Learning Generalizable Robot Skills from Demonstrations in Cluttered Environments

Learning from Demonstration (LfD) is a popular approach to endowing robots with skills without having to program them by hand. Typically, LfD relies on human demonstrations in clutter-free environments. This prevents the demonstrations from being affected by irrelevant objects, whose influence can obfuscate the true intention of the human or the constraints of the desired skill. However, it is unrealistic to assume that the robot's environment can always be restructured to remove clutter when capturing human demonstrations. To contend with this problem, we develop an importance weighted batch and incremental skill learning approach, building on a recent inference-based technique for skill representation and reproduction. Our approach reduces unwanted environmental influences on the learned skill, while still capturing the salient human behavior. We provide both batch and incremental versions of our approach and validate our algorithms on a 7-DOF JACO2 manipulator with reaching and placing skills.

[1]  Jan Peters,et al.  Demonstration based trajectory optimization for generalizable robot motions , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[2]  Byron Boots,et al.  Towards Robust Skill Generalization: Unifying Learning from Demonstration and Motion Planning , 2017, CoRL.

[3]  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).

[4]  Andrej Gams,et al.  Learning of parametric coupling terms for robot-environment interaction , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).

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

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

[7]  Ron Alterovitz,et al.  Demonstration-Guided Motion Planning , 2011, ISRR.

[8]  Simo Särkkä,et al.  Batch Continuous-Time Trajectory Estimation as Exactly Sparse Gaussian Process Regression , 2014, Robotics: Science and Systems.

[9]  Byron Boots,et al.  Gaussian Process Motion planning , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[10]  Byron Boots,et al.  Continuous-time Gaussian process motion planning via probabilistic inference , 2017, Int. J. Robotics Res..

[11]  Gm Gero Walter,et al.  Bayesian linear regression , 2009 .

[12]  Jan Peters,et al.  Guiding Trajectory Optimization by Demonstrated Distributions , 2017, IEEE Robotics and Automation Letters.

[13]  Stefan Schaal,et al.  Learning coupling terms for obstacle avoidance , 2014, 2014 IEEE-RAS International Conference on Humanoid Robots.

[14]  Gregory D. Hager,et al.  An incremental approach to learning generalizable robot tasks from human demonstration , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[15]  Jun Nakanishi,et al.  Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors , 2013, Neural Computation.

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

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

[18]  Jun Nakanishi,et al.  Control, Planning, Learning, and Imitation with Dynamic Movement Primitives , 2003 .

[19]  Aude Billard,et al.  A dynamical system approach to realtime obstacle avoidance , 2012, Autonomous Robots.

[20]  Stefan Schaal,et al.  Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields , 2008, Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots.