发表机构
School of Artificial Intelligence, Shanghai Jiao Tong University; School of Engineering and Informatics, University of Sussex（上海交通大学人工智能学院; 萨塞克斯大学工程与信息学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对长 horizon 机器人操作可靠性难题，提出 Triplet-to-Track System（TTS），该闭环模仿学习系统用人类视频减少数据依赖，经实验平均成功率达74.8%，支持对象级与组合泛化。
AI 中文摘要
在不确定环境中确保长 horizon 机器人操作的可靠性仍然是难题。端到端 VLA 模型数据量大且不透明，难以诊断和验证；分层流水线可解释性更强，但它们的规划常弱依赖观测、与低层动作对齐度低，且计算时无在线反馈，导致开环行为和幻觉。为解决这些问题，我们提出 Triplet-to-Track System（TTS），一种闭环长 horizon 模仿学习系统，利用人类视频减少对机器人采集数据的依赖。TTS 将高层子目标表征为实例接地三元组，转化为连续跟踪先验用于执行，并从观测中监控任务进度以进行在线重规划。在多种真实世界长 horizon 任务中，TTS 平均成功率达 74.8%，支持对象级和组合泛化。
英文摘要
Ensuring reliability in uncertain environments remains difficult for long-horizon robotic manipulation. End-to-end VLA models are data-heavy and opaque, making diagnosis and verification difficult. Hierarchical pipelines are more interpretable, but their plans are often weakly grounded in observations, weakly aligned with low-level actions, and computed without online feedback, leading to open-loop behavior and hallucinations. To address these issues, we introduce the Triplet-to-Track System (TTS), a closed-loop long-horizon imitation learning system that uses human videos to reduce reliance on robot-collected data. TTS represents high-level subgoals as instance-grounded triplets, translates them into continuous track priors for execution, and monitors task progress from observations for online replanning. Across diverse real-world long-horizon tasks, TTS achieves a 74.8\% average success rate and supports object-level and compositional generalization.
Comments8 pages, 6 figures. Accepted for presentation at the 2026 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2026)
