Search | Engineering

订阅投稿

首页工程期刊工程焦点工程成就工程前沿关于我们 English

资源类型

期刊论文 102

会议视频 7

年份

2023 15

2022 13

2021 10

2020 9

2019 9

2018 5

2017 5

2016 4

2015 6

2014 1

2013 1

2012 1

2011 2

2010 5

2009 2

2008 4

2007 3

2006 3

2001 1

2000 2

展开︾

关键词

自动驾驶 3

人工智能 2

驱动因素 2

2022全球工程前沿 1

21世纪海上丝绸之路 1

AUVs 1

CO₂排放 1

Car-to-X 通信系统 1

PM2.5 1

RGB-D 1

ROVs 1

下肢；外骨骼；自平衡；双足行走；模块化设计 1

二次调节 1

交通基础设施 1

产业链 1

人在回路AI 1

人工岛 1

人工智能2.0 1

人机混合智能 1

展开︾

检索范围：

排序：展示方式：

自动驾驶地图有关政策的思考和建议

刘经南,董杨,詹骄,高柯夫

《中国工程科学》 2019年第21卷第3期页码 92-97 doi: 10.15302/J-SSCAE-2019.03.004

摘要：

自动驾驶地图作为实现汽车自动驾驶的关键基础设施，对于推动我国自动驾驶领域的商业化开发至关重要。现阶段，我国受地图测绘、应用和监管等相关法律法规的制度掣肘，在自动驾驶地图的产业化进程方面相对滞后。为此，本文着重分析了我国在自动驾驶地图开发、应用和管理中面临的主要政策法规问题：自动驾驶地图是否需加密的问题、自动驾驶地图部分地理信息表达受限的问题、自动驾驶地图地理信息采集资质和审图流程的问题、自动驾驶地图事故责任和保险问题、自动驾驶地图相关测试规范和测试场景问题。同时结合国内外自动驾驶领域的发展趋势，给出加快我国自动驾驶汽车开发和商业化进程的四点建议：制定自动驾驶地图管理模式、允许自动驾驶地图应用试点及有序开放、适当放开企业权限及优化审核流程、建立国家级自动驾驶地图平台。

关键词：自动驾驶地图自动驾驶法规自动驾驶政策

HTML PDF 收藏

Evolutionary Decision-Making and Planning for Autonomous Driving Based on Safe and Rational Exploration

Kang Yuan,Yanjun Huang,Shuo Yang,Zewei Zhou,Yulei Wang,Dongpu Cao,Hong Chen,

《工程（英文）》 doi: 10.1016/j.eng.2023.03.018

摘要： Decision-making and motion planning are extremely important in autonomous driving to ensure safe driving in a real-world environment. This study proposes an online evolutionary decision-making and motion planning framework for autonomous driving based on a hybrid data- and model-driven method. First, a data-driven decision-making module based on deep reinforcement learning (DRL) is developed to pursue a rational driving performance as much as possible. Then, model predictive control (MPC) is employed to execute both longitudinal and lateral motion planning tasks. Multiple constraints are defined according to the vehicle’s physical limit to meet the driving task requirements. Finally, two principles of safety and rationality for the self-evolution of autonomous driving are proposed. A motion envelope is established and embedded into a rational exploration and exploitation scheme, which filters out unreasonable experiences by masking unsafe actions so as to collect high-quality training data for the DRL agent. Experiments with a high-fidelity vehicle model and MATLAB/Simulink co-simulation environment are conducted, and the results show that the proposed online-evolution framework is able to generate safer, more rational, and more efficient driving action in a real-world environment.

