Analogical representations of naive physics
Artificial Intelligence
Cyc: toward programs with common sense
Communications of the ACM
Readings in qualitative reasoning about physical systems
Readings in qualitative reasoning about physical systems
What computers still can't do: a critique of artificial reason
What computers still can't do: a critique of artificial reason
Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
The challenge of qualitative spatial reasoning
ACM Computing Surveys (CSUR)
CYC: a large-scale investment in knowledge infrastructure
Communications of the ACM
Maintaining knowledge about temporal intervals
Communications of the ACM
Qualitative Representation of Spatial Knowledge
Qualitative Representation of Spatial Knowledge
Introduction to Bayesian Networks
Introduction to Bayesian Networks
Building Large Knowledge-Based Systems; Representation and Inference in the Cyc Project
Building Large Knowledge-Based Systems; Representation and Inference in the Cyc Project
Computational Perception of Scene Dynamics
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
A Maximum-Likelihood Approach to Visual Event Classification
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
Qualitative Spatial Representation and Reasoning Techniques
KI '97 Proceedings of the 21st Annual German Conference on Artificial Intelligence: Advances in Artificial Intelligence
Building Qualitative Event Models Automatically from Visual Input
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
A comprehensive human computation framework: with application to image labeling
MM '08 Proceedings of the 16th ACM international conference on Multimedia
A Qualitative Hidden Markov Model for Spatio-temporal Reasoning
ECSQARU '07 Proceedings of the 9th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty
Robotics and Autonomous Systems
Hi-index | 0.00 |
Autonomous robots are unsuccessful at operating in complex, unconstrained environments. They lack the ability to learn about the physical behaviour of different objects. We examine the viability of using qualitative spatial representations to learn general physical behaviour by visual observation. We combine Bayesian networks with the spatial representations to test them. We input training scenarios that allow the system to observe and learn normal physical behaviour. The position and velocity of the visible objects are represented as discrete states. Transitions between these states over time are entered as evidence into a Bayesian network. The network provides probabilities of future transitions to produce predictions of future physical behaviour. We use test scenarios to determine how well the approach discriminates between normal and abnormal physical behaviour and actively predicts future behaviour. We examine the ability of the system to learn three naive physical concepts, 'no action at a distance', 'solidity' and 'movement on continuous paths'. We conclude that the combination of qualitative spatial representations and Bayesian network techniques is capable of learning these three rules of naive physics.