Green Energy and Intelligent Transportation最新文献

Degradation mechanism of lithium-ion battery under appropriate in-plane temperature gradient 适当面内温度梯度下锂离子电池的降解机理

IF 16.4

Green Energy and Intelligent Transportation Pub Date : 2025-09-04 DOI: 10.1016/j.geits.2025.100352

Zhichao Li , Zhiguo Qu , Zhiyuan Jiang , Hongbo Huang , Wenquan Tao

{"title":"Degradation mechanism of lithium-ion battery under appropriate in-plane temperature gradient","authors":"Zhichao Li , Zhiguo Qu , Zhiyuan Jiang , Hongbo Huang , Wenquan Tao","doi":"10.1016/j.geits.2025.100352","DOIUrl":"10.1016/j.geits.2025.100352","url":null,"abstract":"<div><div>Temperature significantly affects battery performance. However, the mechanism of in-plane temperature gradient caused by high current on battery degradation is still unclear. In this study, the in-plane temperature gradient is artificially constructed between battery tabs and bottom region. Then, the fast-charging cycling test is performed. Post-mortem analysis after battery cycling is carried out to obtain the anode surface morphology and elemental distribution. A three-dimensional electrochemical model is developed to obtain the internal parameter distributions during fast charging. The results indicate that the battery degradation process can be divided into three stages: in-plane current density gradient stage, in-plane temperature gradient stage, and emergence of degradation factors stage. A spatial matching criterion between in-plane temperature gradient and in-plane current density gradient is proposed to suppress battery degradation, where optimal performance is achieved when high current density region coincide with high temperature region. Specifically, the in-plane temperature gradient with high temperature at the high current density tabs and low temperature at the low current density bottom region enhances battery fast charging performance, maintaining over 90% capacity after 50 cycles at 2C charging rate. However, an in-plane temperature gradient in the opposite direction can lead to lithium plating and material cracking, with a 34.3% capacity loss after just 5 cycles. Additionally, the low-temperature discharge tests demonstrate that achieving the spatial matching criterion can enhance battery discharge performance. Specifically, the discharge capacity increases by 8% at −20 °C. This study provides a novel temperature-regulation-based approach for reducing battery polarization.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"4 6","pages":"Article 100352"},"PeriodicalIF":16.4,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A survey on hydrogen tanks for sustainable aviation 可持续航空氢气罐的研究进展

IF 16.4

Green Energy and Intelligent Transportation Pub Date : 2025-08-01 DOI: 10.1016/j.geits.2024.100224

Sergio Bagarello , Dario Campagna , Ivano Benedetti

{"title":"A survey on hydrogen tanks for sustainable aviation","authors":"Sergio Bagarello , Dario Campagna , Ivano Benedetti","doi":"10.1016/j.geits.2024.100224","DOIUrl":"10.1016/j.geits.2024.100224","url":null,"abstract":"<div><div>The aviation industry is facing challenges related to its environmental impact and thus the pressing need to develop aircraft technologies aligned with the society climate goals. Hydrogen is emerging as a potential clean fuel for aviation, as it offers several advantages in terms of supply potential and weight specific energy. One of the key factors enabling the use of H<sub>2</sub> in aviation is the development of reliable and safe storage technologies to be integrated into aircraft design. This work provides an overview of the technologies currently being investigated or developed for the storage of hydrogen within the aircraft, which would enable the use of hydrogen as a sustainable fuel for aviation, with emphasis on tanks material and structural aspects. The requirements dictated by the need of integrating the fuel system within existing or ex-novo aircraft architectures are discussed. Both the storage of gaseous and liquid hydrogen are considered and the main challenges related to the presence of either high internal pressures or cryogenic conditions are explored, in the background of recent literature. The materials employed for the manufacturing of hydrogen tanks are overviewed. The need to improve the storage tanks efficiency is emphasized and issues such as thermal insulation and hydrogen embrittlement are covered as well as the reference to the main structural health monitoring strategies. Recent projects dealing with the development of onboard tanks for aviation are eventually listed and briefly reviewed. Finally, considerations on the tank layout deemed more realistic and achievable in the near future are discussed.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"4 4","pages":"Article 100224"},"PeriodicalIF":16.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of lithium-ion batteries with different structures using magnetic field measurement for onboard battery identification 基于磁场测量的不同结构锂离子电池板载电池识别评价

