Future-Oriented Navigation for Autonomous Mobile Robots

Doktorsavhandling, 2025

As industrial environments become more dynamic and collaborative, Autonomous Mobile Robots (AMRs) are being deployed to work alongside humans. While hybrid human-robot settings offer improved efficiency and adaptability, they also challenge safety due to human behavior's inherent unpredictability. This thesis is motivated by the goal of enabling AMRs to anticipate and react to dynamic environments by integrating learning-based prediction with optimization-based control. Specifically, it focuses on safer and more efficient future-oriented navigation, i.e., decision-making that incorporates predictive information about the near future.

The core problem addressed in the thesis is: How can AMRs safely and efficiently navigate human-populated, dynamic environments by integrating perception, motion prediction, and optimization-based control? Specifically, this involves: (1) developing motion prediction methods capturing the uncertainty of human behavior; (2) designing control strategies incorporating predictive information; (3) ensuring the real-time performance of the system.

The main contributions of this thesis are threefold: (i) a "Factory with Vision" framework integrating perception, prediction, planning, and control; (ii) enhanced multimodal prediction techniques for downstream motion planning and control, and (iii) integration of motion prediction with both model predictive control and on-manifold control barrier functions. The proposed methods were evaluated in simulated scenarios with static and dynamic obstacles, including multi-agent environments. Performance was assessed in terms of safety, efficiency, and adaptability. Results show that the framework outperforms previously proposed approaches, offering more accurate motion prediction, safer navigation, and better handling of complex, dynamic environments.