Drone swarm patrolling with uneven coverage requirements

Piciarelli, Claudio; Foresti, Gian Luca

doi:10.1049/iet-cvi.2019.0963

Cited by 9 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The patrolling method can identify suspicious behavior by utilizing single or multiple object optimization techniques to anticipate human movement [24,25]. This approach leverages heuristic search strategies to explore the impact of various intruder behaviors on search performance [26,27].…”

Section: Related Workmentioning

confidence: 99%

Flying Watchdog-Based Guard Patrol with Check Point Data Verification

Kuantama,

Seth,

James

et al. 2023

Future Internet

View full text Add to dashboard Cite

The effectiveness of human security-based guard patrol systems often faces challenges related to the consistency of perimeter checks regarding timing and patterns. Some solutions use autonomous drones for monitoring assistance but primarily optimize their camera-based object detection capabilities for favorable lighting conditions. This research introduces an innovative approach to address these limitations—a flying watchdog designed to augment patrol operations with predetermined flight patterns, enabling checkpoint identification and position verification through vision-based methods. The system has a laser-based data transmitter to relay real-time location and timing information to a receiver. The proposed system consists of drone and ground checkpoints with distinctive shapes and colored lights, further enhanced by solar panels serving as laser data receivers. The result demonstrates the drone’s ability to detect four white dot LEDs with square configurations at distances ranging from 18 to 20 m, even under deficient light conditions based on the OpenCV detection algorithm. Notably, the study underscores the significance of achieving an even distribution of light shapes to mitigate light scattering effects on readings while also confirming that ambient light levels up to a maximum of 390 Lux have no adverse impact on the performance of the sensing device.

show abstract

Section: Related Workmentioning

confidence: 99%

Flying Watchdog-Based Guard Patrol with Check Point Data Verification

Kuantama,

Seth,

James

et al. 2023

Future Internet

View full text Add to dashboard Cite

show abstract

“…Several other tasks, for which DRL-based solutions were suggested, are closely CPP-related. Typical examples are patrolling [23], [24], which is the task of checking an area of interest repeatedly, and the exploration of unknown environments [25]- [27].…”

Section: Related Workmentioning

confidence: 99%

UAV Coverage Path Planning under Varying Power Constraints using Deep Reinforcement Learning

Theile

Bayerlein

Nai

et al. 2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Coverage path planning (CPP) is a critical problem in robotics, where the goal is to find an efficient path that covers every point in an area of interest. This work addresses the power-constrained CPP problem with recharge for batterylimited unmanned aerial vehicles (UAVs). In this problem, a notable challenge emerges from integrating recharge journeys into the overall coverage strategy, highlighting the intricate task of making strategic, long-term decisions. We propose a novel proximal policy optimization (PPO)-based deep reinforcement learning (DRL) approach with map-based observations, utilizing action masking and discount factor scheduling to optimize coverage trajectories over the entire mission horizon. We further provide the agent with a position history to handle emergent state loops caused by the recharge capability. Our approach outperforms a baseline heuristic, generalizes to different target zones and maps, with limited generalization to unseen maps. We offer valuable insights into DRL algorithm design for longhorizon problems and provide a publicly available software framework for the CPP problem.

show abstract

“…Recently, deep reinforcement learning (DRL) [11] has been widely applied in robots for environment exploration [12], [13] and target-driven visual navigation [14]- [16] in unknown environments. However, differentiating from the full environment exploration problem, our CTS problem aims to infer potential locations of a target instead of maximizing the area covered.…”

Section: Introductionmentioning

confidence: 99%

Collaborative Target Search with a Visual Drone Swarm: An Adaptive Curriculum Embedded Multi-stage Reinforcement Learning Approach

Xiao¹,

Pisutsin²,

Feroskhan³

2022

Preprint

View full text Add to dashboard Cite

Equipping drones with target search capabilities is desirable for applications in disaster management scenarios and smart warehouse delivery systems. Instead of deploying a single drone, an intelligent drone swarm that can collaborate with one another in maneuvering among obstacles will be more effective in accomplishing the target search in a shorter amount of time.In this work, we propose a data-efficient reinforcement learningbased approach, Adaptive Curriculum Embedded Multi-Stage Learning (ACEMSL), to address the challenges of carrying out a collaborative target search with a visual drone swarm, namely the 3D sparse reward space exploration and the collaborative behavior requirement. Specifically, we develop an adaptive embedded curriculum, where the task difficulty level can be adaptively adjusted according to the success rate achieved in training. Meanwhile, with multi-stage learning, ACEMSL allows data-efficient training and individual-team reward allocation for the collaborative drone swarm. The effectiveness and generalization capability of our approach are validated using simulations and actual flight tests. The code is available at https://github.com/NTU-UAVG/ collaborative-target-search-vision-drone-swarm.git and the video is at https://youtu.be/LuCK97i5Bcw.

show abstract

Drone swarm patrolling with uneven coverage requirements

Cited by 9 publications

References 24 publications

Flying Watchdog-Based Guard Patrol with Check Point Data Verification

Flying Watchdog-Based Guard Patrol with Check Point Data Verification

UAV Coverage Path Planning under Varying Power Constraints using Deep Reinforcement Learning

Collaborative Target Search with a Visual Drone Swarm: An Adaptive Curriculum Embedded Multi-stage Reinforcement Learning Approach

Contact Info

Product

Resources

About