Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment
This addresses the challenge of single-life robot deployment in dynamic real-world environments, offering an incremental improvement in adaptation efficiency.
The paper tackles the problem of robots adapting to novel scenarios during deployment by introducing ROAM, a method that selects and adapts pre-trained behaviors based on perceived value, enabling rapid adaptation without human supervision. It demonstrates over 2x efficiency gains in out-of-distribution situations, such as a quadruped robot moving with roller skates.
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 previouslylearned 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 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.