外观
论文arXiv 2610.1081021 天前
诊断并恢复长时程技能接缝处的观察空间偏移
研究长时程操作技能串联中的OSS，提出检测-恢复-继续系统，并在BOSS-44和真实Franka上验证。
Franka FR3原文链接：Diagnosing and Recovering from Observation-Space Shift at Long-Horizon Skill Seams（arXiv 2610.10810 · 发布日期：2026-10-07）
Diagnosing and Recovering from Observation-Space Shift at Long-Horizon Skill Seams
研究长时程操作技能串联中的OSS，提出检测-恢复-继续系统，并在BOSS-44和真实Franka上验证。
核心要点
- 独立训练技能串联时，下游技能从前序遗留状态启动，导致性能显著下降。
- 借助特权仿真重置诊断发现，主要偏移来自抽屉或次要物体等场景状态位移。
- 系统用任务进度监视器检测停滞，学习策略恢复场景组件，再经接缝鲁棒微调继续执行。
- 在BOSS-44上，全链成功率由7.6%升至26.5%，多种基线未能恢复评估接缝状态。
验证范围与局限：验证包括BOSS-44基准和一台真实Franka机械臂上的微调π0.5策略，真实监视器受外部相机可观测性限制。
英文摘要 (Abstract)
Long-horizon robotic manipulation is often built by chaining independently trained skills. Although each skill can be reliable in isolation, performance degrades sharply when skills are chained: each downstream skill must start from the state its predecessor leaves behind rather than from its training distribution. We study this failure mode, Observation-Space Shift (OSS), and ask what causes these skill-seam failures. Using privileged simulator resets, we find that the dominant shift comes from displaced scene state (e.g., an open drawer or secondary objects left behind by earlier skills), not from the robot's joint configuration or the object the downstream skill manipulates. To test this diagnosis, we build a fully learned detect-restore-resume system: a task-progress monitor detects the stall, a learned policy restores the displaced scene components, and seam-robust fine-tuning lets the skill resume. It recovers the seam where every tested alternative fails, which we treat as evidence for the diagnosis rather than as a general-purpose method. On the BOSS-44 benchmark, the system improves full-chain success from 7.6% to 26.5%, a 3.5x improvement over the base policy and 51% of a privileged restoration oracle, whereas best-of-K resampling, a Diffusion Policy, and world-model baselines fail to recover from the evaluated seam states. On a real Franka arm running a fine-tuned $π_{0.5}$ policy, the same monitor is limited by exterior-camera observability, yet closing the loop still recovers some otherwise-terminal failures, motivating wrist and gripper sensing. These results suggest that some long-horizon composition failures are better addressed by restoring the scene before resuming the policy than by retrying from an off-support state.
作者：Pranav Wagh, Yu Fang, Yang Yue, Mingyu Ding
来源
本页事实对应的公开页面，以原文为准。