面向自動(dòng)協(xié)同駕駛的多車編隊(duì)任務(wù)分配策略

李長(zhǎng)樂; 張?jiān)其h; 張堯; 毛國(guó)強(qiáng); 賈存興

doi:10.11999/JEIT190557

面向自動(dòng)協(xié)同駕駛的多車編隊(duì)任務(wù)分配策略

doi: 10.11999/JEIT190557 cstr: 32379.14.JEIT190557

1.
西安電子科技大學(xué)綜合業(yè)務(wù)網(wǎng)理論及關(guān)鍵技術(shù)國(guó)家重點(diǎn)實(shí)驗(yàn)室西安 710071
2.
悉尼科技大學(xué)電氣與數(shù)據(jù)工程系悉尼 2007
3.
河北省高速公路京雄籌建處雄安 071799

基金項(xiàng)目: 國(guó)家自然科學(xué)基金(U1801266)，陜西省重點(diǎn)研發(fā)計(jì)劃項(xiàng)目(2018ZDXM-GY-038, 2018ZDCXL-GY-04-02)，陜西高校青年創(chuàng)新團(tuán)隊(duì)，西安市科技計(jì)劃項(xiàng)目(201809170CX11JC12)

詳細(xì)信息

作者簡(jiǎn)介:
李長(zhǎng)樂：男，1976年生，教授，博士生導(dǎo)師，研究方向?yàn)榫W(wǎng)聯(lián)網(wǎng)控?zé)o人駕駛、智能網(wǎng)聯(lián)汽車超視距感知、交通大數(shù)據(jù)分析及應(yīng)用、大規(guī)模網(wǎng)絡(luò)技術(shù)、高動(dòng)態(tài)網(wǎng)絡(luò)技術(shù)等

張?jiān)其h：男，1996年生，碩士生，研究方向?yàn)檐囕v編隊(duì)、協(xié)同駕駛

張堯：男，1993年生，博士生，研究方向?yàn)檐嚶?lián)網(wǎng)、邊緣計(jì)算、無線傳感器網(wǎng)絡(luò)

毛國(guó)強(qiáng)：男，1974年生，教授，博士生導(dǎo)師，研究方向?yàn)橹悄芙煌夹g(shù)、車聯(lián)網(wǎng)、智慧公路與智能網(wǎng)聯(lián)駕駛、下一代移動(dòng)通信系統(tǒng)(5G)關(guān)鍵技術(shù)研發(fā)、物聯(lián)網(wǎng)、無線定位技術(shù)等

賈存興：男，高級(jí)工程師，研究方向?yàn)楣放c水路運(yùn)輸、建筑科學(xué)與工程

通訊作者:
李長(zhǎng)樂　clli@mail.xidian.edu.cn

中圖分類號(hào): TN929.5
計(jì)量
- 文章訪問數(shù): 3240
- HTML全文瀏覽量: 1556
- PDF下載量: 187
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2019-07-25
- 修回日期: 2019-11-28
- 網(wǎng)絡(luò)出版日期: 2019-11-29
- 刊出日期: 2020-01-21

Task Assignment Strategy for Platoons in Cooperative Driving

1.
State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, China
2.
School of Electrical and Data Engineering, University of Technology Sydney, Sydney 2007, Australia
3.
Hebei Expressway Preparation and Construction Office for Beijing-Xiongan Expressway, Xiongan 071799, China

Funds: The National Natural Science Foundation of China (U1801266), The Key Research and Development Program of Shaanxi (2018ZDXM-GY-038, 2018ZDCXL-GY-04-02), The Youth Innovation Team of Shaanxi Universities, The Science and Technology Projects of Xi’an (201809170CX11JC12)

