Representing Robot Geometry as Distance Fields: Applications to Whole-body Manipulation
Authors:
- 13 May 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 15351-15357
Abstract
In this work, we propose a novel approach to represent robot geometry as distance fields (RDF) that extends the principle of signed distance fields (SDFs) to articulated kinematic chains. Our method employs a combination of Bernstein polynomials to encode the signed distance for each robot link with high accuracy and efficiency while ensuring the mathematical continuity and differentiability of SDFs. We further leverage the kinematics chain of the robot to produce the SDF representation in joint space, allowing robust distance queries in arbitrary joint configurations. The proposed RDF representation is differentiable and smooth in both task and joint spaces, enabling its direct integration to optimization problems. Additionally, the 0-level set of the robot corresponds to the robot surface, which can be seamlessly integrated into whole-body manipulation tasks. We conduct various experiments in both simulations and with 7-axis Franka Emika robots, comparing against baseline methods, and demonstrating its effectiveness in collision avoidance and whole-body manipulation tasks. Project page: https://sites.google.com/view/lrdf/homeKeywords
All Related Versions
Funding Information
- China Scholarship Council
- European Commission
- National Science Foundation
This publication has 27 references indexed in Scilit:
- RAMP: Hierarchical Reactive Motion Planning for Manipulation Tasks Using Implicit Signed Distance Functions2023
- Neural Joint Space Implicit Signed Distance Functions for Reactive Robot Manipulator ControlIEEE Robotics and Automation Letters, 2022
- Regularized Deep Signed Distance Fields for Reactive Motion Generation2022
- Differentiable Collision Avoidance Using Collision Primitives2022
- Synthesizing Diverse and Physically Stable Grasps With Arbitrary Hand Structures Using Differentiable Force Closure EstimatorIEEE Robotics and Automation Letters, 2021
- Object Rearrangement Using Learned Implicit Collision Functions2021
- TT-TSDF: Memory-Efficient TSDF with Low-Rank Tensor Train Decomposition2020
- Mixture Models for the Analysis, Edition, and Synthesis of Continuous Time Series2019
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation2019
- Locally Weighted Regression for Control2012