arXiv 2509.175822026-09-22cs.RO

GeCCo -- 一种用于腿式机器人移动操作技能的通用接触条件策略

GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots

Dynamic Robot Systems Group, Oxford Robotics Institute, University of Oxford（牛津大学机器人研究所动态机器人系统组）；Sony AI（索尼人工智能）；Dyson Institute of Engineering and Technology（戴森工程与技术研究所）

Vassil Atanassov, Wanming Yu, Siddhant Gangapurwala, James Wilson, Ioannis Havoutis

备注：: This paper has been accepted for publication at the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出一种通用接触条件策略（GeCCo），通过深度强化学习训练低层控制器，可跟踪任意接触点，无需重新训练即可适应多种移动操作任务，提高扩展性和效率。

摘要：

大多数现代四足机器人运动方法侧重于使用深度强化学习（DRL）以端到端的方式从头学习策略。此类方法往往难以扩展，因为每个新问题或应用都需要耗时且迭代的奖励定义和调整。我们提出了通用接触条件策略（GeCCo）——一种使用深度强化学习训练的低层策略，能够跟踪四足机器人上的任意接触点。我们方法的优势在于，它提供了一个通用且模块化的低层控制器，可重复用于更广泛的高层任务，而无需从头重新训练新控制器。我们通过在通用框架下、在单一通用策略下评估各种运动和操作任务，展示了我们方法的可扩展性和鲁棒性。这些任务包括多种步态、穿越复杂地形（例如楼梯和斜坡）以及未见过的踏脚石和窄梁，以及与物体交互（例如按按钮、跟踪轨迹）。我们的框架通过简单地将特定任务的高层接触规划器与预训练的通用策略相结合，更高效地获得新行为。补充视频可在 https://youtu.be/o8Dd44MkG2E 找到。

英文摘要：

Most modern approaches to quadruped locomotion focus on using Deep Reinforcement Learning (DRL) to learn policies from scratch, in an end-to-end manner. Such methods often fail to scale, as every new problem or application requires time-consuming and iterative reward definition and tuning. We present Generalist Contact-Conditioned Policy (GeCCo) --- a low-level policy trained with Deep Reinforcement Learning that is capable of tracking arbitrary contact points with a quadruped robot. We shift from task-specific end-to-end learning to a modular hierarchy in which a single planner-agnostic, contact-conditioned tracking policy serves as a robust interface between planning and control. By maintaining stable contact execution under dynamic uncertainty and planner mismatch, the policy enables high-level planners (e.g., handcrafted, learned, or optimization-based) to be composed and swapped without retraining. We demonstrate the scalability and robustness of our method by evaluating on a wide range of locomotion and manipulation tasks in a common framework and under a single generalist policy. These include a variety of gaits, traversing complex terrains (e.g., stairs and slopes) as well as previously unseen stepping-stones and narrow beams, and interacting with objects (e.g., pressing a button, pushing a barrel). Our framework acquires new behaviors more efficiently, simply by combining a task-specific high-level contact planner and the pre-trained generalist policy. Project website: https://vassil-atn.github.io/gecco.github.io

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。