Skip to yearly menu bar Skip to main content


Poster
in
Workshop: 6th Robot Learning Workshop: Pretraining, Fine-Tuning, and Generalization with Large Scale Models

Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment

Annie Chen · Govind Chada · Laura Smith · Archit Sharma · Zipeng Fu · Sergey Levine · Chelsea Finn

Keywords: [ Reinforcement Learning ] [ single-life deployment ] [ out-of-distribution adaptation ] [ autonomous reinforcement learning ]


Abstract:

To succeed in the real world, robots must cope with situations that differ from those seen during training. We study the problem of adapting on-the-fly to such novel scenarios during deployment, by drawing upon a diverse repertoire of previously- learned behaviors. Our approach, RObust Autonomous Modulation (ROAM), introduces a mechanism based on the perceived value of pre-trained behaviors to select and adapt pre-trained behaviors to the situation at hand. Crucially, this adaptation process all happens within a single episode at test time, without any human supervision. We provide theoretical analysis of our selection mechanism and demonstrate that ROAM enables a robot to adapt rapidly to changes in dynamics both in simulation and on a real Go1 quadruped, even successfully moving forward with roller skates on its feet. Our approach adapts over 2x as efficiently compared to existing methods when facing a variety of out-of-distribution situations during deployment by effectively choosing and adapting relevant behaviors on-the-fly.

Chat is not available.