Multi-modal robot pushes and tips objects to find mass and friction
Multi-Modal Non-Prehensile Estimation of Physical Parameters via Press-and-Pull Tipping
Robotics
Summary
Figuring out how heavy things are and how much they slide is tricky when a robot can only push or tip them in one way. The authors show that by combining two types of poking—sliding and a new press-and-pull tipping method—a robot can better learn an object's weight, balance point, and slipperiness. This approach works even on oddly shaped items that normally slip or roll instead of tipping over. Their robot uses different sensors and no prior object details to estimate these physical traits accurately.
What this means in practice
- •For industrial robot programmers: Enable robots to determine object weight and grip properties without grasping, improving handling of unknown items on production lines.
- •For warehouse automation teams: Improve robot ability to interact safely with objects that have curved or slippery bases by estimating physical traits through multi-mode pushing and tipping.
Authors
Steven M. Hyland, Jing Xiao, Cagdas D. Onal
Abstract
Recovering physical properties of unknown objects through non-prehensile interaction is challenging because no single manipulation primitive reveals all relevant parameters. Planar pushing couples mass and friction, while conventional tipping cannot recover friction and may fail entirely when low-friction or curved-base objects slide or rotate instead of tipping. We introduce a multi-modal estimation framework that combines a sliding interaction with a press-and-pull tipping primitive to recover object mass, center of mass height, and surface friction. The press-and-pull interaction increases the object-table sliding threshold and stabilizes the pivot, enabling controlled tipping without any prior geometric object model. Wrist force/torque sensing, RGB-D perception, and robot proprioception are fused to estimate the physical parameters from the two complementary interaction modes. Experiments on an ABB IRB120 across four objects with varied geometry, mass, center of mass, and friction achieve low relative error, while successfully operating on curved-base objects that fail under conventional forward tipping. The results demonstrate that complementary non-prehensile interactions can recover a compact set of physical parameters without grasping, a prior object model, or learned interaction dynamics.