Geometric reinforcement learning for path planning of UAVs

We proposed a new learning algorithm, named Geometric Reinforcement Learning (GRL), for path planning of Unmanned Aerial Vehicles (UAVs). The contributions of GRL are as: (1) GRL exploits a specific reward matrix, which is simple and efficient for path planning of multiple UAVs. The candidate points...

Full description

Bibliographic Details
Main Authors: Zhang, Baochang, Mao, Zhili, Liu, Wan-Quan, Liu, Jianzhuang
Format: Journal Article
Published: Springer Netherlands 2013
Online Access:http://hdl.handle.net/20.500.11937/13448
_version_ 1848748350021566464
author Zhang, Baochang
Mao, Zhili
Liu, Wan-Quan
Liu, Jianzhuang
author_facet Zhang, Baochang
Mao, Zhili
Liu, Wan-Quan
Liu, Jianzhuang
author_sort Zhang, Baochang
building Curtin Institutional Repository
collection Online Access
description We proposed a new learning algorithm, named Geometric Reinforcement Learning (GRL), for path planning of Unmanned Aerial Vehicles (UAVs). The contributions of GRL are as: (1) GRL exploits a specific reward matrix, which is simple and efficient for path planning of multiple UAVs. The candidate points are selected from the region along the Geometric path from the current point to the target point. (2) The convergence of calculating the reward matrix is theoretically proven, and the path in terms of path length and risk measure can be calculated. (3) In GRL, the reward matrix is adaptively updated based on the Geometric distance and risk information shared by other UAVs. Extensive experimental results validate the effectiveness and feasibility of GRL on the navigation of UAVs.
first_indexed 2025-11-14T07:03:38Z
format Journal Article
id curtin-20.500.11937-13448
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:03:38Z
publishDate 2013
publisher Springer Netherlands
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-134482017-09-13T15:01:02Z Geometric reinforcement learning for path planning of UAVs Zhang, Baochang Mao, Zhili Liu, Wan-Quan Liu, Jianzhuang We proposed a new learning algorithm, named Geometric Reinforcement Learning (GRL), for path planning of Unmanned Aerial Vehicles (UAVs). The contributions of GRL are as: (1) GRL exploits a specific reward matrix, which is simple and efficient for path planning of multiple UAVs. The candidate points are selected from the region along the Geometric path from the current point to the target point. (2) The convergence of calculating the reward matrix is theoretically proven, and the path in terms of path length and risk measure can be calculated. (3) In GRL, the reward matrix is adaptively updated based on the Geometric distance and risk information shared by other UAVs. Extensive experimental results validate the effectiveness and feasibility of GRL on the navigation of UAVs. 2013 Journal Article http://hdl.handle.net/20.500.11937/13448 10.1007/s10846-013-9901-z Springer Netherlands restricted
spellingShingle Zhang, Baochang
Mao, Zhili
Liu, Wan-Quan
Liu, Jianzhuang
Geometric reinforcement learning for path planning of UAVs
title Geometric reinforcement learning for path planning of UAVs
title_full Geometric reinforcement learning for path planning of UAVs
title_fullStr Geometric reinforcement learning for path planning of UAVs
title_full_unstemmed Geometric reinforcement learning for path planning of UAVs
title_short Geometric reinforcement learning for path planning of UAVs
title_sort geometric reinforcement learning for path planning of uavs
url http://hdl.handle.net/20.500.11937/13448