IF 16.4

Green Energy and Intelligent Transportation Pub Date : 2025-08-01 DOI: 10.1016/j.geits.2025.100257

Aira Eto , Yutaro Akimoto , Keiichi Okajima , Jun Okano , Yukiko Onoue

{"title":"Evaluation of lithium-ion batteries with different structures using magnetic field measurement for onboard battery identification","authors":"Aira Eto , Yutaro Akimoto , Keiichi Okajima , Jun Okano , Yukiko Onoue","doi":"10.1016/j.geits.2025.100257","DOIUrl":"10.1016/j.geits.2025.100257","url":null,"abstract":"<div><div>When Original Equipment Manufacturer (OEM) lithium-ion batteries (LIBs) in electric vehicles are substituted with lower-quality non-OEM batteries, instances of non-OEM battery-related fires and other incidents have been documented in a report. This underscores the need for a technology capable of authenticating (LIBs) to avert such incidents, especially in electric vehicle applications. Current identification technologies, such as barcodes and integrated circuit (IC) chips, are in place; however, these technologies can be susceptible to counterfeiting through duplication or replacement. Therefore, this study focused on the magnetic field around the LIBs themselves. In previous studies, current distribution analysis of LIBs using magnetic sensors has been conducted as a nondestructive failure determination method. However, this method has not yet been applied to battery identification. This study proposes the identification of individual LIBs through magnetic analysis. Magnetic fields of prismatic LIBs with varying internal structures were measured, and differences between the results were evaluated using theoretical equations and simulations. Consequently, distinct magnetic fields were measured on the short sides of the cell for each sample. This distribution was attributed to the difference in the shape of the current collector. Even when using two cells connected in series to simulate a LIB module, a similar trend was observed in the magnetic field distribution. Magnetic sensors were utilized to measure the magnetic field characteristics of different internal structures of LIBs and reproduce relative relationships in the simulations. These results suggest that individual LIBs can be distinguished by strategically positioning magnetic sensors. The proposed system could serve as fundamental technology for identifying individual battery modules.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"4 4","pages":"Article 100257"},"PeriodicalIF":16.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144852733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LiDAR-IMU SLAM framework in autonomous modular bus docking systems 自主模块化公交对接系统中的LiDAR-IMU SLAM框架

IF 16.4

Green Energy and Intelligent Transportation Pub Date : 2025-07-25 DOI: 10.1016/j.geits.2025.100343

Yixu He , Yushu Gao , Yang Liu , Xiaobo Qu

{"title":"LiDAR-IMU SLAM framework in autonomous modular bus docking systems","authors":"Yixu He , Yushu Gao , Yang Liu , Xiaobo Qu","doi":"10.1016/j.geits.2025.100343","DOIUrl":"10.1016/j.geits.2025.100343","url":null,"abstract":"<div><div>The Autonomous Modular Bus (AMB) introduces an innovative approach to public transportation by allowing modular buses to dock and undock seamlessly while in motion. This capability effectively alleviates traffic congestion and decreases energy usage through smoother and more efficient vehicle operation. However, achieving autonomous docking for AMBs poses significant challenges, including the need for precise localization in both horizontal and vertical dimensions and the ability to manage dynamic persistent obstacles in close-range scenarios. Existing Light Detection and Ranging (LiDAR)-based Simultaneous Localization and Mapping (SLAM) algorithms, such as LIO-SAM, perform well in static environments but encounter limitations in dynamic scenarios, particularly with occlusions and vertical drift during AMB docking. In this paper, we propose an enhanced LiDAR-Inertial Measurement Unit (IMU) SLAM framework focused on improving localization accuracy and robustness during AMB docking. Key contributions include: (1) A two-stage scan-to-map matching method with ground constraints to reduce z-axis drift; (2) A factor graph optimization strategy integrating IMU roll and pitch constraints and periodic resetting to mitigate long-term drift; (3) A deep learning-based front vehicle detection and point cloud filtering mechanism to reduce occlusion effects. Experimental evaluations on single-vehicle and dual-vehicle datasets demonstrate that our method significantly reduces Absolute Pose Error (APE) and Relative Pose Error (RPE) compared to existing methods. These results highlight the framework's ability to address the unique challenges of AMB docking, therefore helping alleviate traffic congestion and reduce energy consumption.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"4 6","pages":"Article 100343"},"PeriodicalIF":16.4,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The effect of lead-based catalyst in-situ electrodeposition on the performance of iron-chromium redox flow batteries 铅基催化剂原位电沉积对铁铬氧化还原液流电池性能的影响

