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

Project: Research project

Grant Program

Collaborative Research Grants Program 2020-2022

Project Description

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.
StatusActive
Effective start/end date1/1/20 → 12/31/22

Fingerprint

Human robot interaction
Model predictive control
Reinforcement learning
Stochastic models
Manipulators
Industrial plants
Robots
Industry
Uncertainty

Keywords

  • Control systems
  • Model predictive control
  • Robotics
  • Human robot interaction