Drone-Based Autonomous Motion Planning System for Outdoor Environments under Object Detection Uncertainty

Recent advances in autonomy of unmanned aerial vehicles (UAVs) have increased their use in remote sensing applications, such as precision agriculture, biosecurity, disaster monitoring, and surveillance. However, onboard UAV cognition capabilities for understanding and interacting in environments wit...

Full description

Bibliographic Details
Main Authors: Juan Sandino, Frederic Maire, Peter Caccetta, Conrad Sanderson, Felipe Gonzalez
Format: Article
Language:English
Published: MDPI AG 2021-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/13/21/4481
_version_ 1797511877983469568
author Juan Sandino
Frederic Maire
Peter Caccetta
Conrad Sanderson
Felipe Gonzalez
author_facet Juan Sandino
Frederic Maire
Peter Caccetta
Conrad Sanderson
Felipe Gonzalez
author_sort Juan Sandino
collection DOAJ
description Recent advances in autonomy of unmanned aerial vehicles (UAVs) have increased their use in remote sensing applications, such as precision agriculture, biosecurity, disaster monitoring, and surveillance. However, onboard UAV cognition capabilities for understanding and interacting in environments with imprecise or partial observations, for objects of interest within complex scenes, are limited, and have not yet been fully investigated. This limitation of onboard decision-making under uncertainty has delegated the motion planning strategy in complex environments to human pilots, which rely on communication subsystems and real-time telemetry from ground control stations. This paper presents a UAV-based autonomous motion planning and object finding system under uncertainty and partial observability in outdoor environments. The proposed system architecture follows a modular design, which allocates most of the computationally intensive tasks to a companion computer onboard the UAV to achieve high-fidelity results in simulated environments. We demonstrate the system with a search and rescue (SAR) case study, where a lost person (victim) in bushland needs to be found using a sub-2 kg quadrotor UAV. The navigation problem is mathematically formulated as a partially observable Markov decision process (POMDP). A motion strategy (or policy) is obtained once a POMDP is solved mid-flight and in real time using augmented belief trees (ABT) and the TAPIR toolkit. The system’s performance was assessed using three flight modes: (1) mission mode, which follows a survey plan and used here as the baseline motion planner; (2) offboard mode, which runs the POMDP-based planner across the flying area; and (3) hybrid mode, which combines mission and offboard modes for improved coverage in outdoor scenarios. Results suggest the increased cognitive power added by the proposed motion planner and flight modes allow UAVs to collect more accurate victim coordinates compared to the baseline planner. Adding the proposed system to UAVs results in improved robustness against potential false positive readings of detected objects caused by data noise, inaccurate detections, and elevated complexity to navigate in time-critical applications, such as SAR.
first_indexed 2024-03-10T05:53:11Z
format Article
id doaj.art-b6b6c48f97534b51aaf2127e17f5355f
institution Directory Open Access Journal
issn 2072-4292
language English
last_indexed 2024-03-10T05:53:11Z
publishDate 2021-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj.art-b6b6c48f97534b51aaf2127e17f5355f2023-11-22T21:34:03ZengMDPI AGRemote Sensing2072-42922021-11-011321448110.3390/rs13214481Drone-Based Autonomous Motion Planning System for Outdoor Environments under Object Detection UncertaintyJuan Sandino0Frederic Maire1Peter Caccetta2Conrad Sanderson3Felipe Gonzalez4School of Electrical Engineering and Robotics, Queensland University of Technology (QUT), 2 George Street, Brisbane, QLD 4000, AustraliaSchool of Electrical Engineering and Robotics, Queensland University of Technology (QUT), 2 George Street, Brisbane, QLD 4000, AustraliaData61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Building 101, Clunies Ross Street, Black Mountain, ACT 2601, AustraliaData61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Building 101, Clunies Ross Street, Black Mountain, ACT 2601, AustraliaSchool of Electrical Engineering and Robotics, Queensland University