Pith. sign in

REVIEW

Know Thyself: Transferable Visual Control Policies Through Robot-Awareness

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2107.09047 v3 pith:M5NITKT4 submitted 2021-07-19 cs.LG cs.CVcs.RO

classification cs.LGcs.CVcs.RO
keywords robotvisualcontroldatadynamicspoliciesrobot-awarerobot-specific
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data. How might we leverage data previously collected on another robot to reduce or even completely remove this need for robot-specific data? We propose a "robot-aware control" paradigm that achieves this by exploiting readily available knowledge about the robot. We then instantiate this in a robot-aware model-based RL policy by training modular dynamics models that couple a transferable, robot-aware world dynamics module with a robot-specific, potentially analytical, robot dynamics module. This also enables us to set up visual planning costs that separately consider the robot agent and the world. Our experiments on tabletop manipulation tasks with simulated and real robots demonstrate that these plug-in improvements dramatically boost the transferability of visual model-based RL policies, even permitting zero-shot transfer of visual manipulation skills onto new robots. Project website: https://www.seas.upenn.edu/~hued/rac

Discussion (0). Sign in to comment.

Pith tools