Self-organizing traffic lights: A realistic simulation

By Seung-Bae Cools, Carlos Gershenson, Bart D'Hooghe. Advances in Applied Self-organizing Systems, 2006

302 citations recorded by the source corpus.

We have previously shown in an abstract simulation (Gershenson in Complex Syst. 16(1):29–53, 2005) that selforganizing traffic lights can greatly improve traffic flow for any density. In this chapter, we extend these results to a realistic setting, implementing self-organizing traffic lights in an advanced traffic simulator using real data from a Brussels avenue. In the next section, a brief introduction to the concept of self-organization is given. The SOTL control method is then presented, followed by the moreVTS simulator. In Sect. 3.5, results from our simulations are shown, followed by Discussion, Future Work, and Conclusions.

Subfields: Building and Construction, Control and Systems Engineering, Transportation

View Paper: https://www.semanticscholar.org/paper/2ea05b32801eb6f7d5037e9701e6e96d7b8b755c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

1. Hua Wei
2. Guanjie Zheng
3. Chacha Chen
4. Kai Xu
5. Zhenhui Jessie Li
6. Nan Xu
7. Vikash V. Gayah
8. Yuanhao Xiong

In Control and Systems Engineering

1. Hua Wei
2. Guanjie Zheng
3. Zhenhui Jessie Li
4. Chacha Chen
5. Kai Xu
6. Nan Xu
7. Vikash V. Gayah
8. Yuanhao Xiong

In Transportation

1. Shalabh Bhatnagar
2. Yuanhao Xiong
3. Hongyuan Zha
4. Hua Wei
5. Chacha Chen
6. Nan Xu
7. Zhenhui Jessie Li
8. Kai Xu

Citations in the corpus

• Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large-Scale Traffic Signal Control (2020, background): “…approaches for traffic signal control can be categorized into following categories: pre-timed control (Koonce and Rodegerdts 2008), actuated con-trol (Cools, Gershenson, and D’Hooghe 2013), adaptive control (Lowrie 1990; Hunt et al. 1981), and optimization-based control (Varaiya 2013).”
• IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control (2018, background): “• Self-Organizing Traffic Light Control (SOTL) [5].”
• A Survey on Traffic Signal Control Methods (2019, background): “Self-Organizing Traffic Light Control (SOTL) is basically the same as fully-actuated control with additional demand responsive rules [Cools et al. 2013; Gershenson 2004].”
• Integrating Independent and Centralized Multi-agent Reinforcement Learning for Traffic Signal Network Optimization (2019, background): “While early works proposed to optimize traffic light controllers based on expert knowledge and traditional model-based planning [4, 9, 18], there are promising recent results on applying flexible model-free methods in reinforcement learning (RL) [21] and deep RL, such as DQN in particular [16], to f”
• Reinforcement Learning With Function Approximation for Traffic Signal Control (2011, methodology): “Full-state representations cannot directly be used in the case of road networks with multiple traffic junctions because of the exponential blowup in the computational requirements as the number of junctions and, thereby, the cardinalities of the state and action spaces increase.”