Robot hands and the mechanics of manipulation
Robot hands and the mechanics of manipulation
The Continuum-Armed Bandit Problem
SIAM Journal on Control and Optimization
Active learning for vision-based robot grasping
Machine Learning - Special issue on robot learning
Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Finite-time Analysis of the Multiarmed Bandit Problem
Machine Learning
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Multi-armed bandits in metric spaces
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
Reactive grasping using optical proximity sensors
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Improved rates for the stochastic continuum-armed bandit problem
COLT'07 Proceedings of the 20th annual conference on Learning theory
Iterative learning of grasp adaptation through human corrections
Robotics and Autonomous Systems
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
Learning via human feedback in continuous state and action spaces
Applied Intelligence
Hi-index | 0.00 |
Grasping an object is a task that inherently needs to be treated in a hybrid fashion. The system must decide both where and how to grasp the object. While selecting where to grasp requires learning about the object as a whole, the execution only needs to reactively adapt to the context close to the grasp's location. We propose a hierarchical controller that reflects the structure of these two sub-problems, and attempts to learn solutions that work for both. A hybrid architecture is employed by the controller to make use of various machine learning methods that can cope with the large amount of uncertainty inherent to the task. The controller's upper level selects where to grasp the object using a reinforcement learner, while the lower level comprises an imitation learner and a vision-based reactive controller to determine appropriate grasping motions. The resulting system is able to quickly learn good grasps of a novel object in an unstructured environment, by executing smooth reaching motions and preshaping the hand depending on the object's geometry. The system was evaluated both in simulation and on a real robot.