Inertia mismatch affects robot learning performance and reliability
When Robots Outweigh Objects: How Inertia Mismatch Shapes Robot Policy Learning
Robotics
Summary
Robot arms are often much heavier than the objects they handle, which can cause problems when the robot accidentally bumps something light. The authors studied how this difference in weight, called inertia mismatch, affects how well robots can learn tasks using computer programs. They found that some learning methods cope better than others depending on the weight difference, and that teaching robots with lighter arms or making demonstrations with less impact improves learning. Their work helps understand and improve how robots learn to handle objects despite the challenges of weight differences.
What this means in practice
- •For robotics engineers: Improve robot manipulation policies by selecting lower-inertia workspaces or demonstration strategies to reduce errors from heavy arms interacting with light objects.
- •For automated assembly teams: Design training data collection protocols that guide robots to use less forceful movements, increasing success when programming heavy robot arms.
Authors
Younghyo Park, Antonia Bronars, Pulkit Agrawal
Abstract
Conventional robot arms can be extremely heavy compared with the everyday objects they manipulate, creating a significant inertia mismatch at contact. Even a small accidental bump from a heavy arm can knock a light object out of place. Modern learning methods have nevertheless demonstrated a wide range of successful manipulation behaviors on these platforms, suggesting that even extreme inertia mismatch can be overcome with sufficient data. However, it remains unclear whether high inertia imposes a hidden cost on learning, potentially worsening scaling with data or lowering the performance ceiling of modern robot learning methods. We investigate this question through controlled simulation experiments that vary robot and object masses. We find that reinforcement learning succeeds across a broad range of mass combinations, while behavior cloning learns more reliable policies when a lighter robot manipulates a heavier object, and more data narrows the resulting gap without closing it. Behavior cloning likewise degrades on a simulated robot arm as its motors reflect more inertia through their gearing, even though its weight stays the same. Finally, because new hardware is rarely an option, we explore ways to lower contact inertia on the arm one already has, either by choosing a lower-inertia workspace before collecting data or by steering the demonstrator toward lower-inertia solutions of the task. In both simulated cases, the lower-inertia demonstrations are imitated more reliably. Project website: https://younghyopark.me/inertia-mismatch/