Intelligence without representation
Artificial Intelligence
Symbolic Boolean manipulation with ordered binary-decision diagrams
ACM Computing Surveys (CSUR)
Neural networks and the bias/variance dilemma
Neural Computation
Efficient learning and planning within the Dyna framework
Adaptive Behavior
Robot grasp synthesis algorithms: a survey
International Journal of Robotics Research
Planning and acting in partially observable stochastic domains
Artificial Intelligence
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Neuro-Dynamic Programming
Object-based queries using color points of interest
CBAIVL '01 Proceedings of the IEEE Workshop on Content-based Access of Image and Video Libraries (CBAIVL'01)
Task-Driven Learning of Spatial Combinations of Visual Features
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
Interactive learning of mappings from visual percepts to actions
ICML '05 Proceedings of the 22nd international conference on Machine learning
Robotic Grasping of Novel Objects using Vision
International Journal of Robotics Research
Reinforcement learning for robot soccer
Autonomous Robots
Learning object-specific grasp affordance densities
DEVLRN '09 Proceedings of the 2009 IEEE 8th International Conference on Development and Learning
A Probabilistic Framework for 3D Visual Object Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Closed-loop learning of visual control policies
Journal of Artificial Intelligence Research
Learning Objects and Grasp Affordances through Autonomous Exploration
ICVS '09 Proceedings of the 7th International Conference on Computer Vision Systems: Computer Vision Systems
A strategy for grasping unknown objects based on co-planarity and colour information
Robotics and Autonomous Systems
Task-Driven discretization of the joint space of visual percepts and continuous actions
ECML'06 Proceedings of the 17th European conference on Machine Learning
Learning Object Affordances: From Sensory--Motor Coordination to Imitation
IEEE Transactions on Robotics
Active learning of visual descriptors for grasping using non-parametric smoothed beta distributions
Robotics and Autonomous Systems
Reinforcement learning in robotics: A survey
International Journal of Robotics Research
Hi-index | 0.00 |
We discuss vision as a sensory modality for systems that interact flexibly with uncontrolled environments. Instead of trying to build a generic vision system that produces task-independent representations, we argue in favor of task-specific, learn-able representations. This concept is illustrated by two examples of our own work. First, our RLVC algorithm performs reinforcement learning directly on the visual input space. To make this very large space manageable, RLVC interleaves the reinforcement learner with a supervised classification algorithm that seeks to split perceptual states so as to reduce perceptual aliasing. This results in an adaptive discretization of the perceptual space based on the presence or absence of visual features. Its extension, RLJC, additionally handles continuous action spaces. In contrast to the minimalistic visual representations produced by RLVC and RLJC, our second method learns structural object models for robust object detection and pose estimation by probabilistic inference. To these models, the method associates grasp experiences autonomously learned by trial and error. These experiences form a non-parametric representation of grasp success likelihoods over gripper poses, which we call a grasp density. Thus, object detection in a novel scene simultaneously produces suitable grasping options.