of Technology (QUT), 2 George Street, Brisbane, QLD 4000, AustraliaRecent advances in autonomy of unmanned aerial vehicles (UAVs) have increased their use in remote sensing applications, such as precision agriculture, biosecurity, disaster monitoring, and surveillance. However, onboard UAV cognition capabilities for understanding and interacting in environments with imprecise or partial observations, for objects of interest within complex scenes, are limited, and have not yet been fully investigated. This limitation of onboard decision-making under uncertainty has delegated the motion planning strategy in complex environments to human pilots, which rely on communication subsystems and real-time telemetry from ground control stations. This paper presents a UAV-based autonomous motion planning and object finding system under uncertainty and partial observability in outdoor environments. The proposed system architecture follows a modular design, which allocates most of the computationally intensive tasks to a companion computer onboard the UAV to achieve high-fidelity results in simulated environments. We demonstrate the system with a search and rescue (SAR) case study, where a lost person (victim) in bushland needs to be found using a sub-2 kg quadrotor UAV. The navigation problem is mathematically formulated as a partially observable Markov decision process (POMDP). A motion strategy (or policy) is obtained once a POMDP is solved mid-flight and in real time using augmented belief trees (ABT) and the TAPIR toolkit. The system’s performance was assessed using three flight modes: (1) mission mode, which follows a survey plan and used here as the baseline motion planner; (2) offboard mode, which runs the POMDP-based planner across the flying area; and (3) hybrid mode, which combines mission and offboard modes for improved coverage in outdoor scenarios. Results suggest the increased cognitive power added by the proposed motion planner and flight modes allow UAVs to collect more accurate victim coordinates compared to the baseline planner. Adding the proposed system to UAVs results in improved robustness against potential false positive readings of detected objects caused by data noise, inaccurate detections, and elevated complexity to navigate in time-critical applications, such as SAR.https://www.mdpi.com/2072-4292/13/21/4481unmanned aerial system (UAS)unmanned aerial vehicle (UAV)artificial intelligence (AI)embedded systemsmachine learning (ML)search and rescue (SAR)
spellingShingle Juan Sandino
Frederic Maire
Peter Caccetta
Conrad Sanderson
Felipe Gonzalez
Drone-Based Autonomous Motion Planning System for Outdoor Environments under Object Detection Uncertainty
Remote Sensing
unmanned aerial system (UAS)
unmanned aerial vehicle (UAV)
artificial intelligence (AI)
embedded systems
machine learning (ML)
search and rescue (SAR)
title Drone-Based Autonomous Motion Planning System for Outdoor Environments under Object Detection Uncertainty
title_full Drone-Based Autonomous Motion Planning System for Outdoor Environments under Object Detection Uncertainty
title_fullStr Drone-Based Autonomous Motion Planning System for Outdoor Environments under Object Detection Uncertainty
title_full_unstemmed Drone-Based Autonomous Motion Planning System for Outdoor Environments under Object Detection Uncertainty
title_short Drone-Based Autonomous Motion Planning System for Outdoor Environments under Object Detection Uncertainty
title_sort drone based autonomous motion planning system for outdoor environments under object detection uncertainty
topic unmanned aerial system (UAS)
unmanned aerial vehicle (UAV)
artificial intelligence (AI)
embedded systems
machine learning (ML)
search and rescue (SAR)
url https://www.mdpi.com/2072-4292/13/21/4481
work_keys_str_mv AT juansandino dronebasedautonomousmotionplanningsystemforoutdoorenvironmentsunderobjectdetectionuncertainty
AT fredericmaire dronebasedautonomousmotionplanningsystemforoutdoorenvironmentsunderobjectdetectionuncertainty
AT petercaccetta dronebasedautonomousmotionplanningsystemforoutdoorenvironmentsunderobjectdetectionuncertainty
AT conradsanderson dronebasedautonomousmotionplanningsystemforoutdoorenvironmentsunderobjectdetectionuncertainty
AT felipegonzalez dronebasedautonomousmotionplanningsystemforoutdoorenvironmentsunderobjectdetectionuncertainty