Stochastic and learning-based predictive control methods for physical human-robot interaction.

Collaborative Research Grants Program 2020-2022

The purpose of our project is to design innovative methods for workspace sharing of humans and robot manipulators based on recent developments in reinforcement learning (RL) and stochastic model predictive control (MPC), so as to tackle the inherent uncertainty of the human motion, at the same time guaranteeing the satisfaction of safety standards and taking care of the workers’ psychological well-being. The developed methods will be tested on two industrial case studies defined in collaboration with the Kazakhstani automotive manufacturing company Saryarka AvtoProm, involving factory workers.