Safe Machine-Learning-supported Model Predictive Force and Motion Control in Robotics
This work addresses safety-critical control for robotics, particularly in applications like handling fragile objects, but it is incremental as it builds on existing MPC and Gaussian process methods.
The paper tackles the problem of achieving safe and high-performance force and motion control in robotics, such as for human-robot interactions, by proposing a learning-supported model predictive control scheme that provides stochastic safety guarantees and adapts to changing situations, with validation through simulations and experiments on a lightweight robot.
Many robotic tasks, such as human-robot interactions or the handling of fragile objects, require tight control and limitation of appearing forces and moments alongside sensible motion control to achieve safe yet high-performance operation. We propose a learning-supported model predictive force and motion control scheme that provides stochastic safety guarantees while adapting to changing situations. Gaussian processes are used to learn the uncertain relations that map the robot's states to the forces and moments. The model predictive controller uses these Gaussian process models to achieve precise motion and force control under stochastic constraint satisfaction. As the uncertainty only occurs in the static model parts -- the output equations -- a computationally efficient stochastic MPC formulation is used. Analysis of recursive feasibility of the optimal control problem and convergence of the closed loop system for the static uncertainty case are given. Chance constraint formulation and back-offs are constructed based on the variance of the Gaussian process to guarantee safe operation. The approach is illustrated on a lightweight robot in simulations and experiments.