Saved in:
Bibliographic Details
Main Authors: Naeem, Ashik Abrar, Haque, Mohammad Ariful
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.01787
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909011379486720
author Naeem, Ashik Abrar
Haque, Mohammad Ariful
author_facet Naeem, Ashik Abrar
Haque, Mohammad Ariful
contents Autonomous navigation and obstacle avoidance remain a core challenge of modern Unmanned Aerial Vehicles (UAVs). While traditional control methods struggle with the complexity and variability of the environment, reinforcement learning (RL) enables UAVs to learn adaptive behaviors through interaction with the environment. Existing research with RL prioritizes the mission success at the expense of mission time and safety of UAVs. This study integrates Potential Based Reward Shaping (PBRS) with Control Lyapunov Functions (CLF) and Control Barrier Functions (CBF) to simultaneously optimize mission time and ensure formal safety guarantees. An RL model is trained in a generalized simple environment, then used in complex scenarios incorporating a CLF-CBF-QP filter without further training. Experimental results in simulated environments demonstrate a significant reduction in mission time and outstanding performance in complex environment.
format Preprint
id arxiv_https___arxiv_org_abs_2605_01787
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Zero-Shot, Safe and Time-Efficient UAV Navigation via Potential-Based Reward Shaping, Control Lyapunov and Barrier Functions
Naeem, Ashik Abrar
Haque, Mohammad Ariful
Systems and Control
Machine Learning
Robotics
Autonomous navigation and obstacle avoidance remain a core challenge of modern Unmanned Aerial Vehicles (UAVs). While traditional control methods struggle with the complexity and variability of the environment, reinforcement learning (RL) enables UAVs to learn adaptive behaviors through interaction with the environment. Existing research with RL prioritizes the mission success at the expense of mission time and safety of UAVs. This study integrates Potential Based Reward Shaping (PBRS) with Control Lyapunov Functions (CLF) and Control Barrier Functions (CBF) to simultaneously optimize mission time and ensure formal safety guarantees. An RL model is trained in a generalized simple environment, then used in complex scenarios incorporating a CLF-CBF-QP filter without further training. Experimental results in simulated environments demonstrate a significant reduction in mission time and outstanding performance in complex environment.
title Zero-Shot, Safe and Time-Efficient UAV Navigation via Potential-Based Reward Shaping, Control Lyapunov and Barrier Functions
topic Systems and Control
Machine Learning
Robotics
url https://arxiv.org/abs/2605.01787