Contact-Aware Imitation Learning Through Contact Factorization

Key points

• Generalizable contact-rich manipulation requires robots to preserve intended task behavior while adapting its physical realization to changing contact conditions.1
• Our representation expresses interaction forces in normalized, contact-relative coordinates, while a learned contact-normal estimator and an online friction estimator infer the local contact normal and effective friction scale.1
• In this way, FACE adapts execution to current contact conditions while preserving the intended task behavior, without updating the policy parameters.1
• We evaluate FACE on real-robot contact-rich manipulation under unseen variations in surface properties and geometry, demonstrating robust generalization across contact conditions through controlled comparisons with variants that adapt prior approaches to our setting.1

Sources (1)

• [1]Contact-Aware Imitation Learning Through Contact Factorization
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 06:36 AM

  We introduce FACE, a contact-factorized imitation learning framework that separates intended task behavior from environment-dependent contact factors.

  Generalizable contact-rich manipulation requires robots to preserve intended task behavior while adapting its physical realization to changing contact conditions.

Extractive summary: sentences quoted from the sources.