Results 1 -
6 of
6
EM-ONE: An Architecture for Reflective Commonsense Thinking
, 2005
"... This thesis describes EM-ONE, an architecture for commonsense thinking capable of reflective reasoning about situations involving physical, social, and mental dimensions. EM-ONE uses as its knowledge base a library of commonsense narratives, each describing the physical, social, and mental activity ..."
Abstract
-
Cited by 48 (0 self)
- Add to MetaCart
This thesis describes EM-ONE, an architecture for commonsense thinking capable of reflective reasoning about situations involving physical, social, and mental dimensions. EM-ONE uses as its knowledge base a library of commonsense narratives, each describing the physical, social, and mental activity that occurs during an interaction between several actors. EM-ONE reasons with these narratives by applying "mental critics, " procedures that debug problems that exist in the outside world or within EM-ONE itself. Mental critics draw upon commonsense narratives to suggest courses of action, methods for deliberating about the circumstances and consequences of those actions, and—when things go wrong—ways to reflect upon and debug the activity of previously invoked mental critics. Mental critics are arranged into six layers, the reactive, deliberative, reflective, self-reflective, self-conscious, and self-ideals layers. The selection of mental critics within these six layers is itself guided by a separate collection
EventMinder: A Personal Calendar Assistant That Understands Events
- Master Thesis, MIT
, 2007
"... Calendar applications do not understand calendar entries. This limitation prevents them from offering the range of assistant that can be provided by a human personal assistant. Understanding calendar entries is a difficult problem because it involves integrating many types of knowledge: commonsense ..."
Abstract
-
Cited by 4 (0 self)
- Add to MetaCart
(Show Context)
Calendar applications do not understand calendar entries. This limitation prevents them from offering the range of assistant that can be provided by a human personal assistant. Understanding calendar entries is a difficult problem because it involves integrating many types of knowledge: commonsense knowledge, about common events and the the partic-ular instances in the world, and user knowledge about the individual’s preferences and goals. In this thesis, I present two models of event understanding: Romulus and Julius. Romulus addresses the problem of how missing information in a calendar entry can be filled in by having an event structure, goal knowledge, and past examples. This system is able to learns by observing the user, and constrains its inductive hypothesis by using knowledge about common goals specific to the event. Although this model is capable of representing some tasks, its structural assumptions limit the range of events that it can represent. Julius treats the event understanding problem as a plan retrieval problem, and draws
Acquisition of Procedural Commonsense Knowledge in a 3-D Simulated World
, 2006
"... In this paper we describe the design of a solution for the acquisition of procedural commonsense knowledge in a situated simulated environment. In this system, users in a simulated game environment, control virtual robots to do various tasks in a real world scenario. In the current system, users are ..."
Abstract
- Add to MetaCart
In this paper we describe the design of a solution for the acquisition of procedural commonsense knowledge in a situated simulated environment. In this system, users in a simulated game environment, control virtual robots to do various tasks in a real world scenario. In the current system, users are situated in a restaurant scenario and take charge of teaching their apprentice robots actions to complete tasks. The main benefit of situating acquisition of knowledge in a real world environment is that procedures and actions in situations get learnt in many different realms of thought and at many different levels of detail ultimately learning a task in many ways.
LIBRARIES EventMinder: A Personal Calendar Assistant That Understands Events
, 2007
"... Calendar applications do not understand calendar entries. This limitation prevents them from offering the range of assistance that can be provided by a human personal assistant. Understanding calendar entries is a difficult problem because it involves integrating many types of knowledge: commonsense ..."
Abstract
- Add to MetaCart
(Show Context)
Calendar applications do not understand calendar entries. This limitation prevents them from offering the range of assistance that can be provided by a human personal assistant. Understanding calendar entries is a difficult problem because it involves integrating many types of knowledge: commonsense knowledge, about common events and the particular in-stances in the world, and user knowledge about the individual's preferences and goals. In this thesis, I present two models of event understanding: ROMULUS and JULIUS. ROMULUS addresses the problem of how missing information in a calendar entry can be filled in by having an event structure, goal knowledge, and past examples. This system is able to learn by observing the user, and constrains its inductive hypothesis by using knowledge about common goals specific to the event. Although this model is capable of representing some tasks, its structural assumptions limit the range of events that it can represent. JULIUS treats event understanding as a plan retrieval problem, and draws from the COMET plan library of 295 everyday plans to interpret the calendar entry. These plans
Panalogies for Common Sense Reasoning
, 2006
"... The Open Mind Common Sense project has a goal of giving computers access to the kind of basic information that people inherently know and use all the time to think about the world. This is the knowledge that will allow computers to think more like people, as long as they have an effective way to acc ..."
Abstract
- Add to MetaCart
(Show Context)
The Open Mind Common Sense project has a goal of giving computers access to the kind of basic information that people inherently know and use all the time to think about the world. This is the knowledge that will allow computers to think more like people, as long as they have an effective way to access and use that knowledge.
