High Precision Real Time Collision Detection
This work addresses the need for plug-and-play collision detection in robotics to enhance safety and reduce expert dependency, though it is incremental as it builds on the existing GJK algorithm.
The paper tackled the problem of enabling safe human-robot interactions by developing a high-precision, real-time collision detection system that requires only URDF descriptions, eliminating the need for extensive installation and calibration. The result demonstrated performance comparable to the Flexible Collision Library (FCL) when tested on robots like the KUKA LBR iiwa 7 R800 and Mecademic Meca500.
Collision detection and collision avoidance are essential components in these systems for safe human-robot interactions. Robotics systems that can work "out-of-the-box" without excessive amount of installation and calibration from the experts is highly ideal. For this, we propose a generic, high precision, collision detect system that only requires the unified robot description format (URDF) and is capable of running in real time. We extended the Gilbert-Johnson-Keerthi (GJK) algorithm by utilizing a geometrical approach to determine the distance between each rigid body in the environment and check for collisions. The proposed system's performance is shown by checking the self-collision of the KUKA LBR iiwa 7 R800 and the Mecademic Meca500. The performance is compared to the Flexible Collision Library (FCL).