Confined Space Navigation via Deep Reinforcement Learning
Published in , 2023
Trained a robot to safely enter tight spaces like elevators using Deep RL. Presented at UR 2023.
Posts by Collection
projects
Multi-Robot System with TurtleBot4 & ROS 2
Published in , 2024
Built a real-world testing platform using TurtleBot4 robots and ROS2 for multi-robot navigation experiments.
Human Demonstration Collection in PyBullet
Published in , 2024
Developed a PyBullet-based interactive environment to collect human demonstrations for robot navigation learning.
Multi-Robot Path Planning with Isaac Sim
Published in , 2024
Developed a dynamic 3D simulation in Isaac Sim to test multi-robot scalability and collision-free path planning.
publications
Room for me?: Mobile Navigation for Entering a Confined Space Using Deep Reinforcement Learning
Published in Int. Conf. on Ubiquitous Robots (UR), 2023, 2023
<!– Inspired by challenges in elevator navigation, this work uses deep reinforcement learning to enable robots to safely enter confined spaces.
Safe Interval RRT* for Scalable Multi-Robot Path Planning in Continuous Space
Published in Preprint, 2025
<!– This paper proposes Safe Interval RRT*, a scalable algorithm for multi-robot path planning in continuous spaces.
Escaping Local Minima: Hybrid Artificial Potential Field with Wall-Follower for Decentralized Multi-Robot Navigation
Published in Int. Conf. on Robotics and Automation (ICRA), 2025, 2025
<!– We introduce a hybrid navigation algorithm that switches between Artificial Potential Field (APF) and Wall-Following (WF) to overcome local minima in decentralized multi-robot systems.
CARE: Enhancing Safety of Visual Navigation through Collision Avoidance via Repulsive Estimation
Published in Conference on Robot Learning (CoRL), 2025, 2025
Merry-Go-Round: Safe Control of Decentralized Multi-Robot Systems with Deadlock Prevention
Published in IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2025, 2025
<!– This paper proposes Safe Interval RRT*, a scalable algorithm for multi-robot path planning in continuous spaces.