Learning Generalizable Robot Skills from Demonstrations in Cluttered Environments
This addresses the challenge of making robot skill learning more practical and generalizable in real-world, cluttered settings, representing an incremental improvement over existing methods.
The paper tackles the problem of learning robot skills from demonstrations in cluttered environments, where irrelevant objects can obscure human intentions, by developing an importance weighted batch and incremental skill learning approach that reduces unwanted environmental influences and captures salient human behavior, validated on a 7-DOF JACO2 manipulator with reaching and placing skills.
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.