Differentiable Simulation for Physical System Identification
- 25 February 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (2) , 3413-3420
Abstract
Simulating frictional contacts remains a challenging research topic in robotics. Recently, differentiable physics emerged and has proven to be a key element in model-based Reinforcement Learning (RL) and optimal control fields. However, most of the current formulations deploy coarse approximations of the underlying physical principles. Indeed, the classic simulators loose precision by casting the Nonlinear Complementarity Problem (NCP) of frictional contact into a Linear Complementarity Problem (LCP) to simplify computations. Moreover, such methods deploy non-smooth operations and cannot be automatically differentiated. In this letter, we propose (i) an extension of the staggered projections algorithm for more accurate solutions of the problem of contacts with friction. Based on this formulation, we introduce (ii) a differentiable simulator and an efficient way to compute the analytical derivatives of the involved optimization problems. Finally, (iii) we validate the proposed framework with a set of experiments to present a possible application of our differentiable simulator. In particular, using our approach we demonstrate accurate estimation of friction coefficients and object masses both in synthetic and real experiments.Keywords
Funding Information
- GENCI-IDRIS (AD011011342)
- French Government (ANR-19-P3IA-0001)
- Louis Vuitton
- Chair on Artificial Intelligence
This publication has 17 references indexed in Scilit:
- Trajectory Optimization With Implicit Hard ContactsIEEE Robotics and Automation Letters, 2018
- Analytical Derivatives of Rigid Body Dynamics Algorithms2018
- Domain randomization for transferring deep neural networks from simulation to the real world2017
- Whole-body model-predictive control applied to the HRP-2 humanoid2015
- Proximal AlgorithmsFoundations and Trends® in Optimization, 2014
- A direct method for trajectory optimization of rigid bodies through contactThe International Journal of Robotics Research, 2013
- MuJoCo: A physics engine for model-based control2012
- Staggered projections for frictional contact in multibody systems2008
- An iterative approach for cone complementarity problems for nonsmooth dynamicsComputational Optimization and Applications, 2008
- Formulating Dynamic Multi-Rigid-Body Contact Problems with Friction as Solvable Linear Complementarity ProblemsNonlinear Dynamics, 1997