An Alignment-Based Approach to Learning Motions from Demonstrations

TL;DR

This paper presents CALM, a novel Learning from Demonstration framework that uses trajectory alignment to overcome limitations of existing time-dependent and time-independent methods, enabling robust multi-modal motion learning.

Contribution

CALM introduces an alignment-based approach for LfD that handles perturbations and supports multi-modal behavior, improving over traditional methods.

Findings

CALM effectively mitigates drawbacks of existing LfD techniques.

The system successfully learns complex motions on a 7-DoF robot.

CALM demonstrates robustness under perturbations in 2D and 3D tasks.

Abstract

Learning from Demonstration (LfD) has shown to provide robots with fundamental motion skills for a variety of domains. Various branches of LfD research (e.g., learned dynamical systems and movement primitives) can generally be classified into ''time-dependent'' or ''time-independent'' systems. Each provides fundamental benefits and drawbacks -- time-independent methods cannot learn overlapping trajectories, while time-dependence can result in undesirable behavior under perturbation. This paper introduces Cluster Alignment for Learned Motions (CALM), an LfD framework dependent upon an alignment with a representative ''mean" trajectory of demonstrated motions rather than pure time- or state-dependence. We discuss the convergence properties of CALM, introduce an alignment technique able to handle the shifts in alignment possible under perturbation, and utilize demonstration clustering to generate multi-modal behavior. We show how CALM mitigates the drawbacks of time-dependent and time-independent techniques on 2D datasets and implement our system on a 7-DoF robot learning tasks in three domains.