An Alignment-Based Approach to Learning Motions from Demonstrations

2025/11/19 by Cuellar, Alex, Fourie, Christopher K, Shah, Julie A
#FOS: Computer and information sciences #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2511.14988

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.

Citations

• Learning Complex Motion Plans using Neural ODEs with Safety and Stability Guarantees
• Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
• Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
• Diffusion policy: Visuomotor policy learning via action diffusion
• ProDMPs: A Unified Perspective on Dynamic and Probabilistic Movement Primitives
• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
• ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by\n Normalizing Flows
• Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors

Related

• TACO: Learning Task Decomposition via Temporal Alignment for Control
• Continual Learning from Demonstration of Robotics Skills
• Arc-Length-Based Warping for Robot Skill Synthesis from Multiple Demonstrations
• A Robust Task-Level Control Architecture for Learned Dynamical Systems
• Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robot Skills