摘要

摘要: 自動(dòng)駕駛的實(shí)現(xiàn)需要大量車載傳感器的支持，然而，在有限車載計(jì)算資源條件下，由傳感器所產(chǎn)生的龐大數(shù)據(jù)量使得自動(dòng)駕駛?cè)蝿?wù)的實(shí)時(shí)性難以滿足，成為阻礙自動(dòng)駕駛技術(shù)進(jìn)一步發(fā)展的重要阻力。通過將駕駛?cè)蝿?wù)進(jìn)行協(xié)作處理，因而充分利用多個(gè)協(xié)作車輛的計(jì)算資源，自動(dòng)協(xié)同駕駛成為解決該問題的新途徑。而如何形成多車編隊(duì)并實(shí)現(xiàn)編隊(duì)中駕駛?cè)蝿?wù)分配則是實(shí)現(xiàn)自動(dòng)協(xié)同駕駛的關(guān)鍵。該文首先采用排隊(duì)理論G/G/1模型建立一種普適性車輛編隊(duì)網(wǎng)絡(luò)拓?fù)浞治瞿Ｐ停浞挚紤]編隊(duì)內(nèi)車輛間的任務(wù)協(xié)作能力和單個(gè)車輛的任務(wù)負(fù)荷，得出任務(wù)的處理時(shí)延和車輛系統(tǒng)中的平均任務(wù)數(shù)；其次，采用支持向量機(jī)(SVM)方法，基于車輛的負(fù)荷程度及處理能力將車輛的“空閑”、“繁忙”兩狀態(tài)進(jìn)行分類，進(jìn)而建立針對(duì)車輛協(xié)作任務(wù)分配的候選車輛集。最后，基于上述分析，該文提出面向多車編隊(duì)協(xié)同駕駛的任務(wù)均衡策略——基于分類的貪婪均衡策略(C-GBS)，以充分平衡編隊(duì)內(nèi)所有車輛的任務(wù)負(fù)荷并利用不同車輛的任務(wù)處理能力。仿真結(jié)果表明，該策略能夠減小重負(fù)荷網(wǎng)絡(luò)中的任務(wù)處理時(shí)延，有效提升自動(dòng)駕駛車輛的任務(wù)處理效率。
- 自動(dòng)協(xié)同駕駛 /
- 多車編隊(duì) /
- 任務(wù)分配 /
- 排隊(duì)論 /
- 支持向量機(jī)
Abstract: Autonomous vehicles are equipped with multiple on-board sensors to achieve self-driving functions. However, a tremendous amount of data is generated by autonomous vehicles, which significantly challenges the real-time task processing. Through multiple-vehicle cooperation, which makes the best of vehicle onboard computing resources, autonomous and cooperative driving becomes a promising candidate to solve the aforementioned problem. In this case, it is vital for autonomous and cooperative driving to form a driving platoon and allocate driving tasks efficiently. In this paper, a more general analytical model is developed based on G/G/1 queueing theory to model the topology of platoons. Next, Support Vector Machine (SVM) method is adopted to classify the “idle” and “busy” categories of the vehicles in the platoon based on their computing load and task processing capacity. Finally, based on the analysis above, an efficient task balancing strategy of platoons in autonomous and cooperative driving called Classification based Greed Balancing Strategy (C-GBS) is proposed, in order to balance the task burden among vehicles and cooperate more efficiently. Extensive simulations demonstrate that the proposed technique can reduce the processing delay of driving tasks in platoons with high computing load, which will improve the processing efficiency in autonomous vehicles.
- Autonomous and cooperative driving /
- Platoon /
- Task assignment /
- Queuing theory /
- Support Vector Machine (SVM)

