Similarity-Aware Skill Reproduction based on Multi-Representational Learning from Demonstration

Learning from Demonstration (LfD) algorithms enable humans to teach new skills to robots through demonstrations. The learned skills can be robustly reproduced from the identical or near boundary conditions (e.g., initial point). However, when generalizing a learned skill over boundary conditions with higher variance, the similarity of the reproductions changes from one boundary condition to another, and a single LfD representation cannot preserve a consistent similarity across a generalization region. We propose a novel similarity-aware framework including multiple LfD representations and a similarity metric that can improve skill generalization by finding reproductions with the highest similarity values for a given boundary condition. Given a demonstration of the skill, our framework constructs a similarity region around a point of interest (e.g., initial point) by evaluating individual LfD representations using the similarity metric. Any point within this volume corresponds to a representation that reproduces the skill with the greatest similarity. We validate our multi-representational framework in three simulated and four sets of real-world experiments using a physical 6-DOF robot. We also evaluate 11 different similarity metrics and categorize them according to their biases in 286 simulated experiments.

[1]  Manuela M. Veloso,et al.  Confidence-based policy learning from demonstration using Gaussian mixture models , 2007, AAMAS '07.

[2]  Sonia Chernova,et al.  Recent Advances in Robot Learning from Demonstration , 2020, Annu. Rev. Control. Robotics Auton. Syst..

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

[4]  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).

[5]  Jan Peters,et al.  Probabilistic Movement Primitives , 2013, NIPS.

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

[7]  S. Reza Ahmadzadeh,et al.  Learning from Successful and Failed Demonstrations via Optimization , 2021, 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[8]  Dorsa Sadigh,et al.  Learning Reward Functions by Integrating Human Demonstrations and Preferences , 2019, Robotics: Science and Systems.

[9]  Wei Jing,et al.  Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning , 2019, 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[10]  Marcin Andrychowicz,et al.  Hindsight Experience Replay , 2017, NIPS.

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

[12]  Allan Hanbury,et al.  An Efficient Algorithm for Calculating the Exact Hausdorff Distance , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Darwin G. Caldwell,et al.  Kernelized movement primitives , 2017, Int. J. Robotics Res..

[14]  Ken Shoemake,et al.  Animating rotation with quaternion curves , 1985, SIGGRAPH.

[15]  Aude Billard,et al.  Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models , 2011, IEEE Transactions on Robotics.

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

[17]  H. Mannila,et al.  Computing Discrete Fréchet Distance ∗ , 1994 .

[18]  Daniel Bennequin,et al.  Geometrical Invariance and Smoothness Maximization for Task-Space Movement Generation , 2016, IEEE Transactions on Robotics.

[19]  Brett Browning,et al.  Automatic weight learning for multiple data sources when learning from demonstration , 2009, 2009 IEEE International Conference on Robotics and Automation.