IF 16.4

Green Energy and Intelligent Transportation Pub Date : 2025-07-03 DOI: 10.1016/j.geits.2025.100331

Yingchun Niu , Wenjie Lv , Yinping Liu , Ziyu Liu , Ruichen Zhou , Xuan Zhou , Weiwei Guo , Wei Qiu , Chunming Xu , Quan Xu

{"title":"The effect of lead-based catalyst in-situ electrodeposition on the performance of iron-chromium redox flow batteries","authors":"Yingchun Niu , Wenjie Lv , Yinping Liu , Ziyu Liu , Ruichen Zhou , Xuan Zhou , Weiwei Guo , Wei Qiu , Chunming Xu , Quan Xu","doi":"10.1016/j.geits.2025.100331","DOIUrl":"10.1016/j.geits.2025.100331","url":null,"abstract":"<div><div>The performance of iron-chromium redox flow batteries is significantly influenced by the electrochemical activity of chromium and iron ions, with a particular emphasis on the reactivity of chromium. However, the impact of the chemical properties of chromium ions on the efficiency of electrochemical reactions remains largely unexplored. In this study, we introduced PbCl<sub>2</sub> into the electrolyte and achieved in-situ electrodeposition of the lead-based catalyst. Our findings indicate that the incorporation of lead ions effectively enhances the chromium half-reaction while inhibiting hydrogen evolution. Experimental analyses and molecular dynamics simulations reveal that PbCl<sub>2</sub> does not significantly affect the electrochemical performance of the electrolyte, its influence is mainly due to the electrochemical deposition on the electrode surface. The observed performance improvement is ascribed to the combined effects of Pb and Pb(ClO<sub>3</sub>)<sub>2</sub>, which catalyze the redox reaction of Cr<sup>3+</sup>/Cr<sup>2+</sup>. In situ differential electrochemical mass spectrometry monitoring of the hydrogen evolution signal demonstrates a clear inhibition of the hydrogen evolution reaction. Notably, the addition of 40 mM Pb<sup>2+</sup> significantly reduces the overpotential of the reaction, allowing the energy efficiency of the battery to reach 83.90% at a current density of 140 mA/cm<sup>2</sup>, which represents a 5.68% increase compared to the original electrolyte (78.22%). Furthermore, this configuration enables long-term stable operation over 400 cycles. This research presents an innovative approach to enhancing the performance of iron-chromium redox flow batteries, characterized by its simplicity and cost-effectiveness.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"4 6","pages":"Article 100331"},"PeriodicalIF":16.4,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cycle-efficient modeling for degradation staging and early life prediction of lithium batteries 锂电池退化分期和早期寿命预测的循环效率建模

IF 16.4

Green Energy and Intelligent Transportation Pub Date : 2025-06-27 DOI: 10.1016/j.geits.2025.100338

