Real Time Collision Avoidance with GPU-Computed Distance Maps

TL;DR

This paper introduces a real-time collision avoidance system for robotic manipulators using GPU-accelerated 3D distance transforms, enabling fast and accurate obstacle and self-collision avoidance during task execution.

Contribution

It presents a novel GPU-based framework that combines environment and robot self-modeling with real-time distance transform computations for collision avoidance.

Findings

Successfully implemented on Tiago robot with real-time performance.

Effectively avoids obstacles and self-collisions during dynamic tasks.

Outperforms CPU-based methods in speed and accuracy.

Abstract

This paper presents reactive obstacle and self-collision avoidance of redundant robotic manipulators within real time kinematic feedback control using GPU-computed distance transform. The proposed framework utilizes discretized representation of the robot and the environment to calculate 3D Euclidean distance transform for task-priority based kinematic control. The environment scene is represented using a 3D GPU-voxel map created and updated from a live pointcloud data while the robotic link model is converted into a voxels offline and inserted into the voxel map according to the joint state of the robot to form the self-obstacle map. The proposed approach is evaluated using the Tiago robot, showing that all obstacle and self collision avoidance constraints are respected within one framework even with fast moving obstacles while the robot performs end-effector pose tracking in real time. A comparison of related works that depend on GPU and CPU computed distance fields is also presented to highlight the time performance as well as accuracy of the GPU distance field.