本文選題：駕駛風(fēng)格 + 駕駛模式��； 參考：《清華大學(xué)》2016年博士論文

【摘要】：我國(guó)道路交通安全形勢(shì)嚴(yán)峻,不良駕駛風(fēng)格充斥于日常駕駛行為之中。在車聯(lián)網(wǎng)技術(shù)迅速發(fā)展的大背景下,研究并實(shí)現(xiàn)對(duì)險(xiǎn)態(tài)駕駛風(fēng)格的有效監(jiān)測(cè),并以離線反饋教育或在線危險(xiǎn)預(yù)警的方式進(jìn)行干預(yù),對(duì)提升道路行車安全性具有重要意義。當(dāng)前針對(duì)駕駛風(fēng)格的研究普遍存在綜合評(píng)測(cè)維度局限性和駕駛操作評(píng)測(cè)維度不完整性的問題。為解決這些問題,本課題構(gòu)建了考慮人認(rèn)知特性和信息優(yōu)化表達(dá)的駕駛模式分解與辨識(shí)方法體系,從駕駛模式轉(zhuǎn)移和駕駛操作控制兩個(gè)維度出發(fā),設(shè)計(jì)了相應(yīng)的駕駛風(fēng)格險(xiǎn)態(tài)評(píng)測(cè)方法,拓展了駕駛風(fēng)格評(píng)測(cè)的方法體系。針對(duì)高速工況下駕駛模式辨識(shí)存在的動(dòng)態(tài)時(shí)變、多維耦合和局部相似的問題,提出了以制動(dòng)減速度、跟馳時(shí)距和跟馳時(shí)距變化率作為縱向駕駛模式的辨識(shí)指標(biāo);針對(duì)橫向駕駛模式的辨識(shí),采用了2s時(shí)窗內(nèi)的方向盤轉(zhuǎn)角香農(nóng)熵、2s時(shí)窗內(nèi)的橫向加速度均方根、5s時(shí)窗內(nèi)的橫擺角速度標(biāo)準(zhǔn)差和4s時(shí)窗內(nèi)的速度香農(nóng)熵四個(gè)特征參數(shù)作為隨機(jī)森林分類器的輸入,以分類器的輸出概率作為橫向駕駛模式的辨識(shí)指標(biāo)。驗(yàn)證結(jié)果顯示,本課題提出的駕駛模式辨識(shí)方法體系可實(shí)現(xiàn)對(duì)各駕駛模式的有效辨識(shí),辨識(shí)精度可達(dá)86~98%。為實(shí)現(xiàn)對(duì)駕駛風(fēng)格在模式轉(zhuǎn)移維度(頻度)的有效評(píng)測(cè),以駕駛模式轉(zhuǎn)移概率為基礎(chǔ),優(yōu)選出了五種可表征駕駛風(fēng)格模式轉(zhuǎn)移特性的典型駕駛模式轉(zhuǎn)移形態(tài)分別為:近距離跟馳→受限右換道,受限右換道→受限左換道,受限左換道→迫近,迫近→受限右換道和受限左換道→自由直行。以這五種形態(tài)發(fā)生的條件概率值作為隨機(jī)森林分類器的輸入,以輸出的隸屬于不同風(fēng)格類型的概率值作為判別標(biāo)準(zhǔn),實(shí)現(xiàn)了對(duì)駕駛風(fēng)格險(xiǎn)態(tài)頻度的有效評(píng)測(cè)。交叉驗(yàn)證結(jié)果顯示,該方法的辨識(shí)精度可達(dá)93%,比基于傳統(tǒng)方法對(duì)駕駛風(fēng)格險(xiǎn)態(tài)頻度表現(xiàn)的評(píng)測(cè)精度高出18%。為實(shí)現(xiàn)對(duì)駕駛風(fēng)格在操作控制維度(強(qiáng)度)的有效評(píng)測(cè),提出了以加速度的冪指數(shù)在時(shí)間序列上的積分量化表征人感知到的險(xiǎn)態(tài)強(qiáng)度,通過對(duì)人在加速、制動(dòng)、車距控制、換道控制和轉(zhuǎn)彎控制五個(gè)維度上的險(xiǎn)態(tài)強(qiáng)度感知進(jìn)行加權(quán)綜合,得到駕駛操作激進(jìn)指數(shù)作為駕駛風(fēng)格險(xiǎn)態(tài)強(qiáng)度表現(xiàn)的評(píng)測(cè)指標(biāo)。基于事后視頻和現(xiàn)場(chǎng)評(píng)價(jià)的驗(yàn)證試驗(yàn)結(jié)果顯示,該算法的辨識(shí)精度可達(dá)85~92%。綜合駕駛風(fēng)格在險(xiǎn)態(tài)頻度和強(qiáng)度兩個(gè)維度的表現(xiàn),構(gòu)建了決策樹模型對(duì)綜合駕駛風(fēng)格進(jìn)行評(píng)測(cè)。驗(yàn)證試驗(yàn)表明,該決策樹模型的辨識(shí)精度可達(dá)89%。
[Abstract]:Our country road traffic safety situation is grim, the bad driving style is flooded in the daily driving behavior. Under the background of the rapid development of vehicle networking technology, it is of great significance to study and realize the effective monitoring of dangerous driving style and to intervene in offline feedback education or online hazard warning. At present, there are some problems in the study of driving style, such as the limitation of comprehensive evaluation dimension and the incompleteness of driving operation evaluation dimension. In order to solve these problems, this paper constructs a driving pattern decomposition and identification method system, which takes into account the cognitive characteristics of human beings and the optimal expression of information, starting from the two dimensions of driving mode transfer and driving operation control. The method of dangerous driving style evaluation is designed, and the method system of driving style evaluation is expanded. Aiming at the problems of dynamic time-varying, multi-dimensional coupling and local similarity in driving mode identification under high-speed operating conditions, this paper puts forward the identification index of longitudinal driving mode based on braking deceleration, following time distance and changing rate of following driving time distance. For lateral driving mode identification, In this paper, four characteristic parameters of steering wheel angle Shannon entropy in 2s window and transverse acceleration root-square velocity standard deviation in 5s window and velocity Shannon entropy in 4s window are used as input of random forest classifier. The output probability of the classifier is used as the identification index of the lateral driving mode. The verification results show that the driving mode identification system presented in this paper can effectively identify each driving mode, and the identification accuracy can reach 860.98%. In order to realize the effective evaluation of driving style in the dimension of mode transfer (frequency), it is based on the probability of driving mode transfer. Five typical driving mode transfer patterns which can characterize the characteristics of driving style mode transfer are selected as follows: short distance following, restricted right change, restricted left approach. The approach is restricted to the right and the restricted left to go straight and free. The conditional probabilistic values of these five morphogenesis are taken as the input of the random forest classifier and the probabilistic values of the output which belong to different style types are taken as the criterion to realize the effective evaluation of the dangerous frequency of driving style. The results of cross validation show that the accuracy of this method can reach 933, which is 18.5% higher than that of the traditional method in evaluating the dangerous frequency of driving style. In order to effectively evaluate driving style in the dimension of operation control (intensity), this paper presents a method of quantifying the perceived dangerous state intensity by integrating the power exponent of acceleration in time series, which is controlled by acceleration, braking and distance control. On the basis of weighted synthesis of risk intensity perception in five dimensions of change control and turn control, the radical index of driving operation is obtained as the evaluation index of dangerous intensity performance of driving style. The experimental results based on post video and field evaluation show that the identification accuracy of the algorithm can reach 85 / 92. The decision tree model is constructed to evaluate the comprehensive driving style in the two dimensions of dangerous frequency and intensity. The experimental results show that the precision of the decision tree model is up to 89.
【學(xué)位授予單位】：清華大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：B842

