arXiv：cs.LG· Rahath Malladi, Arshia Sangwan, Rajesh K. Gupta, Tauhidur Rahman·· 4 小时前AI 评分47
GaugeBench：机器人形态感知策略的表示鲁棒性评测基准
The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies
AI 导读
机器人描述不仅指定物理结构，还编码关节轴方向、关节角零点等任意约定；GaugeBench 通过改写固定机器人的物理等价描述来隔离这一问题。三个 MetaMorph 策略在 80 个熟悉机器人上得分 4030.6，同样机器人等价改写描述后仅得 51.6，低于 98 个真正未见机器人的 1489.6。
正文
Abstract:A robot description does more than specify a physical mechanism: it also encodes arbitrary conventions, such as joint-axis direction, joint-angle zero, and the order and names of links and joints. Morphology-aware policies consume interfaces built from these descriptions, yet cross-embodiment evaluation typically changes the robot while keeping those conventions fixed. This leaves a simple question unanswered: does behavior survive when the robot stays fixed but its description changes? GaugeBench isolates this case by rewriting a fixed mechanism under physically equivalent conventions, verifying that its physics and policy interface are preserved, and then evaluating the same policy weights. The result is stark: three MetaMorph policies score 4030.6 on 80 familiar robots, but only 51.6 when those same robots are equivalently re-described, while 98 genuinely held-out robots score 1489.6. A new description can therefore be more damaging than a new robot. Tracing the failure reveals that axis reversal alone reproduces the collapse, joint-angle zero changes are nearly harmless, and reordering lies between them; moreover, changing joint-state and torque coordinates alone is sufficient to cause the failure, while changing description-derived features alone is not. The same phenomenon appears in ModuMorph and an unrelated PyBullet framework. Yet it is not irreversible: exact two-description transport restores the original controller, and training across equivalent axis conventions raises retained return under axis reversal from 3.6% to 80.6%. Together, these results separate mechanism robustness from representation robustness and show that cross-embodiment evaluation should test both.
| Subjects: | Robotics (cs.RO); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.07597 [cs.RO] |
| (or arXiv:2610.07597v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07597 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rahath Malladi [view email]
[v1]
Tue, 6 Oct 2026 01:37:10 UTC (1,760 KB)
来源：arXiv：cs.LG · arxiv.org