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.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Malladi, R., Sangwan, A., Gupta, R. K., & Rahman, T. (2026). The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies. https://omanscience.com/en/articles/the-robot-is-not-its-description-gaugebench-for-representation-robustness-in-morphology-aware-policies
MLA 9
Malladi, Rahath, et al. "The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies." https://omanscience.com/en/articles/the-robot-is-not-its-description-gaugebench-for-representation-robustness-in-morphology-aware-policies.
Chicago (author–date)
Malladi, Rahath, Arshia Sangwan, Rajesh K. Gupta, and Tauhidur Rahman. 2026. "The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies." https://omanscience.com/en/articles/the-robot-is-not-its-description-gaugebench-for-representation-robustness-in-morphology-aware-policies.
Harvard
Malladi, R., Sangwan, A., Gupta, R. K. and Rahman, T. (2026) 'The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies', Available at: https://omanscience.com/en/articles/the-robot-is-not-its-description-gaugebench-for-representation-robustness-in-morphology-aware-policies.
Vancouver
Malladi R, Sangwan A, Gupta RK, Rahman T. The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies. https://omanscience.com/en/articles/the-robot-is-not-its-description-gaugebench-for-representation-robustness-in-morphology-aware-policies
IEEE
R. Malladi, A. Sangwan, R. K. Gupta, and T. Rahman, "The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies," https://omanscience.com/en/articles/the-robot-is-not-its-description-gaugebench-for-representation-robustness-in-morphology-aware-policies.