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 馬歇爾·戈德史密斯;尹玉生;;換道而行[J];意林(原創(chuàng)版);2008年02期

2 邵傳賢;;你的車速比你想象的快得多[J];人生與伴侶(月末版);2008年04期

相關(guān)會(huì)議論文 前3條

1 張安英;;基于預(yù)判概率的換道決策模型研究[A];第八屆中國(guó)智能交通年會(huì)優(yōu)秀論文集——智能交通與安全[C];2013年

2 李瑋;段建民;龔建偉;;障礙物條件下智能車輛換道路徑規(guī)劃的近優(yōu)解[A];2011年中國(guó)智能自動(dòng)化學(xué)術(shù)會(huì)議論文集（第一分冊(cè)）[C];2011年

3 楊曉光;孫劍;;面向ITS的交通仿真實(shí)驗(yàn)系統(tǒng)研究與開發(fā)[A];第一屆中國(guó)智能交通年會(huì)論文集[C];2005年

相關(guān)重要報(bào)紙文章 前3條

1 本報(bào)記者 李龍俊;換道超車，才有機(jī)會(huì)后來居上[N];四川日?qǐng)?bào);2014年

2 記者 徐景明;車一進(jìn)隧道就不允許換道[N];廈門日?qǐng)?bào);2010年

3 聞天;安全駕車十二訣[N];華夏時(shí)報(bào);2004年

相關(guān)博士學(xué)位論文 前10條

1 宋竹;微觀交通仿真查詢算法與換道模型研究[D];電子科技大學(xué);2015年

2 李慧軒;基于駕駛行為動(dòng)態(tài)獲取的換道行為微觀建模及仿真校驗(yàn)研究[D];北京交通大學(xué);2016年

3 楊柳;基于元胞自動(dòng)機(jī)的高速公路交通流特性研究[D];長(zhǎng)沙理工大學(xué);2015年

4 郭艷君;營(yíng)運(yùn)客車典型危險(xiǎn)行駛狀態(tài)識(shí)別方法研究[D];長(zhǎng)安大學(xué);2016年

5 李國(guó)法;基于模式轉(zhuǎn)移和操控特性的駕駛風(fēng)格評(píng)測(cè)研究[D];清華大學(xué);2016年

6 彭金栓;基于視覺特性與車輛相對(duì)運(yùn)動(dòng)的駕駛?cè)藫Q道意圖識(shí)別方法[D];長(zhǎng)安大學(xué);2012年

7 王暢;車輛換道預(yù)警的若干關(guān)鍵問題研究[D];長(zhǎng)安大學(xué);2012年

8 侯海晶;高速公路駕駛?cè)藫Q道意圖識(shí)別方法研究[D];吉林大學(xué);2013年

9 黨睿娜;具有換道輔助功能的車輛自適應(yīng)巡航控制[D];清華大學(xué);2013年

10 羅強(qiáng);面向高速公路行車安全預(yù)警的車道偏離及換道模型研究[D];華南理工大學(xué);2014年

相關(guān)碩士學(xué)位論文 前10條

1 吳杭哲;基于最小安全距離的車輛換道控制研究[D];哈爾濱工業(yè)大學(xué);2015年

2 滕飛;換道車輛的實(shí)時(shí)軌跡預(yù)測(cè)方法研究[D];北京理工大學(xué);2016年

3 袁盛s，

本文編號(hào)：2031453