Date of Award

3-2025

Document Type

Thesis

Degree Name

Master of Science in Computer Science

Department

Department of Electrical and Computer Engineering

First Advisor

Timothy Machin, PhD

Abstract

Autonomous vehicles are increasingly being deployed for use in high-stakes and uncertain environments where safe and efficient navigation is critical. In these scenarios, traditional path planning approaches, which rely primarily on deterministic models and fixed assumptions, fall short due to the inherent uncertainty of dynamic threats, sensor inaccuracies, and incomplete information. This research addresses these challenges by developing a novel path-planning methodology that combines the Chance-Constrained Rapidly Exploring Random Tree* (CC-RRT*) algorithm with a probabilistic risk assessment heuristic. This method models uncertainty in sensor detection zones, obstacles in the environment, and the Autonomous Vehicle itself, which allows for uncertainty during the path-planning process. This research also incorporates an adaptive trade-off controlled by a tunable alpha parameter, which allows the AV to balance risk minimization and path efficiency based on varying mission objectives. The main contribution of this work is the ability to navigate complex environments by incorporating uncertainty into both the path-planning process and risk assessment. This research demonstrates that varying the alpha parameter can effectively control the UAV’s risk tolerance, leading to distinct path variability and trade-offs in risk and path efficiency. By analyzing many different environments and their planned paths, the methods in this research show the algorithm’s robustness and scalability, but also highlight specific scenarios where issues arose due to parameter tuning or environment complexities. By advancing risk-aware decision-making in uncertain environments, this research contributes to the growing field of probabilistic path planning and provides a foundation for real-world applications for military and civilian AV operations.

AFIT Designator

AFIT-ENG-MS-25-M-008

Comments

An embargo was observed for posting this thesis.

This work is marked Distribution A, Approved for Public Release. PA case number 88ABW-2025-0226

Download

Share

COinS