Model predictive control of a collaborative manipulator considering dynamic obstacles

Abstract

SummaryCollaborative robots have to adapt its motion plan to a dynamic environment and variation of task constraints. Currently, they detect collisions and interrupt or postpone their motion plan to prevent harm to humans or objects. The more advanced strategy proposed in this article uses online trajectory optimization to anticipate potential collisions, task variations, and to adapt the motion plan accordingly. The online trajectory planner pursues a model predictive control approach to account for dynamic motion objectives and constraints during task execution. The prediction model relates reference joint velocities to actual joint positions as an approximation of built‐in robot tracking controllers. The optimal control problem is solved with direct collocation based on a hypergraph structure, which represents the nonlinear program and allows to efficiently adapt to structural changes in the optimization problem caused by moving obstacles. To demonstrate the effectiveness of the approach, the robot imitates pick‐and‐place tasks while avoiding self‐collisions, semistatic, and dynamic obstacles, including a person. The analysis of the approach concerns computation time, constraint violations, and smoothness. It shows that after model identification, order reduction, and validation on the real robot, parallel integrators with compensation for input delays exhibit the best compromise between accuracy and computational complexity. The model predictive controller can successfully approach a moving target configuration without prior knowledge of the reference motion. The results show that pure hard constraints are not sufficient and lead to nonsmooth controls. In combination with soft constraints, which evaluate the proximity of obstacles, smooth and safe trajectories are planned.

Adaptive Simplex Architecture for Safe, Real-Time Robot Path Planning

“…The performances of the proposed approach were compared with those of two ML-based methods [ 26 , 27 ], the development of which was driven by the requirements of human–robot collaboration, an efficient model predictive control (MPC)-based planning algorithm for 6-DOF manipulators with dynamic obstacle avoidance [ 31 ], and the popular Rapidly-exploring Random Trees (RRT) Connect [ 57 ] algorithm, which is integrated in the Robotics Library [ 58 ] and other open-source motion planning libraries. The first ML-based method, called Soft Actor-Critic with Hindsight Experience Replay (SAC–HER) [ 26 ], builds on reinforcement learning to plan motion paths for a dual-arm robot, with each arm having 3-DOF.…”

“…The second Soft Actor-Critic (SAC)-based method [ 27 ] extends the SAC–HER approach by using a dual-arm robot, with each arm having 7-DOF. The MPC-based algorithm [ 31 ] uses the distance between any of the six robot joints and one or several moving obstacles to plan a feasible trajectory for a 6-DOF robot. The method was tested using a UR 10 robot with moving objects and a full-scale human model.…”

“…To create a baseline for comparison, the experimental results from references [ 26 , 27 , 31 ], which provide information about the performances of the respective planning methods, were drawn upon. For the RRT Connect planner, an experiment in the Robotics Library [ 58 ] simulation environment was conducted.…”

“…The method seeks an optimal solution for tracking the desired position profiles accurately and robustly. The model predictive control-based algorithm introduced in reference [ 31 ] uses the distance between the end effector and one or several moving obstacles to plan a feasible trajectory for a 6-DOF robot. Intuitively, this approach comes close to the basic idea behind the path planning method proposed in this paper.…”

“…Intuitively, this approach comes close to the basic idea behind the path planning method proposed in this paper. However, in reference [ 31 ], closed-loop control rather than machine learning is used.…”