Date of Award

12-2024

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Mechanical and Civil Engineering

First Advisor

Kim-Doang Nguyen, Ph.D.

Second Advisor

Hector M. Gutierrez, Ph.D., PE

Third Advisor

Ryan T. White, Ph.D.

Fourth Advisor

Troy Nguyen, Ph.D., PE

Abstract

Abstract: The challenges of multi-robot navigation in dynamic environments, focusing on uncertainties in obstacle complexities, partial observation, and the transition of policies from simulations to the real world. The proposed approach utilizes a deep reinforcement learning (DRL) framework enabling a Light Detection and Ranging (LiDAR)-equipped robot to communicate with a camera-equipped robot to achieve optimal paths despite their different sensors. The key contributions include the development of a cooperative architecture for information exchange between robots, a DRL-based framework for learning navigation policies, and a training mechanism based on dynamic randomization for enhanced real-world adaptability. Experimental validation using Gazebo simulations demonstrates that a differential drive robot equipped with a LiDAR sensor can communicate with another robot equipped with a camera, to perform a task by exchanging sensor and camera data and using it for each robot to navigate the surrounding environment.

Download

Share

COinS