Risk-Sensitive Model Predictive Control for Interaction-Aware Planning -- A Sequential Convexification Algorithm
By: Renzi Wang, Mathijs Schuurmans, Panagiotis Patrinos
Potential Business Impact:
Helps robots safely avoid bumping into things.
This paper considers risk-sensitive model predictive control for stochastic systems with a decision-dependent distribution. This class of systems is commonly found in human-robot interaction scenarios. We derive computationally tractable convex upper bounds to both the objective function, and to frequently used penalty terms for collision avoidance, allowing us to efficiently solve the generally nonconvex optimal control problem as a sequence of convex problems. Simulations of a robot navigating a corridor demonstrate the effectiveness and the computational advantage of the proposed approach.
Similar Papers
Safe Planning in Interactive Environments via Iterative Policy Updates and Adversarially Robust Conformal Prediction
Systems and Control
Makes self-driving cars safer around people.
Risk-Aware Safe Reinforcement Learning for Control of Stochastic Linear Systems
Systems and Control
Teaches robots to be safe and smart.
Tight Collision Avoidance for Stochastic Optimal Control: with Applications in Learning-based, Interactive Motion Planning
Systems and Control
Helps self-driving cars safely navigate busy roads.