Results 1 - 10
of
28
Adaptive Control for Autonomous Underwater Vehicles
- in AAAI
, 2008
"... We describe a novel integration of Planning with Probabilistic State Estimation and Execution resulting in a unified representational and computational framework based on declarative models and constraint-based temporal plans. The work is motivated by the need to explore the oceans more cost-effecti ..."
Abstract
-
Cited by 31 (13 self)
- Add to MetaCart
We describe a novel integration of Planning with Probabilistic State Estimation and Execution resulting in a unified representational and computational framework based on declarative models and constraint-based temporal plans. The work is motivated by the need to explore the oceans more cost-effectively through the use of Autonomous Underwater Vehicles (AUV), requiring them to be goal-directed, perceptive, adaptive and robust in the context of dynamic and uncertain conditions. The novelty of our approach is in integrating deliberation and reaction over different temporal and functional scopes within a single model, and in breaking new ground in oceanography by allowing for precise sampling within a feature of interest using an autonomous robot. The system is general-purpose and adaptable to other ocean going and terrestrial platforms.
In Situ Analysis for Intelligent Control
"... Abstract—We report a pilot study on in situ analysis of backscatter data for intelligent control of a scientific instrument on an Autonomous Underwater Vehicle (AUV) carried out at the Monterey Bay Aquarium Research Institute (MBARI). The objective of the study is to investigate techniques which use ..."
Abstract
-
Cited by 12 (4 self)
- Add to MetaCart
(Show Context)
Abstract—We report a pilot study on in situ analysis of backscatter data for intelligent control of a scientific instrument on an Autonomous Underwater Vehicle (AUV) carried out at the Monterey Bay Aquarium Research Institute (MBARI). The objective of the study is to investigate techniques which use machine intelligence to enable event-response scenarios. Specifically we analyse a set of techniques for automated sample acquisition in the water-column using an electro-mechanical “Gulper”, designed at MBARI. This is a syringe-like sampling device, carried onboard an AUV. The techniques we use in this study are clustering algorithms, intended to identify the important distinguishing characteristics of bodies of points within a data sample. We demonstrate that the complementary features of two clustering approaches can offer robust identification of interesting features in the water-column, which, in turn, can support automatic event-response control in the use of the Gulper. I.
Onboard adaptive control of AUVs using automated planning and execution
- in Proc. Int. Symp. Unmanned Untethered Submersible Technol
, 2009
"... In this paper we describe an integrated goal-oriented control architecture for onboard decision-making for AUVs. Onboard planning and execution is augmented by state estimation of perceived features of interest in the coastal ocean, to drive platform adaptation. The parti-tioned architecture is a co ..."
Abstract
-
Cited by 5 (0 self)
- Add to MetaCart
(Show Context)
In this paper we describe an integrated goal-oriented control architecture for onboard decision-making for AUVs. Onboard planning and execution is augmented by state estimation of perceived features of interest in the coastal ocean, to drive platform adaptation. The parti-tioned architecture is a collection of coordinated control loops, with a recurring sense, plan, act cycle and which allows for plan failures to be localized within a control loop and ensures a divide-and-conquer approach to prob-lem solving in dynamic environments. 1
Learning Behaviors Models for Robot Execution Control
, 2006
"... Robust execution of robotic tasks is a difficult problem. In many situations, these tasks involve complex behaviors combining different functionalities (e.g. perception, localization, motion planning and motion execution). These behaviors are often programmed with a strong focus on the robustness of ..."
Abstract
-
Cited by 4 (0 self)
- Add to MetaCart
(Show Context)
Robust execution of robotic tasks is a difficult problem. In many situations, these tasks involve complex behaviors combining different functionalities (e.g. perception, localization, motion planning and motion execution). These behaviors are often programmed with a strong focus on the robustness of the behavior itself, not on the definition of a “high level” model to be used by a task planner and an execution controller. We propose to learn behaviors models as structured stochastic processes: Dynamic Bayesian Network. Indeed, the DBN formalism allows us to learn and control behaviors with controllable parameters. We experimented our approach on a real robot, where we learned over a large number of runs the model of a complex navigation task using a modified version of Expectation Maximization for DBN. The resulting
Unsupervised learning and recognition of physical activity plans
- Master’s thesis, Massachusetts Institute of Technology
, 2007
"... This thesis desires to enable a new kind of interaction between humans and compu-tational agents, such as robots or computers, by allowing the agent to anticipate and adapt to human intent. In the future, more robots may be deployed in situations that require collaboration with humans, such as scien ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
This thesis desires to enable a new kind of interaction between humans and compu-tational agents, such as robots or computers, by allowing the agent to anticipate and adapt to human intent. In the future, more robots may be deployed in situations that require collaboration with humans, such as scientific exploration, search and rescue, hospital assistance, and even domestic care. These situations require robots to work together with humans, as part of a team, rather than as a stand-alone tool. The intent recognition capability is necessary for computational agents to play a more collab-orative role in human-robot interactions, moving beyond the standard master-slave relationship of humans and computers today. We provide an innovative capability for recognizing human intent, through statis-tical plan learning and online recognition. We approach the plan learning problem by employing unsupervised learning to automatically determine the activities in a plan based on training data. The plan activities are described by a mixture of multivariate probability densities. The number of distributions in the mixture used to describe
Using Learned Action Models in Execution Monitoring
