Learning tracking control with forward models

Performing task-space tracking control on redundant robot manipulators is a difficult problem. When the physical model of the robot is too complex or not available, standard methods fail and machine learning algorithms can have advantages. We propose an adaptive learning algorithm for tracking control of underactuated or non-rigid robots where the physical model of the robot is unavailable. The control method is based on the fact that forward models are relatively straightforward to learn and local inversions can be obtained via local optimization. We use sparse online Gaussian process inference to obtain a flexible probabilistic forward model and second order optimization to find the inverse mapping. Physical experiments indicate that this approach can outperform state-of-the-art tracking control algorithms in this context.

Authors

• Botond Bocsi
• Philipp Hennig
• Lehel Csató
• Jan Peters 0001

Keywords

• Kinematics
• Robots
• Joints
• Adaptation models
• Mathematical model
• Trajectory
• Predictive models
• Forward Model
• Tracking Control
• Learning Algorithms
• Control Method
• Local Optimum
• Gaussian Process
• Robot Control
• Robot Manipulator
• Physical Experiments
• Robot Model
• Inverse Mapping
• Neural Network
• Degrees Of Freedom
• Machine Learning Methods
• Energy Function
• Number Of Data Points
• Centrifugal Force
• Inverse Function
• Inverse Model
• Inverse Kinematics
• Joint Configuration
• Gaussian Process Model
• Inverse Dynamics
• Gradient Search
• Base Point
• Ball Position
• Input Space
• Global Consistency
• Exponential Kernel