Leveraging Locality to Boost Sample Efficiency in Robotic Manipulation

TL;DR

This paper introduces SGRv2, a sample-efficient imitation learning framework for robotic manipulation that leverages action locality to significantly improve performance in both simulated and real-world tasks.

Contribution

SGRv2 incorporates an action locality inductive bias to enhance visual and action representations, leading to superior sample efficiency over existing methods.

Findings

SGRv2 surpasses RVT baseline in 23 of 26 RLBench tasks.

Achieves 2.54 times higher success rate than SGR on ManiSkill2 and MimicGen.

Performs effectively in real-world tasks with only eight demonstrations.

Abstract

Given the high cost of collecting robotic data in the real world, sample efficiency is a consistently compelling pursuit in robotics. In this paper, we introduce SGRv2, an imitation learning framework that enhances sample efficiency through improved visual and action representations. Central to the design of SGRv2 is the incorporation of a critical inductive bias-action locality, which posits that robot's actions are predominantly influenced by the target object and its interactions with the local environment. Extensive experiments in both simulated and real-world settings demonstrate that action locality is essential for boosting sample efficiency. SGRv2 excels in RLBench tasks with keyframe control using merely 5 demonstrations and surpasses the RVT baseline in 23 of 26 tasks. Furthermore, when evaluated on ManiSkill2 and MimicGen using dense control, SGRv2's success rate is 2.54 times that of SGR. In real-world environments, with only eight demonstrations, SGRv2 can perform a variety of tasks at a markedly higher success rate compared to baseline models. Project website: http://sgrv2-robot.github.io