Learning Multi-Reference Frame Skills from Demonstration with Task-Parameterized Gaussian Processes

A central challenge in Learning from Demonstration is to generate representations that are adaptable and can generalize to unseen situations. This work proposes to learn such a representation without using task-specific heuristics within the context of multi-reference frame skill learning by superimposing local skills in the global frame. Local policies are first learned by fitting the relative skills with respect to each frame using Gaussian Processes (GPs). Then, another GP, which determines the relevance of each frame for every time step, is trained in a self-supervised manner from a different batch of demonstrations. The uncertainty quantification capability of GPs is exploited to stabilize the local policies and to train the frame relevance in a fully Bayesian way. We validate the method through a dataset of multi-frame tasks generated in simulation and on real-world experiments with a robotic manipulation pick-and-place re-shelving task. We evaluate the performance of our method with two metrics: how close the generated trajectories get to each of the task goals and the deviation between these trajectories and test expert trajectories. According to both of these metrics, the proposed method consistently outperforms the state-of-the-art baseline, Task-Parameterised Gaussian Mixture Model (TPGMM).

Authors

• Mariano Ramírez Montero
• Giovanni Franzese
• Jens Kober
• Cosimo Della Santina

Keywords

• Measurement
• Uncertainty
• Fitting
• Trajectory
• Bayes methods
• Intelligent robots
• Gaussian mixture model
• Gaussian Process
• Time Step
• Local Policy
• Learning Context
• Robot Manipulator
• Uncertainty Quantification
• Global Frame
• Inverse Reinforcement Learning
• Training Data
• System Dynamics
• Performance Metrics
• Simulation Experiments
• Morphine
• Hidden Markov Model
• Minimum Variance
• Predictive Distribution
• Coordinate Frame
• Fiducial Markers
• Training Labels
• Dynamic Time Warping
• Training Configurations
• Local Frame
• Origin Of Frame
• Linear Quadratic Regulator
• Test Configuration
• Number Of Demonstrations