Planning Cases by Change of.. - Bergmann, Wilke (1995)(Correct)
Planning Cases
by Change of Representation Language
Ralph Bergmann bergmann@informatik.uni-kl.de
Wolfgang Wilke wilke@informatik.uni-kl.de
Centre for Learning Systems and Applications (LSA)
Universi... / Building and Refining Abstract Planning Cases by Change of br -as used in most hierarchical planners -has proven useful. In this
42.8 Parts Feeding on a Conveyor with a One Joint Robot - Akella, Huang, Lynch, Mason (2000)(Correct)
This paper explores a method of manipulating a planar rigid part on a conveyor belt using a
robot with just one joint. This approach has the potential of offering a simple and flexible method for fe... / polygonal parts. We present the planners for these systems and describe br Robotics Manipulation Mechanics Planning Minimalism Automation
42.6 Planning by Incremental Dynamic Programming - Sutton (1991)(Correct)
This paper presents the basic results and ideas of dynamic programming as they relate most directly to the concerns of planning in AI. These form the theoretical basis for the incremental planning met... / - Morgan-Kaufmann Planning by Incremental Dynamic br most directly to the concerns of planning in AI. These form the
42.5 High-Level Planning and Low-Level Execution: Towards a Complete.. - Haigh, Veloso (1997)(Correct)
We have been developing Rogue, an architecture that
integrates high-level planning with a low-level executing
robotic agent. Rogue is designed as the office gofer
task planner for Xavier the robot. Us... / High-Level Planning and Low-Level Execution Towards br that integrates high-level planning with a low-level executing
41.2 Techniques for Requirements Elicitation - Joseph Goguen (1993)(Correct)
This paper surveys and evaluates techniques for eliciting
requirements of computer-based systems, paying particular
attention to how they deal with social issues. The
methods surveyed include introspe... / person-years should be carefully planned and managed. Therefore the br typically preceeded by business planning and is formally initiated by
40.5 Evolving Optimal Populations with XCS Classifier Systems - Kovacs (1996)(Correct)
This work investigates some uses of self-monitoring in classifier systems (CS) using Wilson's recent XCS system as a framework. XCS is a significant advance in classifier systems technology which shif... / it e.g. those which incorporate planning.The current work endeavours to br e.g. those which require planning. . . The Learning System or
40.5 Scaling up goal recognition - Lesh (1996)(Correct)
out of a few predicates. Large libraries arise in the domains in which we have tested our
goal recognizers; namely Unix, Microsoft Windows, and a simulated kitchen domain. We address
the following fo... / plan-operator graphs from work on planning to represent plans more br draws on work from both planning and machine learning. Previous
40.5 Anchoring the Software Process - Boehm (1995)(Correct)
The current proliferation of software process models provides flexibility for
organizations to deal with the unavoidably wide variety of software project
situations, cultures, and environments. But it... / as a basis for software life-cycle planning measuring controlling and br or evolutionary developments pre-planned product improvements annual or
39.9 Alternative Essences of Intelligence - Brooks, (Ferrell), Irie, Kemp.. (1998)(Correct)
We present a novel methodology for building humanlike
artificially intelligent systems. We take as a model
the only existing systems which are universally accepted
as intelligent: humans. We emphasize... / one sees a continuing interest in planning Littman Hauskrecht br jug does not need to be explicitly planned or controlled since it is the
39.9 On the relations between Intelligent Backtracking and Failure-driven.. - Kambhampati (1998)(Correct)
The ideas of intelligent backtracking (IB) and explanation-based learning (EBL) have developed independently in the constraint satisfaction, planning, machine learning and problem solving communities.... / Relations between IB EBL in Planning and CSP On the relations br In Constraint Satisfaction And Planning Asu Cse Tr - Subbarao
39.9 Active Object Recognition in Parametric Eigenspace - Borotschnig, Paletta, Prantl, Pinz (1998)(Correct)
We present an efficient method within an active vision framework for recognizing
objects which are ambiguous from certain viewpoints. The system
is allowed to reposition the camera to capture addition... / gives us a gauge to view planning. View planning is shown to be of br us a gauge to view planning. View planning is shown to be of great use in
39.9 The CMUnited-97 Small Robot Team - Veloso, Stone, Han, Achim (1998)(Correct)
Robotic soccer is a challenging research domain which involves
multiple agents that need to collaborate in an adversarial environment
to achieve specific objectives. In this paper, we describe CMUni... / of collaborative and adversarial planning and learning in real-time br that requires real-time dynamic planning. This paper describes the
39.9 Integrating Reactive and Scripted Behaviors in a Life-Like.. - André, Rist, Müller (1998)(Correct)
Animated agents - based either on real video,
cartoon-style drawings or even model-based
3D graphics - offer great promise for
computer-based presentations as they make
presentations more lively and a... / process which involves AI planning and a two-step compilation. Since br design which combines hierarchical planning with temporal reasoning. .
