Learning Object Properties Using Robot Proprioception via Differentiable Robot-Object Interaction
Authors:
- 19 May 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5997-6004
Abstract
Differentiable simulation has become a powerful tool for system identification. While prior work has focused on identifying robot properties using robot-specific data or object properties using object-specific data, our approach calibrates object properties by using information from the robot, without relying on data from the object itself. Specifically, we utilize robot joint encoder information, which is commonly available in standard robotic systems. Our key observation is that by analyzing the robot's reactions to manipulated objects, we can infer properties of those objects, such as inertia and softness. Leveraging this insight, we develop differentiable simulations of robot-object interactions to inversely identify the properties of the manipulated objects. Our approach relies solely on proprioception – the robot's internal sensing capabilities – and does not require external measurement tools or vision-based tracking systems. This general method is applicable to any articulated robot and requires only joint position information. We demonstrate the effectiveness of our method on a low-cost robotic platform, achieving accurate mass and elastic modulus estimations of manipulated objects with just a few seconds of computation on a laptop.Keywords
All Related Versions
This publication has 49 references indexed in Scilit:
- A Differentiable Newton–Euler Algorithm for Real-World Robotics2023
- Common Sensors in Industrial Robots: A ReviewJournal of Physics: Conference Series, 2019
- Stereo vision based autonomous robot calibrationRobotics and Autonomous Systems, 2017
- Calibrating a Multi-arm Multi-sensor Robot: A Bundle Adjustment Approach2014
- Nonlinear Continuum Mechanics for Finite Element Analysis2008
- Rigid Body Dynamics Algorithms2008
- The CMA Evolution Strategy: A Comparing Review2007
- A First Course in Continuum Mechanics2001
- Successive one-step-ahead predictions in multiple model predictive controlInternational Journal of Systems Science, 1998
- Haptic Dominance in Form Perception: Vision versus ProprioceptionPerception, 1992