Skip to content

Real-Time Obstacle Avoidance for Manipulators and Mobile Robots

Authors: Oussama Khatib

Published: 1985 (Conference Paper)

Source: Proceedings of the 1985 IEEE International Conference on Robotics and Automation

Algorithm: Artificial Potential Field

DOI: 10.1109/ROBOT.1985.1087247

Summary

Introduces the Artificial Potential Field (APF) method for real-time obstacle avoidance, where repulsive potentials push the robot away from obstacles and an attractive potential pulls it toward the goal. Extended to robotic manipulators via an operational-space formulation. Highly influential classical result; subsequent work addressed the local-minima problem inherent to gradient-descent on a potential surface.

Abstract

This paper presents a unique real-time obstacle avoidance approach for manipulators and mobile robots based on the "artificial potential field" concept. In this approach, collision avoidance, traditionally considered a high level planning problem, can be effectively distributed between different levels of control, allowing real-time robot operations in a complex environment. We have applied this obstacle avoidance scheme to robot arm using a new approach to the general problem of real-time manipulator control. We reformulated the manipulator control problem as direct control of manipulator motion in operational space-the space in which the task is originally described-rather than as control of the task's corresponding joint space motion obtained only after geometric and kinematic transformation. This method has been implemented in the COSMOS system for a PUMA 560 robot. Using visual sensing, real-time collision avoidance demonstrations on moving obstacles have been performed.

Primary

Paper doi.org

Standard

DOI 10.1109/ROBOT.1985.1087247

Tags

  • obstacle avoidance

  • potential field

  • mobile robots

  • robot arm

  • operational space

  • collision avoidance

  • real-time planning