BiKC: Keypose-Conditioned Consistency Policy for Bimanual Robotic Manipulation

TL;DR

This paper presents BiKC, a hierarchical imitation learning framework with a keypose-conditioned policy for efficient bimanual manipulation, improving success rates and inference speed in complex multi-stage tasks.

Contribution

Introduction of a novel keypose-conditioned consistency policy with a hierarchical structure for bimanual manipulation tasks, emphasizing fast inference and multi-stage task handling.

Findings

Outperforms baseline methods in success rate

Demonstrates improved operational efficiency

Effective in both simulated and real-world environments

Abstract

Bimanual manipulation tasks typically involve multiple stages which require efficient interactions between two arms, posing step-wise and stage-wise challenges for imitation learning systems. Specifically, failure and delay of one step will broadcast through time, hinder success and efficiency of each sub-stage task, and thereby overall task performance. Although recent works have made strides in addressing certain challenges, few approaches explicitly consider the multi-stage nature of bimanual tasks while simultaneously emphasizing the importance of inference speed. In this paper, we introduce a novel keypose-conditioned consistency policy tailored for bimanual manipulation. It is a hierarchical imitation learning framework that consists of a high-level keypose predictor and a low-level trajectory generator. The predicted keyposes provide guidance for trajectory generation and also mark the completion of one sub-stage task. The trajectory generator is designed as a consistency model trained from scratch without distillation, which generates action sequences conditioning on current observations and predicted keyposes with fast inference speed. Simulated and real-world experimental results demonstrate that the proposed approach surpasses baseline methods in terms of success rate and operational efficiency. Codes are available at https://github.com/ManUtdMoon/BiKC.