Can Wang , Renjie Wang , Jianming Li , Zhuangzhuang Li , Quanqing Yu

{"title":"Cycle-efficient modeling for degradation staging and early life prediction of lithium batteries","authors":"Can Wang , Renjie Wang , Jianming Li , Zhuangzhuang Li , Quanqing Yu","doi":"10.1016/j.geits.2025.100338","DOIUrl":"10.1016/j.geits.2025.100338","url":null,"abstract":"<div><div>An effective and time-saving early life prediction model is crucial for rapid battery assessment. However, existing models face a dilemma: they either rely heavily on extensive historical data or provide limited predictive insights into battery degradation. To address this, this study proposes a cycle-efficient battery life assessment framework integrating data-driven and empirical models. The framework consists of two components: degradation stage detection relying solely on data from one cycle and early life prediction using five-cycle data. The early life prediction model is capable of achieving joint prediction of the battery's remaining useful life and the cycle to knee point. Experimental results demonstrate that the degradation staging model achieves an accuracy of 0.977,6 for lithium iron phosphate batteries. Meanwhile, the early life prediction model yields mean absolute percentage errors of 10.5% for remaining useful life and 12.8% for the cycle to knee predictions. The model's accuracy and generalizability have been validated across diverse battery types, health states, and operating conditions. This proposed framework exhibits excellent generalizability capability under all evaluated scenarios, establishing a robust foundation for rapid battery design assessment and retirement decisions.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"4 5","pages":"Article 100338"},"PeriodicalIF":16.4,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144885772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A joint time-frequency analysis of the mechanical-electrochemical coupling mechanism from particles to electrodes for the Li-ion battery 锂离子电池从颗粒到电极的机械-电化学耦合机制时频联合分析

IF 16.4

Green Energy and Intelligent Transportation Pub Date : 2025-06-02 DOI: 10.1016/j.geits.2025.100322

Zihan Meng , Yuxuan Bai , Fangzhou Zhang , Jiujun Zhang , Qiu-An Huang

{"title":"A joint time-frequency analysis of the mechanical-electrochemical coupling mechanism from particles to electrodes for the Li-ion battery","authors":"Zihan Meng , Yuxuan Bai , Fangzhou Zhang , Jiujun Zhang , Qiu-An Huang","doi":"10.1016/j.geits.2025.100322","DOIUrl":"10.1016/j.geits.2025.100322","url":null,"abstract":"<div><div>Diffusion-induced stress (DIS) originates from the shrinkage/expand during Li extraction/insertion from/into the active particle for the Li-ion battery (LIB). Till today, the two-way coupled mechanical-electrochemical mechanism is still unclear. The above challenge can be decomposed into 2W + lH as follows: (i) Why need to reveal the two-way coupled mechanical-electrochemical mechanism? (ii) What is the two-way coupled mechanical-electrochemical mechanism? (iii) How to reveal the two-way coupled mechanical-electrochemical mechanism. In the process of answering the above 2W + lH, the following contributions have been made in this work: (i) An electro-chemo-mechanical (ECM) model is established for the LIB, in which the mechanical-electrochemical coupling is two-way; (ii) The mechanical-electrochemical responses are solved for the ECM model in the time/frequency domain, respectively; (iii) The time-domain analysis shows that DIS enhances Li diffusion at the early and middle stages of discharge, while DIS inhibits Li diffusion at the end of discharge; (iv) The frequency-domain analysis shows that stress mainly affects solid-phase diffusion instead of electrolyte-phase diffusion. In a word, the multi-scale analysis quantitatively analyzes the impact of DIS on Li diffusion on the particle scale and reveals the two-way coupled mechanical-electrochemical mechanism on the electrode scale. The above results provide theoretical support for the battery manufacture and stress monitoring.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"4 6","pages":"Article 100322"},"PeriodicalIF":16.4,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A comprehensive review on deep learning applications in advancing biodiesel feedstock selection and production processes 深度学习在推进生物柴油原料选择和生产过程中的应用综述

Green Energy and Intelligent Transportation Pub Date : 2025-06-01 DOI: 10.1016/j.geits.2025.100260

