Learning from Successful and Failed Demonstrations via Optimization
This addresses the challenge of sub-optimal demonstrations in robot learning, offering a more efficient way to utilize human-provided data, though it is incremental as it builds on existing Learning from Demonstration methods.
The paper tackles the problem of learning robot skills from both successful and failed human demonstrations, proposing a method that encodes these into a statistical model and optimizes skill reproduction under new constraints, achieving improved performance over existing approaches in real-world experiments with a UR5e manipulator.
Learning from Demonstration (LfD) is a popular approach that allows humans to teach robots new skills by showing the correct way(s) of performing the desired skill. Human-provided demonstrations, however, are not always optimal and the teacher usually addresses this issue by discarding or replacing sub-optimal (noisy or faulty) demonstrations. We propose a novel LfD representation that learns from both successful and failed demonstrations of a skill. Our approach encodes the two subsets of captured demonstrations (labeled by the teacher) into a statistical skill model, constructs a set of quadratic costs, and finds an optimal reproduction of the skill under novel problem conditions (i.e. constraints). The optimal reproduction balances convergence towards successful examples and divergence from failed examples. We evaluate our approach through several 2D and 3D experiments in real-world using a UR5e manipulator arm and also show that it can reproduce a skill from only failed demonstrations. The benefits of exploiting both failed and successful demonstrations are shown through comparison with two existing LfD approaches. We also compare our approach against an existing skill refinement method and show its capabilities in a multi-coordinate setting.