Comparative Analysis of Classical and Machine Learning Pathfinding Approaches

Author

Miguel Gapud, University of South AlabamaFollow

Date of Award

5-2025

Document Type

Undergraduate Thesis

Department

Computer Science

Faculty Mentor

George Clark

Advisor(s)

Na Gong, Todd McDonald

Abstract

Pathfinding is an essential task for any autonomous robot. Graph-based classical pathfinding algorithms and machine learning approaches have both been used for this end, but they are often not compared against each other. An implementation of end-to-end (E2E) pathfinding using Proximal Policy Optimization (PPO) and an Alexnet architecture is compared against an implementation of Hybrid A*. A digital twin in Unity3D is used as the testing environment with the Clearpath Dingo as the pathfinding robot. In machine learning, the robot is controlled using PPO through ROS-Noetic with a camera as its sensor. Hybrid A* and its controls are implemented directly in Unity3D. The two pathfinding algorithms were evaluated on path length and traversal time along a marked route in simulation. They are also evaluated on training time, path calculation time, and storage space. Experimental results showed that PPO had a success rate of only 28.68% over 10801 test runs. In successful runs, PPO produced paths that were 13.91 meters on average with a standard deviation of ± 0.22 meters, traversed in 34.32 seconds on average with a standard deviation of ± 4.54 seconds. Hybrid A* produced a path that was 13.36 meters, traversed in 22.69 seconds.

Recommended Citation

Gapud, Miguel, "Comparative Analysis of Classical and Machine Learning Pathfinding Approaches" (2025). Honors Theses. 113.
https://jagworks.southalabama.edu/honors_college_theses/113