发表机构
University of California San Diego; New York University（加利福尼亚大学圣迭戈分校; 纽约大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出GaugeBench，通过等效重写机器人描述评估形态感知策略的表示鲁棒性，发现描述变化比新机器人更具破坏性，但可通过双描述迁移或跨约定训练恢复性能。
AI 中文摘要
机器人描述不仅仅指定物理机制：它还编码了任意约定，例如关节轴方向、关节角零点以及连杆和关节的顺序和名称。形态感知策略使用基于这些描述构建的接口，然而跨实体评估通常改变机器人而保持这些约定不变。这留下了一个简单的问题未得到解答：当机器人保持不变但其描述改变时，行为是否仍然存在？GaugeBench 通过将固定机制在物理等效约定下重写，验证其物理和策略接口得以保留，然后评估相同的策略权重来隔离这种情况。结果是显著的：三个 MetaMorph 策略在 80 个熟悉机器人上得分为 4030.6，但当这些相同机器人被等效重新描述时仅得分为 51.6，而 98 个真正保留的机器人得分为 1489.6。因此，新描述可能比新机器人更具破坏性。追踪失败揭示，仅轴反转就能复现崩溃，关节角零点变化几乎无害，而重排介于两者之间；此外，仅改变关节状态和扭矩坐标就足以导致失败，而仅改变描述派生的特征则不会。相同现象出现在 ModuMorph 和无关的 PyBullet 框架中。然而这并非不可逆转：精确的双描述迁移恢复了原始控制器，而在等效轴约定下训练将轴反转下的保留回报从 3.6% 提高到 80.6%。总之，这些结果将机制鲁棒性与表示鲁棒性区分开来，并表明跨实体评估应同时测试两者。
英文摘要
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.