Olugbenga Akande , Jude A. Okolie , Richard Kimera , Chukwuma C. Ogbaga

{"title":"A comprehensive review on deep learning applications in advancing biodiesel feedstock selection and production processes","authors":"Olugbenga Akande , Jude A. Okolie , Richard Kimera , Chukwuma C. Ogbaga","doi":"10.1016/j.geits.2025.100260","DOIUrl":"10.1016/j.geits.2025.100260","url":null,"abstract":"<div><div>Biodiesel as a renewable alternative to conventional diesel is a growing topic of interest due to its potential environmental benefits. It is typically produced from oilseed crops such as soybean, rapeseed, palm oil, or animal fats. However, its sustainability is debated, primarily because of the reliance on edible oil feedstocks and associated economic and environmental concerns. This study explores alternative, non-edible feedstocks, such as algae and jatropha, that do not compete with food production, offering increased sustainability. Despite their potential, these feedstocks are hindered by high production costs. To address these challenges, innovative approaches in feedstock assessment are imperative for ensuring the long-term viability of biodiesel as an alternative fuel. This review examines explicitly the application of deep learning techniques in selecting and evaluating biodiesel feedstocks. It focuses on their production processes and the chemical and physical properties that impact biodiesel quality. Our comprehensive analysis demonstrates that ANNs provide significant insights into the feedstock assessment process, emerging as a potent tool for identifying new correlations within complex datasets. By leveraging this capability, ANNs can significantly advance biodiesel research, producing more sustainable and efficient feedstock production. The study concludes by highlighting the substantial potential of ANN modeling in contributing to renewable energy strategies and expanding biodiesel research, underscoring its vital role in accelerating the development of biodiesel as a sustainable fuel alternative.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"4 3","pages":"Article 100260"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144222124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel metaheuristic approach for simultaneous loss minimization and torque ripple reduction of DTC- IM driven EV 一种新的元启发式方法，用于同时减小直接转矩控制电机的损耗和转矩脉动

Green Energy and Intelligent Transportation Pub Date : 2025-06-01 DOI: 10.1016/j.geits.2025.100254

Anjan Kumar Sahoo

{"title":"A novel metaheuristic approach for simultaneous loss minimization and torque ripple reduction of DTC- IM driven EV","authors":"Anjan Kumar Sahoo","doi":"10.1016/j.geits.2025.100254","DOIUrl":"10.1016/j.geits.2025.100254","url":null,"abstract":"<div><div>The efficiency and torque ripple of an electric vehicle (EV) determine its performance and driving range. An optimum reference flux increases efficiency and decreases torque ripple and harmonics. This strategy used in the current literature is based on either a lookup table or a search control approach. However, these methods have convergence issues at optimal values, require large memory spaces, have higher computational complexity, and are difficult to implement. In the recent literature, efforts have been made to improve either the efficiency or the ripple, whereas in this paper, a multi-objective dynamic reference flux selection algorithm based on teamwork optimization is used to improve the efficiency and ripples simultaneously for a wide range of operating scenarios. The proposed dynamic reference flux selection algorithm is evaluated numerically and compared using standard drive cycles, and the amount of energy a vehicle uses during different drive cycles is compared. The results obtained justify the effectiveness and feasibility of the proposed algorithm over a wide range of driving conditions.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"4 3","pages":"Article 100254"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144511036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The investigation of reinforcement learning-based end-to-end decision-making algorithms for autonomous driving on the road with consecutive sharp turns 基于强化学习的连续急转弯道路自动驾驶端到端决策算法研究

Green Energy and Intelligent Transportation Pub Date : 2025-06-01 DOI: 10.1016/j.geits.2025.100288

Tongyang Li, Jiageng Ruan, Kaixuan Zhang

{"title":"The investigation of reinforcement learning-based end-to-end decision-making algorithms for autonomous driving on the road with consecutive sharp turns","authors":"Tongyang Li, Jiageng Ruan, Kaixuan Zhang","doi":"10.1016/j.geits.2025.100288","DOIUrl":"10.1016/j.geits.2025.100288","url":null,"abstract":"<div><div>Learning-based algorithm attracts great attention in the autonomous driving control field, especially for decision-making, to meet the challenge in long-tail extreme scenarios, where traditional methods demonstrate poor adaptability even with a significant effort. To improve the autonomous driving performance in extreme scenarios, specifically consecutive sharp turns, three deep reinforcement learning algorithms, i.e. Deep Deterministic Policy Gradient (DDPG), Twin Delayed Deep Deterministic policy gradient (TD3), and Soft Actor-Critic (SAC), based decision-making policies are proposed in this study. The role of the observation variable in agent training is discussed by comparing the driving stability, average speed, and consumed computational effort of the proposed algorithms in curves with various curvatures. In addition, a novel reward-setting method that combines the states of the environment and the vehicle is proposed to solve the sparse reward problem in the reward-guided algorithm. Simulation results from the road with consecutive sharp turns show that the DDPG, SAC, and TD3 algorithms-based vehicles take 367.2, 359.6, and 302.1 s to finish the task, respectively, which match the training results, and verifies the observation variable role in agent quality improvement.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"4 3","pages":"Article 100288"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144241793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0