Motion planning of collaborative robots is often required to simultaneously satisfy the contradictory objectives of reliably avoiding human workers and safely approaching them. In this article, we propose a new strategy that adaptively selects one of two objective functions based on the current operational region of the robot; the objective function for avoiding the worker with a distance larger than the safe distance, and the objective function for approaching the worker with a speed limitation for human safety. This strategy improves the worker safety while limiting the negative impact of the speed limit on time efficiency. The chattering related to the switching between the two objectives is solved using a continuous approximation of the switching based on uncertainties of the predicted worker's motion. We implement the proposed motion planning with the objective-switching strategy into a collaborative assembly system to deal with the worker moving with high irregularities. We experimentally evaluate the effectiveness of the proposed motion planning from the safety and efficiency points of view.

Collaborative robots are expected to work in cooperation with humans to improve productivity and maintain the quality of products. In the previous study, we have proposed an incremental learning system for adaptively scheduling a motion of the collaborative robot based on a worker's behavior. Although this system could model the worker's motion pattern precisely and robustly without collecting the worker's data in advance, it required two different models for modeling the worker's spatial and temporal features respectively and was not well considered for generalization. In this paper, we extend the previous incremental learning system by integrating the spatial and temporal models using a mixture model. In addition, we install a new incremental learning algorithm which improves a generalization capability of the mixture model and avoids overfitting in the situation where the prior information is limited. Implementing the proposed algorithm, we evaluate the effectiveness of the proposed system by experiments for several workers and for several assembly processes.

Industrial robots are expected to share the same workspace with human workers and work in cooperation with humans to improve the productivity and maintain the quality of products. In this situation, the worker's safety and work-time efficiency must be enhanced simultaneously. In this paper, we extend a task scheduling system proposed in the previous work by installing an online trajectory generation system. On the basis of the probabilistic prediction of the worker's motion and the receding horizon scheme for the trajectory planning, the proposed motion planning system calculates an optimal trajectory that realizes collision avoidance and the reduction of waste time simultaneously. Moreover, the proposed system plans the robot's trajectory adaptively based on updated predictions and its uncertainty to deal not only with the regular behavior of workers but also with their irregular behavior. We apply the proposed system to an assembly process where a two-link planar manipulator supports a worker by delivering parts and tools. After implementing the proposed system, we experimentally evaluate the effectiveness of the adaptive motion planning system.