PPO-based Reinforcement Learning for UAV Navigation in Urban Environments

Khalil Chikhaoui; Hakim Ghazzai; Yehia Massoud; IEEE

doi:10.1109/MWSCAS54063.2022.9859287

Back

Conference proceeding

PPO-based Reinforcement Learning for UAV Navigation in Urban Environments

Khalil Chikhaoui, Hakim Ghazzai, Yehia Massoud and IEEE

2022 IEEE 65th International Midwest Symposium on Circuits and Systems (MWSCAS), pp.1-4

01/01/2022

DOI: https://doi.org/10.1109/MWSCAS54063.2022.9859287

Abstract

Autonomous aerial vehicles

Autonomous navigation

deep reinforcement learning

Navigation

obstacle avoidance

proximal policy

Reinforcement learning

Solid modeling

Three-dimensional displays

UAV

Urban areas

Virtual environments

Autonomous navigation of unmanned aerial vehicles (UAVs) in urban environments is a difficult task due to the complexity of the surroundings and the battery limitations of the flying unit. In this paper, we present an autonomous framework for UAV navigation using deep reinforcement learning. We deploy a proximal policy optimization (PPO) algorithm for path planning with collision avoidance. The energy limitations of the UAV is taken into account to prevent crashes due to low battery situations. We develop a virtual environment that simulates a random three dimensional space with obstacles, and we use it to train the model and evaluate its performance. It is shown that 90% of the trips have been successfully accomplished.

Metrics

1 Record Views

Details

Title: PPO-based Reinforcement Learning for UAV Navigation in Urban Environments
Creators - without role: Khalil Chikhaoui - King Fahd University of Petroleum and Minerals
Hakim Ghazzai - King Abdullah University of Science and Technology
Yehia Massoud - King Abdullah University of Science and Technology
IEEE
Publication Details: 2022 IEEE 65th International Midwest Symposium on Circuits and Systems (MWSCAS), pp.1-4
Publisher: IEEE
Identifiers: 9945349008331
Academic Unit: King Abdullah University of Science & Technology; King Fahd University of Petroleum & Minerals
Language: English
Resource Type: Conference proceeding