A Planning Framework for Stable Robust Multi-Contact Manipulation

TL;DR

The paper addresses robust multi-contact manipulation by reframing it as a planning and optimization problem that explicitly accounts for contact stability and sensor-noise robustness. It introduces a quasi-static framework with a novel configuration space and impedance-based contact modeling, integrating friction-cone constraints, squeeze costs, and a Hessian-based stability criterion into a differentiable cost for Black-Box Optimization (BBO) and Dynamic Movement Primitives (DMP). The approach is extended to dual-arm peg-in-hole and Multi-Manipulator Multiple Peg-in-Hole (MMPiH) tasks, with parallel scenario training to boost robustness; stability is analytically derived and validated in simulations and real-world experiments, showing higher success rates than baseline DMP methods. The work advances robust, generalizable planning for contact-rich manipulation, with practical impact in precise assembly tasks under pose uncertainty and varying surface properties.

Abstract

While modeling multi-contact manipulation as a quasi-static mechanical process transitioning between different contact equilibria, we propose formulating it as a planning and optimization problem, explicitly evaluating (i) contact stability and (ii) robustness to sensor noise. Specifically, we conduct a comprehensive study on multi-manipulator control strategies, focusing on dual-arm execution in a planar peg-in-hole task and extending it to the Multi-Manipulator Multiple Peg-in-Hole (MMPiH) problem to explore increased task complexity. Our framework employs Dynamic Movement Primitives (DMPs) to parameterize desired trajectories and Black-Box Optimization (BBO) with a comprehensive cost function incorporating friction cone constraints, squeeze forces, and stability considerations. By integrating parallel scenario training, we enhance the robustness of the learned policies. To evaluate the friction cone cost in experiments, we test the optimal trajectories computed for various contact surfaces, i.e., with different coefficients of friction. The stability cost is analytical explained and tested its necessity in simulation. The robustness performance is quantified through variations of hole pose and chamfer size in simulation and experiment. Results demonstrate that our approach achieves consistently high success rates in both the single peg-in-hole and multiple peg-in-hole tasks, confirming its effectiveness and generalizability. The video can be found at https://youtu.be/IU0pdnSd4tE.

Figures (9)

• Figure 1: Overview of key factors affecting multi-contact robotic manipulation, including robustness, slip, and stability.
• Figure 2: Configuration space of multi-contact manipulation with friction.
• Figure 3: Planning framework with parallel scenarios for robust training, BBO selects the optimal DMP parameter ${\boldsymbol{\Theta}}$.
• Figure 4: Bimanual peg-in-hole insertion with impedance control.
• Figure 5: Stable v.s. unstable equilibrium