Complementarity-Free Multi-Contact Modeling and Optimization for Dexterous Manipulation

2024-08-14

arXiv.org

AI Summary

To address the complexity and computational intractability of real-time optimization in dexterous manipulation involving multi-point contact dynamics, this paper proposes a complementarity-free, smooth, and differentiable multi-contact model. Leveraging optimization duality theory, the model employs a smooth approximation of friction constraints that inherently satisfies the Coulomb friction law, while enabling explicit time-stepping, end-to-end differentiability, and minimal hyperparameter dependence. Integrated within a model predictive control (MPC) framework and coupled with real-time dynamics simulation, the approach achieves an average task success rate of 96.5% across diverse dexterous manipulation tasks, with orientation and position errors of 11° and 7.8 mm, respectively, and MPC execution frequencies of 50–100 Hz—surpassing state-of-the-art performance. This work presents the first efficient, fully complementarity-free multi-contact modeling and closed-loop control framework for dexterous manipulation.

Technology Category

• Intelligent Robots: Manipulation
• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

A significant barrier preventing model-based methods from matching the high performance of reinforcement learning in dexterous manipulation is the inherent complexity of multi-contact dynamics. Traditionally formulated using complementarity models, multi-contact dynamics introduces combinatorial complexity and non-smoothness, complicating contact-rich planning and control. In this paper, we circumvent these challenges by introducing a novel, simplified multi-contact model. Our new model, derived from the duality of optimization-based contact models, dispenses with the complementarity constructs entirely, providing computational advantages such as explicit time stepping, differentiability, automatic satisfaction of Coulomb friction law, and minimal hyperparameter tuning. We demonstrate the effectiveness and efficiency of the model for planning and control in a range of challenging dexterous manipulation tasks, including fingertip 3D in-air manipulation, TriFinger in-hand manipulation, and Allegro hand on-palm reorientation, all with diverse objects. Our method consistently achieves state-of-the-art results: (I) a 96.5% average success rate across tasks, (II) high manipulation accuracy with an average reorientation error of 11{deg} and position error of 7.8 mm, and (III) model predictive control running at 50-100 Hz for all tested dexterous manipulation tasks. These results are achieved with minimal hyperparameter tuning.

Problem

• Robot Dexterity
• Multi-Point Contact Mechanics
• Real-time Operation

Innovation

• Lightweight Modeling
• Real-time Dextrous Manipulation
• Automated Friction Compliance