HTML全文

圖 1 自動(dòng)協(xié)同駕駛的多車編隊(duì)場(chǎng)景示意圖

下載: 全尺寸圖片幻燈片

圖 2 車輛編隊(duì)網(wǎng)絡(luò)拓?fù)浣?/p>

下載: 全尺寸圖片幻燈片

圖 3 不同分配策略的任務(wù)總時(shí)延

下載: 全尺寸圖片幻燈片

圖 4 不同分配策略的處理時(shí)延比值關(guān)系圖

下載: 全尺寸圖片幻燈片

圖 5 不同分配策略的系統(tǒng)資源利用率

下載: 全尺寸圖片幻燈片

表 1 C-GBS算法

　輸入：車輛集$V$，任務(wù)集T

　輸出：結(jié)果集S

　(1) 基于對(duì)車輛狀態(tài)的分類，初始化候選車輛集${V_1}$和結(jié)果集S；

　(2) 遍歷任務(wù)集T，選取T 中時(shí)延門限${T_i}$最小的任務(wù)${t_i}$，對(duì)其進(jìn)行
　　分配；

　(3) 選擇候選車輛集${V_1}$中的第1輛車${v_{k,1}}$，根據(jù)${v_{k,1}}$的處理速率和
　　任務(wù)${t_i}$的size_i估計(jì)${v_{k,1}}$處理任務(wù)${t_i}$所需的時(shí)間${\tau _{i,1}}$，并令
　　 $ {\tau _i} = {\tau _{i,1}},\kappa = 1$；

　(4) 遍歷候選車輛集${V_1}$，依次計(jì)算${V_1}$中每輛車v_k處理任務(wù)${t_i}$所需
　　時(shí)間${\tau _{i,k}}$，若${\tau _{i,k}}<{\tau _{i}}$，則令$ {\tau _i} = {\tau _{i,k}},\kappa = k$；

　(5) 遍歷${V_1}$完成后，將任務(wù)${t_i}$分配給${V_1}$中的第$ \kappa $輛車處理；

　(6) 更新車輛v_k的狀態(tài)，更新候選車輛集${V_1}$，更新任務(wù)集T并更
　　新結(jié)果集S記錄每項(xiàng)任務(wù)的處理情況；

　(7) 返回第(2)步，繼續(xù)執(zhí)行，直到任務(wù)全部完成。

下載: 導(dǎo)出CSV

參考文獻(xiàn)(25)

CESARI G, SCHILDBACH G, CARVALHO A, et al. Scenario model predictive control for lane change assistance and autonomous driving on highways[J]. IEEE Intelligent Transportation Systems Magazine, 2017, 9(3): 23–35. doi: 10.1109/MITS.2017.2709782

CHANG L and DORMEHL L. 6 self-driving car crashes that tapped the brakes on the autonomous revolution[EB/OL]. https://www.digitaltrends.com/cool-tech/most-significant-self-driving-car-crashes/, 2018.

SU Zhou, HUI Yilong, XU Qichao, et al. An edge caching scheme to distribute content in vehicular networks[J]. IEEE Transactions on Vehicular Technology, 2018, 67(6): 5346–5356. doi: 10.1109/TVT.2018.2824345

AISSIOUI A, KSENTINI A, GUEROUI A M, et al. On enabling 5G automotive systems using follow me edge-cloud concept[J]. IEEE Transactions on Vehicular Technology, 2018, 67(6): 5302–5316. doi: 10.1109/TVT.2018.2805369

TRAN T X, HAJISAMI A, PANDEY P, et al. Collaborative mobile edge computing in 5G networks: New paradigms, scenarios, and challenges[J]. IEEE Communications Magazine, 2017, 55(4): 54–61. doi: 10.1109/MCOM.2017.1600863

LUAN T H, CAI L X, CHEN Jiming, et al. Engineering a distributed infrastructure for large-scale cost-effective content dissemination over urban vehicular networks[J]. IEEE Transactions on Vehicular Technology, 2014, 63(3): 1419–1435. doi: 10.1109/TVT.2013.2251924

SU Zhou, HUI Yilong, and GUO Song. D2D-based content delivery with parked vehicles in vehicular social networks[J]. IEEE Wireless Communications, 2016, 23(4): 90–95. doi: 10.1109/MWC.2016.7553031

LI S E, GAO Feng, LI Keqiang, et al. Robust longitudinal control of multi-vehicle systems-a distributed h-infinity method[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(9): 2779–2788. doi: 10.1109/TITS.2017.2760910

JAIN A, GHOSE D, and MENON P P. Multi-vehicle formation in a controllable force field with non-identical controller gains[J]. IET Control Theory & Applications, 2018, 12(6): 802–811.

