Corpus ID: 237490318

EMVLight: A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles

@article{Su2021EMVLightAD,
  title={EMVLight: A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles},
  author={Haoran Su and Yaofeng Desmond Zhong and Biswadip Dey and Amit Chakraborty},
  journal={ArXiv},
  year={2021},
  volume={abs/2111.00278}
}
  • Haoran Su, Yaofeng Desmond Zhong, +1 author Amit Chakraborty
  • Published 12 September 2021
  • Computer Science, Engineering
  • ArXiv
Emergency vehicles (EMVs) play a critical role in a city’s response to time-critical events such as medical emergencies and fire outbreaks. The existing approaches to reduce EMV travel time employ route optimization and traffic signal pre-emption without accounting for the coupling between route these two subproblems. As a result, the planned route often becomes suboptimal. In addition, these approaches also do not focus on minimizing disruption to the overall traffic flow. To address these… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 45 REFERENCES
Multiagent Reinforcement Learning for Integrated Network of Adaptive Traffic Signal Controllers (MARLIN-ATSC): Methodology and Large-Scale Application on Downtown Toronto
TLDR
This paper presents the development and evaluation of a novel system of multiagent reinforcement learning for integrated network of adaptive traffic signal controllers (MARLIN-ATSC), and shows unprecedented reduction in the average intersection delay. Expand
Real-time deep reinforcement learning based vehicle navigation
TLDR
A deep reinforcement learning (DRL) method to build a real-time intelligent vehicle routing and navigation system by formulating the task as a sequence of decisions is proposed and found that the achieved improvement of the proposed method becomes more significant under the maps with more edges and more complicated traffics comparing to the state-of-the-art navigation methods. Expand
ROUTE-BASED DYNAMIC PREEMPTION OF TRAFFIC SIGNALS FOR EMERGENCY VEHICLE OPERATIONS
A route-based dynamic strategy is developed for efficient preemption of traffic signals for emergency vehicles in real time. The proposed method combines an on-line route selection module and aExpand
Hierarchically and Cooperatively Learning Traffic Signal Control
TLDR
Empirically, HiLight outperforms state-of-the-art RL methods for traffic signal control in real road networks with real traffic and can easily learn a high-level policy that optimizes the objective locally by selecting among the sub-policies that respectively optimize short-term targets. Expand
A systematic review of route optimisation and pre-emption methods for emergency vehicles
TLDR
A systematic literature review of optimisation and pre-emption techniques for routing EVs, including optimisations using real-time dynamic traffic data, and considering time to travel as a critical parameter within dynamic route planning algorithms is presented. Expand
A Priority Algorithm to Control the Traffic Signal for Emergency Vehicles
TLDR
A priority signal control algorithm is presented to alleviate the impact of EVP on general traffic and reduces overall traffic delay by up to 8% compared to conventional EVP system. Expand
Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control
TLDR
This paper presents a fully scalable and decentralized MARL algorithm for the state-of-the-art deep RL agent, advantage actor critic (A2C), within the context of ATSC, and presents two methods to stabilize the learning procedure, by improving the observability and reducing the learning difficulty of each local agent. Expand
Dispatching and routing of emergency vehicles in disaster mitigation using data fusion
TLDR
A robust methodology for the dispatching and routing of emergency vehicles (EVs) in a post-disaster environment with the support of data fusion is developed, considering an earthquake scenario with a large number of casualties needing medical attention. Expand
CoLight: Learning Network-level Cooperation for Traffic Signal Control
TLDR
The proposed model, CoLight, is the first to use graph attentional networks in the setting of reinforcement learning for traffic signal control and to conduct experiments on the large-scale road network with hundreds of traffic signals. Expand
Connected-Vehicle-Based Traffic Signal Control Strategy for Emergency Vehicle Preemption
Connected Vehicle (CV) technologies such as Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) promise major benefits in both mobility and safety applications. One of the CV applications isExpand
...
1
2
3
4
5
...