关键词： Autonomous driving Decision-making Motion planning Deep reinforcement learning Model predictive control

HTML PDF 收藏

一种用于自动驾驶的车辆概率性长期轨迹预测框架 Article

刘金鑫, 罗禹贡, 钟志华, 李克强, 黄荷叶, 熊辉

《工程（英文）》 2022年第19卷第12期页码 228-239 doi: 10.1016/j.eng.2021.12.020

摘要：

在混合动态交通环境中，准确地预测周围车辆长期范围内的运动轨迹是自动驾驶车辆（AV）实现合理行为决策和保障行车安全不可或缺的前提条件之一。本文提出了一种车辆长期轨迹预测的概率框架，由驾驶意图推理模型（DIM）和轨迹预测模型（TPM）组成。DIM基于动态贝叶斯网络进行设计和应用，用于准确推断车辆潜在的驾驶意图。文中所提出的DIM结合了基本的交通规则和车辆多维运动信息。为了进一步提高轨迹预测精度并实现预测不确定性识别，本文开发了基于高斯过程（GP）的TPM，综合考虑了车辆模型的短期预测结果和运动特性。最后，在高速换道场景下进行仿真验证，说明了新方法的有效性。通过与其他先进方法进行对比，展示并验证了该框架在车辆长期轨迹预测任务中的优异性能。

关键词：自动驾驶动态贝叶斯网络驾驶意图识别高斯过程车辆轨迹预测

HTML PDF 收藏

迈向L5级自动驾驶汽车的发展原则 Article

王建强, 黄荷叶, 李克强, 李骏

《工程（英文）》 2021年第7卷第9期页码 1313-1325 doi: 10.1016/j.eng.2020.10.018

摘要：

自动驾驶汽车的快速发展给现有交通出行方式带来了全新面貌和潜在挑战。目前，L3 级及以下驾驶辅助系统已经量产，L4 级在特定场景下的一些应用也逐步开发，通过逐渐提高车辆的自动化、智能化程度来不断向完全自动驾驶发展。然而，针对L5 级自动驾驶汽车的发展思路始终未明确，而现有针对L0~L4级自动驾驶发展过程的研发方式主要基于任务驱动来进行特定场景下的功能开发，难以揭示高等级自动驾驶汽车所需解决问题的本质逻辑和物理机制，进而阻碍了迈向L5 级自动驾驶的途径。本文通过探索高等级自动驾驶系统背后的物理机制，并从驾驶的本质出发，采用推理演绎方式，提出“大脑-小脑-器官”协调平衡框架，基于“乌鸦推理+鹦鹉学舌”的混合模式，探索“自主学习+先验知识”的研究范式，实现自动驾驶汽车“自学习、自适应、自超越”特性。从系统、统一、均衡的角度出发，基于最小作用量原理和统一安全场思想，旨在为高等级自动驾驶汽车，尤其是L5 级自动驾驶的研发提供一种全新的研发思路与有效途径。

关键词：自动驾驶汽车最小作用量原理行车安全场自主学习基础范式

HTML PDF 收藏

智能城市(iCity) 中自动驾驶汽车工业的关键挑战——高清地图 Perspective

Heiko G. Seif,胡晓龙

《工程（英文）》 2016年第2卷第2期页码 159-162 doi: 10.1016/J.ENG.2016.02.010

摘要：

本文对未来城市中自动驾驶的必要技术进行了深入的分析，从车载电脑运算、数据处理、路边基础设施和云解决方案等不同方面反映了科技的发展状况，主要对自动驾驶的核心技术——高清地图的应用所带来的挑战进行了描述。

关键词：自动驾驶交通基础设施智能城市(iCity) Car-to-X 通信系统汽车通信高清地图

HTML PDF 收藏

人在回路的深度强化学习算法及其在自动驾驶智能决策中的应用 Article

吴京达, 黄志宇, 胡中旭, 吕辰

《工程（英文）》 2023年第21卷第2期页码 75-91 doi: 10.1016/j.eng.2022.05.017

摘要：

由于机器学习智能和能力有限，它目前仍无法处理各种情况，因此不能在现实应用中完全取代人类。因为人类在复杂场景中表现出稳健性和适应性，所以将人类引入人工智能（AI）的训练回路并利用人类智能进一步提升机器学习算法变得至关重要。本研究开发了一种基于实时人类指导（Hug）的深度强化学习
（DRL）方法，用于端到端自动驾驶案例中的策略训练。通过新设计的人类与自动化之间的控制转移机制，人类能够在模型训练过程中实时干预和纠正智能体的不合理行为。基于这种人在回路的指导机制，本研究开发一种基于修正策略和价值网络的改良的演员-评论家架构（actor-critic architecture）。所提出的Hug-DRL的快速收敛允许实时的人类指导行为融合到智能体的训练回路中，进一步提高了DRL的效率和性能。本研究通过40 名受试者的人在回路实验对开发的方法进行了验证，并与其他最先进的学习方法进行了比较。结果表明，该方法可以在人类指导下有效地提高DRL算法的训练效率和性能，且不特定要求参与者的专业知识或经验。

