Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Explicit Contact Optimization in Whole-Body Contact-Rich Manipulation

Victor Leve, João Moura, Namiko Saito, Steve Tonneau, Sethu Vijayakumar

TL;DR

The paper tackles planar Whole-Body Contact-Rich Manipulation (WBCRM) by introducing a continuous explicit-contact-location representation that enables hierarchical optimization for simultaneous contact-location planning and object pushing. It combines an RRT-inspired context sampling with a two-stage trajectory optimization and a tracking loop, demonstrating large improvements in convergence speed and feasibility over state-of-the-art methods. Key contributions include the explicit 2D surface parameterization p(\phi) and its integration into contact planning, long-horizon guidance, and contact-mode handling via complementarity constraints, achieving up to 99% fewer iterations and 96% faster planning on tested scenarios. The work demonstrates feasibility in simulation and preliminary hardware transfer, and outlines pathways to 3D extensions and real-time control, with practical implications for versatile WBCRM in robotics.

Abstract

Humans can exploit contacts anywhere on their body surface to manipulate large and heavy items, objects normally out of reach or multiple objects at once. However, such manipulation through contacts using the whole surface of the body remains extremely challenging to achieve on robots. This can be labelled as Whole-Body Contact-Rich Manipulation (WBCRM) problem. In addition to the high-dimensionality of the Contact-Rich Manipulation problem due to the combinatorics of contact modes, admitting contact creation anywhere on the body surface adds complexity, which hinders planning of manipulation within a reasonable time. We address this computational problem by formulating the contact and motion planning of planar WBCRM as hierarchical continuous optimization problems. To enable this formulation, we propose a novel continuous explicit representation of the robot surface, that we believe to be foundational for future research using continuous optimization for WBCRM. Our results demonstrate a significant improvement of convergence, planning time and feasibility - with, on the average, 99% less iterations and 96% reduction in time to find a solution over considered scenarios, without recourse to prone-to-failure trajectory refinement steps.

Explicit Contact Optimization in Whole-Body Contact-Rich Manipulation

TL;DR

The paper tackles planar Whole-Body Contact-Rich Manipulation (WBCRM) by introducing a continuous explicit-contact-location representation that enables hierarchical optimization for simultaneous contact-location planning and object pushing. It combines an RRT-inspired context sampling with a two-stage trajectory optimization and a tracking loop, demonstrating large improvements in convergence speed and feasibility over state-of-the-art methods. Key contributions include the explicit 2D surface parameterization p(\phi) and its integration into contact planning, long-horizon guidance, and contact-mode handling via complementarity constraints, achieving up to 99% fewer iterations and 96% faster planning on tested scenarios. The work demonstrates feasibility in simulation and preliminary hardware transfer, and outlines pathways to 3D extensions and real-time control, with practical implications for versatile WBCRM in robotics.

Abstract

Humans can exploit contacts anywhere on their body surface to manipulate large and heavy items, objects normally out of reach or multiple objects at once. However, such manipulation through contacts using the whole surface of the body remains extremely challenging to achieve on robots. This can be labelled as Whole-Body Contact-Rich Manipulation (WBCRM) problem. In addition to the high-dimensionality of the Contact-Rich Manipulation problem due to the combinatorics of contact modes, admitting contact creation anywhere on the body surface adds complexity, which hinders planning of manipulation within a reasonable time. We address this computational problem by formulating the contact and motion planning of planar WBCRM as hierarchical continuous optimization problems. To enable this formulation, we propose a novel continuous explicit representation of the robot surface, that we believe to be foundational for future research using continuous optimization for WBCRM. Our results demonstrate a significant improvement of convergence, planning time and feasibility - with, on the average, 99% less iterations and 96% reduction in time to find a solution over considered scenarios, without recourse to prone-to-failure trajectory refinement steps.
Paper Structure (29 sections, 18 equations, 7 figures)

This paper contains 29 sections, 18 equations, 7 figures.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. PROBLEM STATEMENT
  4. METHOD
  5. Pipeline
  6. Context Sampling
  7. Contact Planning
  8. Long-Horizon Guide
  9. Guide Tracking
  10. Representation
  11. Contact Location
  12. State-Space Representation
  13. Collision avoidance
  14. Contact modes as Complementarity Constraints
  15. State Distance and Reachability
  16. ...and 14 more sections

Figures (7)

  • Figure 1: Snapshots of a robot performing planar Whole-Body Contact-Rich Manipulation of a box in a real setup.
  • Figure 2: Problem representation of the planar Whole-Body Contact-Rich Manipulation.
  • Figure 3: Pipeline of the proposed method
  • Figure 4: Half-space separation between one convex body and one non-convex body to determine collision
  • Figure 5: Planning performance comparison between the state-of-the-art (SOTA) and our method (OURS).
  • ...and 2 more figures