Development of a Decision-Making Method for Trajectory Planning in an Uncertain Dynamic Environment for a Collaborative Mobile Robot

Abstract

This paper addresses the decision-making problem for trajectory planning of a collaborative mobile robot operating in an uncertain dynamic environment. A risk-aware trajectory planning method based on model predictive control is proposed, which integrates probabilistic state estimation of the robot and its environment with the prediction of dynamic obstacle motion and safety constraints. The method relies on the fusion of data from a camera, an inertial measurement unit, and an ultrasonic sensor, enabling increased robustness and adaptability of trajectory planning under sensor noise and incomplete information. Numerical simulation results confirm the effectiveness of the proposed approach in terms of maintaining safety margins, control stability, and goal reachability in complex navigation scenarios.