PEARS: Physical-Prior-Guided Efficient Adaptation via Failure Reasoning and Diffusion Steering for Tactile Manipulation

Key points

• Pretrained robotic policies can suffer substantial performance degradation under out-of-distribution (OOD) conditions encountered during deployment, motivating post-training through real-world interaction.1
• However, reinforcement-learning (RL)-based post-training typically requires substantial environment interactions, a burden that is especially significant in manipulation, where each trial can be slow, costly, or destructive.1
• After each episode, its physics-guided force reasoning (PFR) module uses physical priors encoded in a vision-language model (VLM) to diagnose failures from the visual outcome and tactile interaction history and update task-appropriate contact-force bounds.1
• Complementarily, tactile-conditioned diffusion steering reinforcement learning adjusts the latent noise of the frozen flow-matching policy to correct errors in free-space motion and contact timing without updating the base model.1

Sources (1)

• [1]PEARS: Physical-Prior-Guided Efficient Adaptation via Failure Reasoning and Diffusion Steering for Tactile Manipulation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 05:59 PM

  Therefore, we present PEARS, a physics-prior-guided hybrid RL framework for sample-efficient online adaptation of pretrained policies with tactile feedback.

  Pretrained robotic policies can suffer substantial performance degradation under out-of-distribution (OOD) conditions encountered during deployment, motivating post-training through real-world interaction.

Extractive summary: sentences quoted from the sources.