面向铰接物体操作的约束参照评估方法 CRS
Kinematic Constraint-Referenced Evaluation for Articulated Object Manipulation
AI 导读
研究者提出约束参照策略评估方法 CRS，将末端执行器的速度指令投影到物体关节轴上，把沿关节的有效进展与偏离约束的浪费动作分开，无需示教数据或学习型评判器。在 74 个仿真铰接物体上，传统任务成功率只能反映迁移失败而无法归因，CRS 的两个通道则给出各自可区分的失败特征。
正文 · 原文
Abstract:Manipulation policies are evaluated predominantly by binary task success, which cannot tell whether the commanded gesture is the one the object's kinematics admit. We introduce Constraint-Referenced Strategy (CRS), which projects the commanded end-effector twist onto the object's joint axis, separating progress along the joint from off-constraint waste. CRS requires a joint model and a joint-following scripted controller derived from it, but no recorded demonstration or learned judge. On 74 simulated articulated objects, success registers three transfer failures as lower rates but attributes none, while the two CRS channels give each a distinct signature. A door-trained behavior-cloning policy opens drawers in 59 of 110 episodes, and in these passes it commands about $40\times$ the off-axis rotation of a drawer-trained policy's passes ($1.27$ vs.\ $0.032$~rad/s). Relative to a scripted controller scored with the same axis, CRS verdicts are unchanged under joint-axis errors up to $30^\circ$; absolute thresholds tolerate about $8^\circ$.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.37550 [cs.RO] |
| (or arXiv:2610.37550v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37550 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Baptiste Bonin [view email]
[v1]
Tue, 27 Oct 2026 17:00:01 UTC (605 KB)
来源：arXiv cs.AI · arxiv.org