39.1 Approaches to Abductive Reasoning - An Overview - Paul (1993)(Correct)
Abduction is a form of non-monotonic reasoning that has gained increasing interest
in the last few years. The key idea behind it can be represented by the
following inference rule
' ! !; !
'
;
i.e., ... / Applications to Planning and Plan Recognition . br program debugging cf. CM planning e.g.Esh user modelling
39.1 Evolution of Subsumption Using Genetic Programming - Koza (1993)(Correct)
this paper, we use the genetic
programming paradigm to evolve a computer
program that exhibits emergent behavior and
enables an autonomous mobile robot to follow
the walls of an irregularly shaped roo... / behavior Koza a planning e.g. navigating an artificial br of genetic programming to planning emergent behavior empirical
39.1 Intelligence without Robots (A Reply to Brooks) - Etzioni (1993)(Correct)
In his recent papers, entitled "Intelligence without Representation and "Intelligence without
Reason," Brooks argues for studying complete agents in real-world environments and for
mobile robots as th... / softbot has led us to investigate planning with incomplete information br information interleaving planning and execution and a host of
39.0 Using experience in learning and problem solving - Koton (1989)(Correct)
This paper contains a brief overview of case-based reasoning (CBR) with an emphasis on
European activities in the field. The main objective was to have a balance between brevity
and expressiveness and... / Hammond and others on case-based planning Hammond Collins br have been built to do case-based planning and design among them let us
38.2 Visual architecture and cognitive architecture - Horswill (1997)(Correct)
Traditional architectures have fundamental epistemological
problems. Perception is inherently resource
limited so controlling perception involves all the same
AI-complete problems of reasoning about t... / planing problem. Allowing a planner to transparently assume that the br a problem at least as difficult as planning itself. Although one can imagine
38.2 An On-Line Method to Evolve Behavior and to Control a Miniature Robot .. - Nordin, Banzhaf (1997)(Correct)
We present a novel evolutionary approach to robotic control of a real
robot based on genetic programming (GP). Our approach uses genetic
programming techniques that manipulate machine code to evolve c... / behavior characteristic of planning systems. Floreano and Mondada br systems. Both reactive and planning rules are implemented using what
38.2 A Competitive Genetic Algorithm for Resource-Constrained Project.. - Hartmann (1997)(Correct)
In this paper we consider the resource-constrained project scheduling problem
(RCPSP) with makespan minimization as objective. We propose a new genetic algorithm
approach to solve this problem. Subseq... / as within systems for production planning and scheduling. The currently br search optimization and machine learning. Addison-Wesley Reading
37.6 CBR in Context: The Present and Future - Leake (1996)(Correct)
This chapter provides an introduction to case-based reasoning, discusses motivations for CBR, and describes the central steps in the CBR process. It examines the relationship of CBR to other approache... / such as explanation and planning are NP-hard Bylander et al. br For example a case-based planning system generates a new plan by
37.6 PSPLIB - A project scheduling problem library - Kolisch, Sprecher (1996)(Correct)
We present a set of benchmark instances for the evaluation of solution procedures for singleand
multi-mode resource-constrained project scheduling problems. The instances have been systematically
gene... / resourceconstrained project planning problems with minimal and maximal
37.6 Multi-Strategy Learning of Search Control for Partial-Order Planning - Estlin, Mooney (1996)(Correct)
Most research in planning and learning has involved
linear, state-based planners. This paper presents
Scope, a system for learning search-control rules
that improve the performance of a partial-order... / Search Control for Partial-Order Planning Tara A. Estlin and Raymond br Abstract Most research in planning and learning has involved
37.6 Is There Any Need for Domain-Dependent Control Information? A Reply - Minton (1996)(Correct)
In this paper, we consider the role that domaindependent
control knowledge plays in problem
solving systems. Ginsberg and Geddis (Ginsberg
& Geddis 1991) have claimed that domaindependent
control info... / For instance they consider planning a trip from Stanford to MIT. The br control knowledge is this When planning a long trip plan the airplane
37.6 Bayesian Learning in Negotiation - Zeng (1996)(Correct)
This paper appears in the Working Notes of the
AAAI 1996 Stanford Spring Symposium Series on Adaptation,
Co-evolution and Learning in Multiagent Systems. unknown Bayesian Learning in Negotiation
Dajun... / model by integrating AI planning Case-Based Reasoning and other br Sycara K. . Negotiation planning An AI approach. European