关键词：人在回路AI 深度强化学习人类指导自动驾驶

HTML PDF 收藏

Semantic Consistency and Correctness Verification of Digital Traffic Rules

Lei Wan,Changjun Wang,Daxin Luo,Hang Liu,Sha Ma,Weichao Hu,

《工程（英文）》 doi: 10.1016/j.eng.2023.04.016

摘要： The consensus of the automotive industry and traffic management authorities is that autonomous vehicles must follow the same traffic laws as human drivers. Using formal or digital methods, natural language traffic rules can be translated into machine language and used by autonomous vehicles. In this paper, a translation flow is designed. Beyond the translation, a deeper examination is required, because the semantics of natural languages are rich and complex, and frequently contain hidden assumptions. The issue of how to ensure that digital rules are accurate and consistent with the original intent of the traffic rules they represent is both significant and unresolved. In response, we propose a method of formal verification that combines equivalence verification with model checking. Reasonable and reassuring digital traffic rules can be obtained by utilizing the proposed traffic rule digitization flow and verification method. In addition, we offer a number of simulation applications that employ digital traffic rules to assess vehicle violations. The experimental findings indicate that our digital rules utilizing metric temporal logic (MTL) can be easily incorporated into simulation platforms and autonomous driving systems (ADS).

关键词： Autonomous driving Traffic rules Digitization Formalization Verification

HTML PDF 收藏

大规模车辆排队的调度与规划技术的进展与挑战 Review

Jing Hou, Guang Chen, Jin Huang, Yingjun Qiao, Lu Xiong, Fuxi Wen, Alois Knoll, Changjun Jiang

《工程（英文）》 2023年第28卷第9期页码 26-48 doi: 10.1016/j.eng.2023.01.012

摘要：

Through vehicle-to-vehicle (V2V) communication, autonomizing a vehicle platoon can significantly reduce the distance between vehicles, thereby reducing air resistance and improving road traffic efficiency. The gradual maturation of platoon control technology is enabling vehicle platoons to achieve basic driving functions, thereby permitting large-scale vehicle platoon scheduling and planning, which is essential for industrialized platoon applications and generates significant economic benefits. Scheduling and planning are required in many aspects of vehicle platoon operation; here, we outline the advantages and challenges of a number of the most important applications, including platoon formation scheduling, lane-change planning, passing traffic light scheduling, and vehicle resource allocation. This paper's primary objective is to integrate current independent platoon scheduling and planning techniques into an integrated architecture to meet the demands of large-scale platoon applications. To this end, we first summarize the general techniques of vehicle platoon scheduling and planning, then list the primary scenarios for scheduling and planning technique application, and finally discuss current challenges and future development trends in platoon scheduling and planning. We hope that this paper can encourage related platoon researchers to conduct more systematic research and integrate multiple platoon scheduling and planning technologies and applications.

关键词： Autonomous vehicle platoon Autonomous driving Connected and automated vehicles Scheduling and planning techniques

HTML PDF 收藏

Spatiotemporal evolution and driving factors for GHG emissions of aluminum industry in China

《能源前沿（英文）》 2023年第17卷第2期页码 294-305 doi: 10.1007/s11708-022-0819-7

摘要： China’s aluminum (Al) production has released a huge amount of greenhouse gas (GHG) emissions. As one of the biggest country of primary Al production, China must mitigate its overall GHG emission from its Al industry so that the national carbon neutrality target can be achieved. Under such a background, the study described in this paper conducts a dynamic material flow analysis to reveal the spatiotemporal evolution features of Al flows in China from 2000 to 2020. Decomposition analysis is also performed to uncover the driving factors of GHG emission generated from the Al industry. The major findings include the fact that China’s primary Al production center has transferred to the western region; the primary Al smelting and carbon anode consumption are the most carbon-intensive processes in the Al life cycle; the accumulative GHG emission from electricity accounts for 78.14% of the total GHG emission generated from the Al industry; China’s current Al recycling ratio is low although the corresponding GHG emission can be reduced by 93.73% if all the primary Al can be replaced by secondary Al; and the total GHG emission can be reduced by 88.58% if major primary Al manufacturing firms are transferred from Inner Mongolia to Yunnan. Based upon these findings and considering regional disparity, several policy implications are proposed, including promotion of secondary Al production, support of clean electricity penetration, and relocation of the Al industry.

