Learning from Successful and Failed Demonstrations via Optimization

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.

[1]  Aude Billard,et al.  On Learning, Representing, and Generalizing a Task in a Humanoid Robot , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[2]  Vivian Chu,et al.  Benchmark for Skill Learning from Demonstration: Impact of User Experience, Task Complexity, and Start Configuration on Performance , 2019, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[3]  Aude Billard,et al.  Learning control Lyapunov function to ensure stability of dynamical system-based robot reaching motions , 2014, Robotics Auton. Syst..

[4]  Sandra Hirche,et al.  Spatial adaption of robot trajectories based on laplacian trajectory editing , 2016, Auton. Robots.

[5]  Darwin G. Caldwell,et al.  Robot motor skill coordination with EM-based Reinforcement Learning , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Aude Billard,et al.  Donut as I do: Learning from failed demonstrations , 2011, 2011 IEEE International Conference on Robotics and Automation.

[7]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[8]  Byron Boots,et al.  Learning Generalizable Robot Skills from Demonstrations in Cluttered Environments , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[9]  Stefan Schaal,et al.  Learning and generalization of motor skills by learning from demonstration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[10]  Eamonn J. Keogh,et al.  Scaling up dynamic time warping for datamining applications , 2000, KDD '00.

[11]  Sonia Chernova,et al.  Skill Acquisition via Automated Multi-Coordinate Cost Balancing , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[12]  Kai Zheng,et al.  A survey of trajectory distance measures and performance evaluation , 2019, The VLDB Journal.

[13]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[14]  Sonia Chernova,et al.  Trajectory-Based Skill Learning Using Generalized Cylinders , 2018, Front. Robot. AI.

[15]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[16]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[17]  Eric L. Sauser,et al.  Tactile guidance for policy refinement and reuse , 2010, 2010 IEEE 9th International Conference on Development and Learning.

[18]  Shimon Whiteson,et al.  Inverse Reinforcement Learning from Failure , 2016, AAMAS.

[19]  Alexander N. Gorban,et al.  Elastic Principal Graphs and Manifolds and their Practical Applications , 2005, Computing.