Online optimal motion generation with guaranteed safety in shared workspace

Abstract

With new, safer manipulator robots, the probability of serious injury due to collisions with humans remains low (5%), even at speeds as high as 2 m.s −1. Collisions would better be avoided nevertheless, because they disrupt the tasks of both the robot and the human. We propose in this paper to equip robots with exteroceptive sensors and online motion generation so that the robot is able to perceive and react to the motion of the human in order to reduce the occurrence of collisions. It's impossible to guarantee that no collision will ever take place in a partially unknown dynamic environment such as a shared workspace, but we can guarantee instead that, if a collision takes place, the robot is at rest at the time of collision, so that it doesn't inject its own kinetic energy in the collision. To do so, we adapt a Model Predictive Control scheme which has been demonstrated previously with two industrial manipulator robots avoiding collisions while sharing their workspace. The proposed control scheme is validated in simulation.

Efficient and Collision-Free Human–Robot Collaboration Based on Intention and Trajectory Prediction

“…Considering the whole volume of obstacles across all prediction time steps for safe trajectory generation results in conservatively planned trajectories. Zheng et al [11] propose a framework to deal with this problem. They reformulate the obstacle avoidance problem into two Quadratic Programming (QP) programs.…”

“…Safe robot trajectories were generated online by solving two optimization problems in [10], [11], but under the assumption that the AH trajectory prediction was known already. Based on the predicted AH trajectory from our proposed motion prediction module, we can efficiently generate a safe robot trajectory by solving only one optimization problem with fewer objective functions.…”

Human Arm Motion Prediction for Collision Avoidance in a Shared Workspace

“…However, deep learning models are data greedy models and require heavy data for training which are not easily available for human hand prediction, and datasets contain point clouds that are not suitable for real-time applications. Therefore, as a more accessible approach, estimating human poses from RGB images captured by regular cameras and then mapping the 2D information into 3D space is efficient and widely practiced in industry and academia [6,9].…”

“…In this paper, we extend our previous work by predicting trajectories of human hands with our online trajectory generation framework [6] to ensure a safe and efficient humanrobot collaboration in a shared workspace. The trajectories generated for cobots are fused with the predicted trajectories of a human hand to ensure a collision free environment.…”

“…In our previous work, we proposed a model for predictive control scheme to generate trajectories for cobots that ensures a collision free environment in a shared workspace with humans by separating the work plane for the cobot [6]. The cobot automatically changes its trajectory to avoid the collision if a human hand enters the cobot plane.…”