CycleManip: Enabling Cyclic Task Manipulation via Effective Historical Perception and Understanding

TL;DR

This paper introduces CycleManip, a framework for cycle-based robot manipulation tasks that leverages effective historical perception and understanding, along with a new benchmark and evaluation tools, to improve success rates in both simulation and real-world settings.

Contribution

The paper presents a novel end-to-end imitation framework for cycle-based manipulation, a new benchmark dataset, and an automatic evaluation method, addressing key challenges in the field.

Findings

Achieves high success rates in cycle-based tasks in simulation and real-world.

Demonstrates strong adaptability across various robotic platforms.

Shows compatibility with existing imitation policies like VLA models.

Abstract

In this paper, we explore an important yet underexplored task in robot manipulation: cycle-based manipulation, where robots need to perform cyclic or repetitive actions with an expected terminal time. These tasks are crucial in daily life, such as shaking a bottle or knocking a nail. However, few prior works have explored this task, leading to two main challenges: 1) the imitation methods often fail to complete these tasks within the expected terminal time due to the ineffective utilization of history; 2) the absence of a benchmark with sufficient data and automatic evaluation tools hinders development of effective solutions in this area. To address these challenges, we first propose the CycleManip framework to achieve cycle-based task manipulation in an end-to-end imitation manner without requiring any extra models, hierarchical structure or significant computational overhead. The core insight is to enhance effective history perception by a cost-aware sampling strategy and to improve historical understanding by multi-task learning. Second, we introduce a cycle-based task manipulation benchmark, which provides diverse cycle-based tasks, and an automatic evaluation method. Extensive experiments conducted in both simulation and real-world settings demonstrate that our method achieves high success rates in cycle-based task manipulation. The results further show strong adaptability performance in general manipulation, and the plug-and-play ability on imitation policies such as Vision-Language-Action (VLA) models. Moreover, the results show that our approach can be applied across diverse robotic platforms, including bi-arm grippers, dexterous hands, and humanoid robots.