Resources Allocation for Drones Tracking Utilizing Agent-Based Proximity Policy Optimization

This paper presents a reinforcement learning agent-based model that works by incorporating the MESA environment with the Stone Soup radar systems simulator. In particular, the Proximity Policy Optimization (PPO) reinforcement algorithm is used to discover a policy for sensor selection that results i...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: De Rochechouart, Maxence (author)
مؤلفون آخرون: Segrouchni, Amal El Fallah (author), Barbaresco, Frederic (author), Abu Zitar, Raed (author)
منشور في: 2023
الموضوعات:
الوصول للمادة أونلاين:https://depot.sorbonne.ae/handle/20.500.12458/1457
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1857415064025300992
author De Rochechouart, Maxence
author2 Segrouchni, Amal El Fallah
Barbaresco, Frederic
Abu Zitar, Raed
author2_role author
author
author
author_facet De Rochechouart, Maxence
Segrouchni, Amal El Fallah
Barbaresco, Frederic
Abu Zitar, Raed
author_role author
dc.creator.none.fl_str_mv De Rochechouart, Maxence
Segrouchni, Amal El Fallah
Barbaresco, Frederic
Abu Zitar, Raed
dc.date.none.fl_str_mv 2023
2024-01-03T06:13:55Z
2024-01-03T06:13:55Z
dc.identifier.none.fl_str_mv https://depot.sorbonne.ae/handle/20.500.12458/1457
10.1109/RADAR54928.2023.10371080
dc.language.none.fl_str_mv en
dc.relation.none.fl_str_mv 2023 IEEE International Radar Conference (RADAR)
dc.subject.none.fl_str_mv Proximity Policy Optimization (PPO)
Sensors Allocation
Drone Tracking
Fusion
dc.title.none.fl_str_mv Resources Allocation for Drones Tracking Utilizing Agent-Based Proximity Policy Optimization
dc.type.none.fl_str_mv Controlled Vocabulary for Resource Type Genres::text::conference object::conference proceedings
description This paper presents a reinforcement learning agent-based model that works by incorporating the MESA environment with the Stone Soup radar systems simulator. In particular, the Proximity Policy Optimization (PPO) reinforcement algorithm is used to discover a policy for sensor selection that results in optimum sensor resource allocation. In this work, one radar and one camera collaborate to generate tracks of a drone. The sequential measurements processing method is used to merge the inputs from the camera and the radar. An Extended Kalman Filter (EKF) is used to estimate the track. The learned system can apply sensor allocation online, works in real-time, and selects one radar and one camera at a time without having to reevaluate a cost function at every time step. Comparisons are done with the straight minimum entropy method and the random selection baseline method. The work demonstrates how machine learning techniques can capture resource allocation policy and help avoid the complexity of having to re-calculate cost function at every time step, especially when we have many radars and many cameras.
id sorbonner_ee1b63e8f5ae5fbd5fe993ba068136de
identifier_str_mv 10.1109/RADAR54928.2023.10371080
language_invalid_str_mv en
network_acronym_str sorbonner
network_name_str Sorbonne University Abu Dhabi repository
oai_identifier_str oai:depot.sorbonne.ae:20.500.12458/1457
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Resources Allocation for Drones Tracking Utilizing Agent-Based Proximity Policy OptimizationDe Rochechouart, MaxenceSegrouchni, Amal El FallahBarbaresco, FredericAbu Zitar, RaedProximity Policy Optimization (PPO)Sensors AllocationDrone TrackingFusionThis paper presents a reinforcement learning agent-based model that works by incorporating the MESA environment with the Stone Soup radar systems simulator. In particular, the Proximity Policy Optimization (PPO) reinforcement algorithm is used to discover a policy for sensor selection that results in optimum sensor resource allocation. In this work, one radar and one camera collaborate to generate tracks of a drone. The sequential measurements processing method is used to merge the inputs from the camera and the radar. An Extended Kalman Filter (EKF) is used to estimate the track. The learned system can apply sensor allocation online, works in real-time, and selects one radar and one camera at a time without having to reevaluate a cost function at every time step. Comparisons are done with the straight minimum entropy method and the random selection baseline method. The work demonstrates how machine learning techniques can capture resource allocation policy and help avoid the complexity of having to re-calculate cost function at every time step, especially when we have many radars and many cameras.2024-01-03T06:13:55Z2024-01-03T06:13:55Z2023Controlled Vocabulary for Resource Type Genres::text::conference object::conference proceedingshttps://depot.sorbonne.ae/handle/20.500.12458/145710.1109/RADAR54928.2023.10371080en2023 IEEE International Radar Conference (RADAR)oai:depot.sorbonne.ae:20.500.12458/14572024-01-03T06:13:55Z
spellingShingle Resources Allocation for Drones Tracking Utilizing Agent-Based Proximity Policy Optimization
De Rochechouart, Maxence
Proximity Policy Optimization (PPO)
Sensors Allocation
Drone Tracking
Fusion
title Resources Allocation for Drones Tracking Utilizing Agent-Based Proximity Policy Optimization
title_full Resources Allocation for Drones Tracking Utilizing Agent-Based Proximity Policy Optimization
title_fullStr Resources Allocation for Drones Tracking Utilizing Agent-Based Proximity Policy Optimization
title_full_unstemmed Resources Allocation for Drones Tracking Utilizing Agent-Based Proximity Policy Optimization
title_short Resources Allocation for Drones Tracking Utilizing Agent-Based Proximity Policy Optimization
title_sort Resources Allocation for Drones Tracking Utilizing Agent-Based Proximity Policy Optimization
topic Proximity Policy Optimization (PPO)
Sensors Allocation
Drone Tracking
Fusion
url https://depot.sorbonne.ae/handle/20.500.12458/1457