关键词： aluminum material flow analysis GHG (greenhouse gas) emissions LMDI (logarithmic mean divisa index)

HTML PDF 收藏

An autonomous miniature wheeled robot based on visual feedback control

CHEN Haichu

《机械工程前沿（英文）》 2007年第2卷第2期页码 197-200 doi: 10.1007/s11465-007-0033-7

摘要： Using two micro-motors, a novel omni-direction miniature wheeled robot is designed on the basis of the bi-corner driving principle. The robot takes advantage of the Bluetooth technology to wirelessly transmit data at a short distance. Its position and omni-direction motion are precise. A Charge Coupled Device (CCD) camera is used for measuring and for visual navi gation. A control system is developed. The precision of the position is 0.5 mm, the resolution is about 0.05 mm, and the maximum velocity is about 52 mm/s. The visual navigation and control system allow the robot to navigate and track the target and to accomplish autonomous locomotion.

关键词： measuring distance autonomous locomotion advantage navigation

HTML PDF 收藏

基于专家示教聚类经验池的高效深度强化学习 Research Article

王士珉1,赵彬琦1,张政锋1,张军平1,浦剑2

《信息与电子工程前沿（英文）》 2023年第24卷第11期页码 1541-1556 doi: 10.1631/FITEE.2300084

摘要：作为强化学习领域最基本的主题之一，样本效率对于深度强化学习算法的部署至关重要。与现有大多数从不同类型的后验分布中对动作进行采样的探索方法不同，我们专注于策略的采样过程，提出一种有效的选择性采样方法，通过对环境的内部层次结构建模来提高样本效率。具体来说，首先在策略采样过程中使用聚类方法生成动作候选集，随后引入一个用于对内部层次结构建模的聚类缓冲区，它由同轨数据、异轨数据以及专家数据组成，用于评估探索阶段动作候选集中不同类别动作的价值。通过这种方式，我们的方法能够更多地利用专家示教数据中的监督信息。在6种不同的连续运动环境中进行了实验，结果表明选择性采样方法具有卓越的强化学习性能和更快的收敛速度。特别地，在LGSVL任务中，该方法可以减少46.7%的收敛步数和28.5%的收敛时间。代码已开源，见https://github.com/Shihwin/SelectiveSampling。

关键词：强化学习；采样效率；采样过程；聚类方法；自动驾驶

HTML PDF 收藏

面向强化学习自动驾驶模型的异步监督学习预训练方法 Research Articles

王云鹏,郑坤贤,田大新,段续庭,周建山

《信息与电子工程前沿（英文）》 2021年第22卷第5期页码 615-766 doi: 10.1631/FITEE.1900637

摘要：基于人定规则所设计的自动驾驶系统可能会因大规模相互耦合的规则而变得越来越复杂，因此许多研究人员致力于探索基于学习的解决方案。强化学习（reinforcement learning，RL）因其在各种顺序控制问题上的出色表现而被应用于自动驾驶系统设计。然而，基于RL的自动驾驶系统落地应用所面临的主要挑战是其初始性能不佳。强化学习训练需要大量训练数据，然后模型才能达到合理的性能要求，这使得基于强化学习的模型不适用于现实环境，尤其在数据昂贵的情况下。本文为基于强化学习的端到端自动驾驶模型提出一种异步监督学习（asynchronous supervised learning，ASL）方法，以解决在实际环境中训练基于强化学习模型时初始性能差的问题。具体而言，通过在多个驾驶演示数据集上并行且异步执行多个监督学习过程，在异步监督学习预训练阶段引入先验知识。经过预训练后，模型将被部署到真实车辆上进一步开展强化学习训练，以适应实际环境并不断突破性能极限。本文在赛车模拟器TORCS（The Open Racing Car Simulator）上对所提出的预训练方法进行评估，以验证该方法在改善强化学习训练阶段端到端自动驾驶模型的初始性能和收敛速度方面足够可靠。此外，建立一个实车验证系统，以验证所提预训练方法在实车部署中的可行性。仿真结果表明，在有监督的预训练阶段使用一些演示，可以显著提高强化学习训练阶段的初始性能和收敛速度。

