Reinforcement learning for traffic light control with emphasis on emergency vehicles

Shamsi, Mahboubeh; Kenari, Abdolreza Rasouli; Aghamohammadi, Roghayeh

doi:10.1007/s11227-021-04068-w

Cited by 11 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Numerous studies have investigated the use of deep reinforcement learning techniques for traffic light control [21][22][23][24][25][26][27][28]. These techniques incorporate reinforcement learning and deep learning [29].…”

Section: Literature Reviewmentioning

confidence: 99%

A Resilient Intelligent Traffic Signal Control Scheme for Accident Scenario at Intersections via Deep Reinforcement Learning

2023

View full text Add to dashboard Cite

Deep reinforcement learning methods have shown promising results in the development of adaptive traffic signal controllers. Accidents, weather conditions, or special events all have the potential to abruptly alter the traffic flow in real life. The traffic light must take immediate and appropriate action based on a reasonable understanding of the environment. In this way, traffic congestion would be prevented. In this paper, we develop a reliable controller for such a highly dynamic environment and investigate the resilience of these controllers to a variety of environmental disruptions, such as accidents. In this method, the agent is provided with a complete understanding of the environment by discretizing the intersection and modifying the state space. The proposed algorithm is independent of the location and time of accidents. If the location of the accident changes, the agent does not need to be retrained. The agent is trained using deep Q-learning and experience replay. The model is evaluated in the traffic microsimulator SUMO. The simulation results demonstrate that the proposed method is effective at shortening queues when there is disruption.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Resilient Intelligent Traffic Signal Control Scheme for Accident Scenario at Intersections via Deep Reinforcement Learning

2023

View full text Add to dashboard Cite

show abstract

“…Gambar 3. Desain Sensor infra merah ke lampu pengatur lalu lintas HASIL DAN PEMBAHASAN Suatu perancangan sistem kendali lampu lalu lintas perlu untuk memperhatikan prioritas persimpangan dan lama waktu tunggu kendaraan [19], [20] .Perancangan gerbang logika ditetapkan bahwa ada persimpangan. Pada penelitian ini, persimpangan dari arah utara dan selatan merupakan arah jalan prioritas.…”

Section: Gambar 2 Modul Infra Merah Fc-51unclassified

Rancang Bangun Lampu Pengatur Lalu Lintas Berbasiskan Gerbang Logika

Mirshad,

Diputra,

Mulya

2023

JTEIN

View full text Add to dashboard Cite

Sistem kendali lampu lalu lintas (Lampu lalu lintas ) mengambil peran penting dalam memberikan pengaturan yang lebih baik dan mengontrol arus lalu lintas. Strategi yang lebih baik dalam pengendalian arus lalu lintas dapat meningkatkan pergerakan kendaraan dengan mempersingkat waktu perjalanan. Penulisan ini bertujuan untuk merancang dan membuat alat Lampu lalu lintas dengan gerbang logika. Perancangan peralatan menggunakan sistem tata lampu lalu lintas simpang empat fase yang berarti akan ada empat lampu hijau yang akan menyala secara bergantian dan empat lampu merah yang 3 hidup bersamaan. Tahap desain dimulai dari perancangan perangkat keras yang mengacu pada sistem blok diagram, selanjutnya program dibuat sesuai dengan perencanaan. Sensor Infra merah adalah komponen elektronika yang dapat mengidentifikasi cahaya infra merah (infra red, IR). Sensor infra merah atau detektor infra merah saat ini ada yang dibuat khusus dalam satu modul dan dinamakan sebagai IR Detector Photomodules. IR Detector Photomodules merupakan sebuah chip detektor infra merah digital yang di dalamnya terdapat fotodiode dan penguat (amplifier). Hasil pengujian alat ini menunjukkan LED dan seven segment yang ditampilkan akan menyala sesuai masukan sensor

show abstract

“…This algorithm prioritized transit vehicles while minimizing their impact on other vehicles on the road. Shamsi et al introduced dynamic scheduling of red and green phases of traffic signals [42]. This method reducing 11% of individual vehicle waiting time and average delay from 27% to 40% of emergency vehicles , effectively resolving the conflicts between those vehicles.…”

Section: Both Personal Vehicles and Others Are Consideredmentioning

confidence: 99%

A Review of Urban Real-time Traffic Signal Control

Ren¹,

Luo²,

He³

2023

AETR

View full text Add to dashboard Cite

Urban traffic congestion was a challenging problem. In recent years, researchers in the fields of transportation and computer science devoted considerable attention to studying real-time traffic signal control (RTSC) to alleviate urban traffic congestion. This paper reviewed various methods for RTSC, categorizing them based on the algorithms. Additionally, simulators were summarized to validate algorithm performances, and the analysis further explored the interrelationships between different traffic entities, optimization objectives, and network types. Finally, potential avenues for future research in traffic signal control (TSC) were discussed, with the aim of providing valuable references to researchers working on intelligent transportation systems (ITS) for practical implementations.

show abstract

Reinforcement learning for traffic light control with emphasis on emergency vehicles

Cited by 11 publications

References 14 publications

A Resilient Intelligent Traffic Signal Control Scheme for Accident Scenario at Intersections via Deep Reinforcement Learning

A Resilient Intelligent Traffic Signal Control Scheme for Accident Scenario at Intersections via Deep Reinforcement Learning

Rancang Bangun Lampu Pengatur Lalu Lintas Berbasiskan Gerbang Logika

A Review of Urban Real-time Traffic Signal Control

Contact Info

Product

Resources

About