LI Xin and ZHU Daqi. An adaptive SOM neural network method for distributed formation control of a group of AUVs[J]. IEEE Transactions on Industrial Electronics, 2018, 65(10): 8260–8270.

LIU Yuanchang and BUCKNALL R. A survey of formation control and motion planning of multiple unmanned vehicles[J]. Robotica, 2018, 36(7): 1019–1047. doi: 10.1017/S0263574718000218

ZHU Daqi, CAO Xiang, SUN Bing, et al. Biologically inspired self-organizing map applied to task assignment and path planning of an AUV system[J]. IEEE Transactions on Cognitive and Developmental Systems, 2018, 10(2): 304–313. doi: 10.1109/TCDS.2017.2727678

GODFREY G A and POWELL W B. An adaptive dynamic programming algorithm for dynamic fleet management, II: Multiperiod travel times[J]. Transportation Science, 2002, 36(1): 40–54. doi: 10.1287/trsc.36.1.40.572

VIEGAS D, BATISTA P, OLIVEIRA P, et al. Discrete-time distributed Kalman filter design for formations of autonomous vehicles[J]. Control Engineering Practice, 2018, 75: 55–68. doi: 10.1016/j.conengprac.2018.03.014

The 5G Infrastructure Public Private Partnership (5G PPP). 5G PPP white paper on automotive vertical sectors[EB/OL]. https://5g-ppp.eu/wp-content/uploads/2014/02/5G-PPP-White-Paper-on-Automotive-Vertical-Sectors.pdf, 2015.

PENG Haixia, LI Dazhou, ABBOUD K, et al. Performance analysis of IEEE 802.11p DCF for multiplatooning communications with autonomous vehicles[J]. IEEE Transactions on Vehicular Technology, 2017, 66(3): 2485–2498. doi: 10.1109/TVT.2016.2571696

3GPP. Study on LTE-based V2X services[EB/OL]. https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=2934.

PIRO G, ORSINO A, CAMPOLO C, et al. D2D in LTE vehicular networking: System model and upper bound performance[C]. The 7th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, Brno, Czech Republic, 2015: 281–286.

WHITT W. The queueing network analyzer[J]. The Bell System Technical Journal, 1983, 62(9): 2779–2815. doi: 10.1002/j.1538-7305.1983.tb03204.x

DAVIS J L, MASSEY W A, and WHITT W. Sensitivity to the service-time distribution in the nonstationary erlang loss model[J]. Management Science, 1995, 41(6): 1107–1116. doi: 10.1287/mnsc.41.6.1107

LI Changle, ZHANG Yao, LUAN T H, et al. Building transmission backbone for highway vehicular networks: Framework and analysis[J]. IEEE Transactions on Vehicular Technology, 2018, 67(9): 8709–8722. doi: 10.1109/TVT.2018.2844471

WHITT W. Approximating a point process by a renewal process, I: Two basic methods[J]. Operations Research, 1982, 30(1): 125–147. doi: 10.1287/opre.30.1.125

RAY W D. Basic queueing theory[J]. Journal of the Royal Statistical Society: Series A, 1988, 151(3): 550–684.

AVIDAN S. Support vector tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(8): 1064–1072. doi: 10.1109/TPAMI.2004.53

MOLINA-MASEGOSA R and GOZALVEZ J. LTE-V for sidelink 5G V2X vehicular communications: A new 5G technology for short-range vehicle-to-everything communications[J]. IEEE Vehicular Technology Magazine, 2017, 12(4): 30–39. doi: 10.1109/MVT.2017.2752798

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)