Contact Trajectory Prompting: In-Context Transfer of Contact-Rich Behaviors from a Single Demonstration

Embodied AI and Robotics Imitation Learning CFCIC
2026年10月13日
上下文内机器人学习（in-context robot learning）使机器人无需在测试阶段更新模型参数，即可仅通过示范示例便习得新行为。然而，单靠视觉与运动学信息往往难以区分那些动作轨迹相似、但所需接触强度或接触模式截然不同的富含接触（contact-rich）行为。为此，我们提出了“接触轨迹提示”（Contact Trajectory Prompting, CTP）框架，用于实现富含接触类操作行为的单次示范迁移。CTP 将单个示范中蕴含的运动信息与接触信息编码为一条有序的“接触轨迹提示”，该提示不仅刻画了二者随时间演化的动态关系，更明确指定了期望的物理交互行为。在执行过程中，策略借助在线感知反馈，从该提示中实时检索与当前交互相关的信息，并以此为条件生成闭环控制的动作——即其动作输出始终以示范中所体现的接触行为为依据。在真实世界场景下，针对训练阶段未曾见过的物体，CTP 在擦拭、旋转与插入三类富含接触的任务中整体成功率高达 78.7%，显著优于当前最强基线方法 13.0 个百分点。仅需更换参考示范，CTP 即可灵活遵循不同强度与方向的接触规范：例如实现中等力度的擦拭，或分别完成顺时针与逆时针方向的瓶盖旋转。上述结果表明，接触轨迹可作为高效、具象的行为规范，从而将上下文内机器人学习的能力范畴，由单纯的运动模仿拓展至物理交互行为的迁移。项目网站：https://ctp-robotics.github.io/project_page
In-context robot learning enables robots to acquire new behaviors from demonstrations without test-time parameter updates. However, visual and kinematic specifications alone may not distinguish contact-rich behaviors that share similar motions but require different interaction intensities or patterns. We propose Contact Trajectory Prompting (CTP), a framework for one-shot transfer of contact-rich manipulation behaviors. CTP encodes motion and contact information from a single demonstration into an ordered contact trajectory prompt that captures their temporal evolution and specifies the desired physical interaction behavior. During execution, the policy uses online sensory feedback to retrieve interaction-relevant information from the prompt, conditioning closed-loop action generation on the demonstrated contact behavior. Across real-world wiping, rotation, and insertion tasks on objects excluded from training, CTP achieves 78.7% overall success, outperforming the strongest evaluated baseline by 13.0 percentage points. Changing only the reference demonstration enables CTP to follow contact specifications for both intensity and direction, including an intermediate wiping force level and clockwise or counterclockwise cap rotation. These results demonstrate that contact trajectories serve as effective behavioral specifications, extending in-context robot learning beyond motion imitation to physical interaction transfer. Project website: https://ctp-robotics.github.io/project_page.
许愿