Optimal redundancy control of robot manipulators
International Journal of Robotics Research
Similarity metric learning for a variable-kernel classifier
Neural Computation
Randomized query processing in robot path planning
STOC '95 Proceedings of the twenty-seventh annual ACM symposium on Theory of computing
From egocentric to allocentric spatial behavior: a computational model of spatial development
Adaptive Behavior - Special issue on biologically inspired models of navigation
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
An inverse kinematics architecture enforcing an arbitrary number of strict priority levels
The Visual Computer: International Journal of Computer Graphics - Special section on implicit surfaces
Recognition and reproduction of gestures using a probabilistic framework combining PCA, ICA and HMM
ICML '05 Proceedings of the 22nd international conference on Machine learning
Autonomous shaping: knowledge transfer in reinforcement learning
ICML '06 Proceedings of the 23rd international conference on Machine learning
A Generalized Path Integral Control Approach to Reinforcement Learning
The Journal of Machine Learning Research
A policy-blending formalism for shared control
International Journal of Robotics Research
Hi-index | 0.00 |
Trajectory planning and optimization is a fundamental problem in articulated robotics. Algorithms used typically for this problem compute optimal trajectories from scratch in a new situation. In effect, extensive data is accumulated containing situations together with the respective optimized trajectories - but this data is in practice hardly exploited. The aim of this paper is to learn from this data. Given a new situation we want to predict a suitable trajectory which only needs minor refinement by a conventional optimizer. Our approach has two essential ingredients. First, to generalize from previous situations to new ones we need an appropriate situation descriptor - we propose a sparse feature selection approach to find such well-generalizing features of situations. Second, the transfer of previously optimized trajectories to a new situation should not be made in joint angle space - we propose a more efficient task space transfer of old trajectories to new situations. Experiments on a simulated humanoid reaching problem show that we can predict reasonable motion prototypes in new situations for which the refinement is much faster than an optimization from scratch.