"... Planners reason with abstracted models of the behaviours they use to construct plans. When plans are turned into the instructions that drive an executive, the real behaviours interacting with the unpredictable uncertainties of the environment can lead to failure. One of the challenges for intelligen ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Planners reason with abstracted models of the behaviours they use to construct plans. When plans are turned into the instructions that drive an executive, the real behaviours interacting with the unpredictable uncertainties of the environment can lead to failure. One of the challenges for intelligent autonomy is to recognise when the actual execution of a behaviour has diverged so far from the expected behaviour that it can be considered to be a failure. In this paper we present further developments of the work described in (Fox et al. 2006), where models of behaviours were learned as Hidden Markov Models. Execution of behaviours is monitored by tracking the most likely trajectory through such a learned model, while possible failures in execution are identified as deviations from common patterns of trajectories within the learned models. We present results for our experiments with a model learned for a robot behaviour. 1
Detecting Execution Failures Using Learned Action Models
- AAAI Proceedings
, 2007
"... Planners reason with abstracted models of the behaviours they use to construct plans. When plans are turned into the instructions that drive an executive, the real behaviours in-teracting with the unpredictable uncertainties of the environ-ment can lead to failure. One of the challenges for intellig ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Planners reason with abstracted models of the behaviours they use to construct plans. When plans are turned into the instructions that drive an executive, the real behaviours in-teracting with the unpredictable uncertainties of the environ-ment can lead to failure. One of the challenges for intelligent autonomy is to recognise when the actual execution of a be-haviour has diverged so far from the expected behaviour that it can be considered to be a failure. In this paper we present an approach by which a trace of the execution of a behaviour is monitored by tracking its most likely explanation through a learned model of how the behaviour is normally executed. In this way, possible failures are identified as deviations from common patterns of the execution of the behaviour. We per-form an experiment in which we inject errors into the be-haviour of a robot performing a particular task, and explore how well a learned model of the task can detect where these errors occur. 1
Learning the Behavior Model of a Robot
"... Complex artifacts are designed today from well specified and well modeled components. But most often, the models of these components cannot be composed into a global functional model of the artifact. A significant observation, modeling and identification effort is required to get such a global model ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Complex artifacts are designed today from well specified and well modeled components. But most often, the models of these components cannot be composed into a global functional model of the artifact. A significant observation, modeling and identification effort is required to get such a global model, which is needed in order to better understand, control and improve the designed artifact. Robotics provides a good illustration of this need. Autonomous robots are able to achieve more and more complex tasks, relying on more advanced sensori-motor functions. To better understand their behavior and improve their performance, it becomes necessary but more difficult to characterize and to model, at the global level, how robots behave in a given environment. Low-level models of sensors, actuators and controllers cannot be easily combined into a behavior model. Sometimes high level models operators used for planning are also available, but generally they are too coarse to represent the actual robot behavior. We propose here a general framework for learning from observation data the behavior model of a robot when performing a given task. The behavior is modeled as a Dynamic Bayesian Network, a convenient stochastic structured representations. We show how such a probabilistic model can be learned and how it can be used to improve, on line, the robot behavior with respect to a specific environment and user preferences. Framework and algorithms are detailed; they are substantiated by experimental results for autonomous navigation tasks. 1 1
1An Agent-based Implementation of Hidden Markov Models for Gas Turbine Condition Monitoring
"... Abstract—This paper considers the use of a multi-agent sys-tem (MAS) incorporating hidden Markov models (HMMs) for the condition monitoring of gas turbine (GT) engines. Hidden Markov models utilizing a Gaussian probability distribution are proposed as an anomaly detection tool for gas turbines compo ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract—This paper considers the use of a multi-agent sys-tem (MAS) incorporating hidden Markov models (HMMs) for the condition monitoring of gas turbine (GT) engines. Hidden Markov models utilizing a Gaussian probability distribution are proposed as an anomaly detection tool for gas turbines components. The use of this technique is shown to allow the modeling of the dynamics of GTs despite a lack of high frequency data. This allows the early detection of developing faults and avoids costly outages due to asset failure. These models are implemented as part of a MAS, using a proposed extension of an established power system ontology, for fault detection of gas turbines. The multi-agent system is shown to be applicable through a case study and comparison to an existing system utilizing historic data from a combined-cycle gas turbine plant provided by an industrial partner.
Qualitative Hidden Markov Models for Classifying Gene Expression Data
"... Abstract. Hidden Markov Models (HMMs) have been successfully used in tasks involving prediction and recognition of patterns in sequence data, with applications in areas such as speech recognition and bioinformatics. While variations of traditional HMMs proved to be practical in applications where it ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract. Hidden Markov Models (HMMs) have been successfully used in tasks involving prediction and recognition of patterns in sequence data, with applications in areas such as speech recognition and bioinformatics. While variations of traditional HMMs proved to be practical in applications where it is feasible to obtain the numerical probabilities required for the specification of the parameters of the model and the probabilities available are descriptive of the underlying uncertainty, the capabilities of HMMs remain unexplored in applications where this convenience is not available. Motivated by such applications, we present a HMM that uses qualitative probabilities instead of quantitative ones. More specifically, the HMM presented here captures the order of magnitude of the probabilities involved instead of numerical probability values. We analyze the resulting model by using it to perform classification tasks on gene expression data. 1
