Local Navigation
Local navigation research focuses on enabling robots and autonomous systems to efficiently and safely navigate complex environments, achieving goals specified through various means, including language or visual cues. Current efforts concentrate on improving perception (e.g., using multi-sensor fusion, 3D reconstruction, and vision-language models) and planning (e.g., employing reinforcement learning, model predictive control, and A* search algorithms) in dynamic and cluttered settings. These advancements are crucial for applications ranging from autonomous vehicles and drones to assistive technologies for visually impaired individuals, impacting both robotics and accessibility.
Papers
SHINE: Social Homology Identification for Navigation in Crowded Environments
Diego Martinez-Baselga, Oscar de Groot, Luzia Knoedler, Luis Riazuelo, Javier Alonso-Mora, Luis Montano
RUMOR: Reinforcement learning for Understanding a Model of the Real World for Navigation in Dynamic Environments
Diego Martinez-Baselga, Luis Riazuelo, Luis Montano