关键词：自主驾驶；自动驾驶车辆；强化学习；监督学习

HTML PDF 收藏

Toward autonomous mining: design and development of an unmanned electric shovel via point cloud-based

《机械工程前沿（英文）》 2022年第17卷第3期 doi: 10.1007/s11465-022-0686-2

摘要： With the proposal of intelligent mines, unmanned mining has become a research hotspot in recent years. In the field of autonomous excavation, environmental perception and excavation trajectory planning are two key issues because they have considerable influences on operation performance. In this study, an unmanned electric shovel (UES) is developed, and key robotization processes consisting of environment modeling and optimal excavation trajectory planning are presented. Initially, the point cloud of the material surface is collected and reconstructed by polynomial response surface (PRS) method. Then, by establishing the dynamical model of the UES, a point to point (PTP) excavation trajectory planning method is developed to improve both the mining efficiency and fill factor and to reduce the energy consumption. Based on optimal trajectory command, the UES performs autonomous excavation. The experimental results show that the proposed surface reconstruction method can accurately represent the material surface. On the basis of reconstructed surface, the PTP trajectory planning method rapidly obtains a reasonable mining trajectory with high fill factor and mining efficiency. Compared with the common excavation trajectory planning approaches, the proposed method tends to be more capable in terms of mining time and energy consumption, ensuring high-performance excavation of the UES in practical mining environment.

关键词： autonomous excavation unmanned electric shovel point cloud excavation trajectory planning

HTML PDF 收藏

基于驾驶脑的智能驾驶车辆硬件平台架构 Article

李德毅,高洪波

《工程（英文）》 2018年第4卷第4期页码 464-470 doi: 10.1016/j.eng.2018.07.015

摘要：

不同智能驾驶试验平台的传感器型号、数量、安装位置各不相同，导致传感器信息处理模块也各不相同；不同驾驶地图，其提供信息的粒度也没有固定标准，由此构成的智能驾驶系统软件模块的数量、接口各不相同。基于以驾驶脑为核心的智能驾驶车辆软件与硬件架构，决策模块将不直接与传感器信息处理模块发生关联，通过驾驶认知的形式化语言，将驾驶认知形式化，由驾驶脑认知形成决策。驾驶认知的形式化降低了传感器数量、类型、安装位置的变化对整个软件架构的影响，使得软件架构可以在不同传感器配置车辆平台上方便地移植。

关键词：驾驶脑智能驾驶硬件平台架构

HTML PDF 收藏

Extended model predictive control scheme for smooth path following of autonomous vehicles

《机械工程前沿（英文）》 2022年第17卷第1期页码 4-4 doi: 10.1007/s11465-021-0660-4

摘要： This paper presents an extended model predictive control (MPC) scheme for implementing optimal path following of autonomous vehicles, which has multiple constraints and an integrated model of vehicle and road dynamics. Road curvature and inclination factors are used in the construction of the vehicle dynamic model to describe its lateral and roll dynamics accurately. Sideslip, rollover, and vehicle envelopes are used as multiple constraints in the MPC controller formulation. Then, an extended MPC method solved by differential evolution optimization algorithm is proposed to realize optimal smooth path following based on driving path features. Finally, simulation and real experiments are carried out to evaluate the feasibility and the effectiveness of the extended MPC scheme. Results indicate that the proposed method can obtain the smooth transition to follow the optimal drivable path and satisfy the lateral dynamic stability and environmental constraints, which can improve the path following quality for better ride comfort and road availability of autonomous vehicles.

关键词： autonomous vehicles vehicle dynamic modeling model predictive control path following optimization algorithm