Bae, Han Jun Park, Juyoun 2025-08-19T08:34:07Z 2025-08-19T08:34:07Z 2025-08-18 2025-08 https://pubs.kist.re.kr/handle/201004/152953 Path planning is a key technique for vehicle navigation, and significant research has focused on how to manage obstacles. Previous methods have addressed either removing movable obstacles or avoiding immovable ones. However, real-world environments contain both movable and immovable obstacles. To address this, we propose a path planning system for Navigation Among Movable and IMmovable Obstacles (NAMIMO) based on hierarchical reinforcement learning. In our system, lower-level agents generate paths for the vehicle to either avoid or remove obstacles, while the higher-level agent dynamically selects which lower-level agent to utilize based on the movability of the obstacle, incorporating visual and linguistic knowledge. English Institute of Electrical and Electronics Engineers Inc. Hierarchical Reinforcement Learning for Navigation among Movable and Immovable Obstacles Article 10.1109/access.2025.3598230 1 IEEE Access, v.13, pp.142844 - 142851 IEEE Access 13 142844 142851 Y scie scopus 001554481400039 Computer Science, Information Systems Engineering, Electrical & Electronic Telecommunications Computer Science Engineering Telecommunications Article Navigation local path planning local path planning hierarchical reinforcement learning hierarchical reinforcement learning visual and linguistic knowledge visual and linguistic knowledge