Using Reinforcement Learning to Minimize the Probability of Delay Occurrence in Transportation

Cao, Zhiguang; Guo, Hongliang; Song, Wen; Gao, Kaizhou; Chen, Zhenghua; Zhang, Le; Zhang, Xuexi

doi:10.1109/tvt.2020.2964784

Cited by 56 publications

(20 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[40] employed a cardinality minimization approach to solve the stochastic shortest path problem. The authors further extended their research by employing the reinforcement learning method to improve the accuracy of finding the optimal shortest path so as to minimize the probability of delay occurrence [41]. The results yielded a feasible performance over other methods.…”

Section: Literature Review 21 Ambulance Planningmentioning

confidence: 99%

Local Dynamic Path Planning for an Ambulance Based on Driving Risk and Attraction Field

et al. 2021

View full text Add to dashboard Cite

Path planning is one of the most important aspects for ambulance driving. A local dynamic path planning method based on the potential field theory is presented in this paper. The potential field model includes two components—repulsive potential and attractive potential. Repulsive potential includes road potential, lane potential and obstacle potential. Considering the driving distinction between an ambulance and a regular vehicle, especially in congested traffic, an adaptive potential function for a lane line is constructed in association with traffic conditions. The attractive potential is constructed with target potential, lane-velocity potential and tailgating potential. The design of lane-velocity potential is to characterize the influence of velocity on other lanes so as to prevent unnecessary lane-changing behavior for the sake of time-efficiency. The results obtained from simulation demonstrate that the proposed method yields a good performance for ambulance driving in an urban area, which can provide support for designing an ambulance support system for the ambulance personnel and dispatcher.

show abstract

Section: Literature Review 21 Ambulance Planningmentioning

confidence: 99%

Local Dynamic Path Planning for an Ambulance Based on Driving Risk and Attraction Field

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In addition, traffic management to reduce congestion is a crucial topic in the smart city context, and numerous studies related to this topic were published [29,30]. A smart transportation system, or intelligent transportation system (ITS), focuses on economy and society interest, reduced travel times [31], arrival on time [32], fuel consumption, and pollution, as well as improving traffic safety. Several smart transportation system applications rely on the Internet of Things (IoT), including smart roads [33], intelligent parking systems [34,35], and real-world connected vehicle data [36].…”

Section: Introductionmentioning

confidence: 99%

Intelligent Total Transportation Management System for Future Smart Cities

Nguyen

Rohács

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Smart mobility and transportation, in general, are significant elements of smart cities, which account for more than 25% of the total energy consumption related to smart cities. Smart transportation has seven essential sections: leisure, private, public, business, freight, product distribution, and special transport. From the management point of view, transportation can be classified as passive or non-cooperating, semi-active or simple cooperating, active or cooperating, contract-based, and priority transportation. This approach can be applied to public transport and even to passengers of public transport. The transportation system can be widely observed, analyzed, and managed using an extensive distribution network of sensors and actuators integrated into an Internet of Things (IoT) system. The paper briefly discusses the benefits that the IoT can offer for smart city transportation management. It deals with the use of a hierarchical approach to total transportation management, namely, defines the concept, methodology, and required sub-model developments, which describes the total system optimization problems; gives the possible system and methodology of the total transportation management; and demonstrates the required sub-model developments by examples of car-following models, formation motion, obstacle avoidances, and the total management system implementation. It also introduces a preliminary evaluation of the proposed concept relative to the existing systems.

show abstract

“…This is because a shorter path may be more expensive than a longer path if the AUV needs to make many turns for the shorter path. Reinforcement Learning (RL) has been proven suitable for path finding problems with given constraints such as energy consumption or delay [11]. We model the AUV energy consumption to account for straight flights and flights at angled inclinations which consume more energy.…”

Section: Introductionmentioning

confidence: 99%

Energy Optimisation through Path Selection for Underwater Wireless Sensor Networks

Omeke

Mollel

Zhang

et al. 2020

2020 International Conference on UK-China Emerging Technologies (UCET)

View full text Add to dashboard Cite

This paper explores energy-efficient ways of retrieving data from underwater sensor fields using autonomous underwater vehicles (AUVs). Since AUVs are battery-powered and therefore energy-constrained, their energy consumption is a critical consideration in designing underwater wireless sensor networks. The energy consumed by an AUV depends on the hydrodynamic design, speed, on-board payload and its trajectory. In this paper, we optimise the trajectory taken by the AUV deployed from a floating ship to collect data from every cluster head in an underwater sensor network and return to the ship to offload the data. The trajectory optimisation algorithm models the trajectory selection as a stochastic shortest path problem and uses reinforcement learning to select the minimum cost path, taking into account that banked turns consume more energy than straight movement. We also investigate the impact of AUV speed on its energy consumption. The results show that our algorithm improves AUV energy consumption by up to 50% compared with the Nearest Neighbour algorithm for sparse deployments.

show abstract

Using Reinforcement Learning to Minimize the Probability of Delay Occurrence in Transportation

Cited by 56 publications

References 36 publications

Local Dynamic Path Planning for an Ambulance Based on Driving Risk and Attraction Field

Local Dynamic Path Planning for an Ambulance Based on Driving Risk and Attraction Field

Intelligent Total Transportation Management System for Future Smart Cities

Energy Optimisation through Path Selection for Underwater Wireless Sensor Networks

Contact Info

Product

Resources

About