Safe Human-Robot Collaboration via Collision Checking and Explicit Representation of Danger Zones

This paper deals with safe human-robot collaboration in the context of speed and separation monitoring paradigm. The core of the approach is to continuously track the separation distance between the robot and the human. The robot speed is then adjusted according to the perceived distance so that it will be able to stop before eventually come into contact with the human. We present an approach that aims at maximizing the productivity of the robot, i.e., its speed, while keeping the prescribed safety requirements satisfied. The method is based on explicit representation of danger zones – regions around the robot, where safety requirements are violated. The motion is then generated such that the robot moves as fast as possible, while its danger zone still does not collide with human operators. The approach is validated within an experimental study. Note to Practitioners—This article was motivated by the problem of maximizing productivity of the robotic manipulator while ensuring the safety of human collaborator. The increase in productivity is achieved by a faster traversal of predefined paths without compromising the safety of the human, which is specifically defined by industrial standard. The approach requires limited knowledge on robot’s dynamical properties. More precisely, we only need the braking time as a “lumped” representation of robot’s inertia. The underlying optimization problem is conveniently resolved by introducing danger zones that allow for intuitive visualization and geometrical representation of the regions around the robot that must be avoided. On the other hand, the method assumes the representation of humans via typical geometric primitives, which can be obtained using of-the-shelf depth perception systems. The solution to the problem reduces to a repeated collision checking between danger zones and the human. Such an approach turns out to be suitable for real-time implementation due to availability of fast and efficient collision checking algorithms/libraries.

I. Introduction

In today’s industrial contexts, removing physical barriers between human workers and robots has been a regular objective. Contemporary technologies that are in line with Industry 4.0 standards presume adaptable, reliable, and flexible production lines that require people and robots to work together closely. Accordingly, the area of human-robot collaboration (HRC) has grown dramatically from research lab demonstrations to real-world applications that are gaining traction even among small and medium-sized businesses. Emerging control techniques, coupled with contemporary hardware, geared at maintaining the most important feature of HRC– human safety– often make conventional safety standards too rigid and practically outdated [1]–[4].