Task-Driven Hybrid Model Reduction for Dexterous Manipulation
- 29 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 40 (15523098) , 1774-1794
Abstract
In contact-rich tasks, like dexterous manipulation, the hybrid nature of making and breaking contact creates challenges for model representation and control. For example, choosing and sequencing contact locations for in-hand manipulation, where there are thousands of potential hybrid modes, is not generally tractable. In this paper, we are inspired by the observation that far fewer modes are actually necessary to accomplish many tasks. Building on our prior work learning hybrid models, represented as linear complementarity systems, we find a reduced-order hybrid model requiring only a limited number of task-relevant modes. This simplified representation, in combination with model predictive control, enables real-time control yet is sufficient for achieving high performance. We demonstrate the proposed method first on synthetic hybrid systems, reducing the mode count by multiple orders of magnitude while achieving task performance loss of less than 5%. We also apply the proposed method to a three-fingered robotic hand manipulating a previously unknown object. With no prior knowledge, we achieve state-of-the-art closed-loop performance within a few minutes of online learning, by collecting only a few thousand environment samples.Keywords
All Related Versions
Funding Information
- Toyota Research Institute
This publication has 37 references indexed in Scilit:
- OSQP: an operator splitting solver for quadratic programsMathematical Programming Computation, 2020
- CasADi: a software framework for nonlinear optimization and optimal controlMathematical Programming Computation, 2018
- On the complexity of piecewise affine system identificationAutomatica, 2015
- Centroidal dynamics of a humanoid robotAutonomous Robots, 2013
- Model-Based Reinforcement Learning2012
- On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programmingMathematical Programming, 2005
- A Tutorial on the Cross-Entropy MethodAnnals of Operations Research, 2005
- A clustering technique for the identification of piecewise affine systemsAutomatica, 2003
- Equivalence of hybrid dynamical modelsAutomatica, 2001
- A review of trust region algorithms for optimization2000