【摘要】：道路交通事故的頻繁發(fā)生嚴(yán)重影響了人們的生命財(cái)產(chǎn)安全和道路交通通行效率。汽車(chē)碰撞事故是道路交通事故中最主要的一種事故形態(tài),如何有效的防止汽車(chē)碰撞事故的發(fā)生,提高道路車(chē)輛的行駛安全性一直是汽車(chē)安全輔助駕駛領(lǐng)域眾多學(xué)者面臨的共同問(wèn)題。在實(shí)際道路交通環(huán)境中,駕駛?cè)藳Q策意圖/操控行為、汽車(chē)運(yùn)動(dòng)狀態(tài)、道路交通環(huán)境(路面濕滑程度、道路線(xiàn)型等)多種因素會(huì)導(dǎo)致汽車(chē)碰撞事故的發(fā)生。國(guó)內(nèi)外學(xué)者對(duì)汽車(chē)智能避碰技術(shù)開(kāi)展了深入的研究,但迄今為止針對(duì)復(fù)雜道路交通環(huán)境下的行車(chē)安全狀態(tài)辨識(shí)方法以及動(dòng)態(tài)道路交通環(huán)境下的汽車(chē)避碰決策仍然存在許多有待解決的問(wèn)題:如何將駕駛?cè)艘蛩嘏c動(dòng)態(tài)道路交通環(huán)境相結(jié)合,綜合評(píng)估駕駛意圖/駕駛行為、汽車(chē)運(yùn)動(dòng)狀態(tài)以及車(chē)外環(huán)境對(duì)行車(chē)安全性的影響;如何解決“人-車(chē)-路”協(xié)同感知環(huán)境下行車(chē)安全相關(guān)多源異構(gòu)信息的處理與融合問(wèn)題;如何構(gòu)建復(fù)雜道路交通環(huán)境下的汽車(chē)碰撞危險(xiǎn)態(tài)勢(shì)辨識(shí)模型;如何考慮道路環(huán)境和車(chē)輛動(dòng)力學(xué)特性對(duì)汽車(chē)運(yùn)動(dòng)狀態(tài)的約束問(wèn)題來(lái)規(guī)劃合理的避碰路徑。本文的研究工作主要依托國(guó)家自然科學(xué)基金項(xiàng)目“基于駕駛意圖與動(dòng)態(tài)環(huán)境的汽車(chē)碰撞危險(xiǎn)態(tài)勢(shì)辨識(shí)研究”、“車(chē)聯(lián)網(wǎng)環(huán)境下多意圖跟蹤的車(chē)輛碰撞預(yù)警方法研究”和國(guó)家863計(jì)劃項(xiàng)目“車(chē)路交互式行車(chē)安全系統(tǒng)關(guān)鍵技術(shù)”。針對(duì)現(xiàn)有汽車(chē)避碰技術(shù)的不足之處,本文綜合考慮了駕駛意圖和動(dòng)態(tài)道路交通環(huán)境對(duì)行車(chē)安全性的影響,研究了復(fù)雜道路交通環(huán)境下的汽車(chē)碰撞危險(xiǎn)態(tài)勢(shì)辨識(shí)方法和避碰路徑規(guī)劃方法。本文主要研究工作如下:1.對(duì)典型駕駛意圖下(自由行駛、跟馳行駛、換道行駛)的駕駛?cè)瞬倏匦袨樘攸c(diǎn)進(jìn)行了深入研究。基于線(xiàn)性最優(yōu)二次型理論與方法建立了駕駛意圖導(dǎo)向下的駕駛行為預(yù)測(cè)模型,通過(guò)求解模型效用函數(shù)來(lái)量化表示駕駛?cè)藢?duì)汽車(chē)運(yùn)動(dòng)狀態(tài)的期望操控方式。同時(shí),通過(guò)調(diào)整模型參數(shù)來(lái)適應(yīng)駕駛?cè)肆?xí)慣或道路交通環(huán)境導(dǎo)致的駕駛操控行為差異性。2.綜合考慮駕駛意圖和汽車(chē)運(yùn)動(dòng)狀態(tài)提出了汽車(chē)行駛軌跡的短時(shí)預(yù)測(cè)方法。通過(guò)將預(yù)測(cè)的駕駛操控量序列加入到運(yùn)動(dòng)學(xué)模型(CA模型),并基于Kalman估計(jì)算法和改進(jìn)的CA模型來(lái)預(yù)測(cè)汽車(chē)在下一時(shí)刻的運(yùn)動(dòng)狀態(tài)。在此基礎(chǔ)上,考慮鄰域范圍內(nèi)的多車(chē)行車(chē)意圖和運(yùn)動(dòng)狀態(tài),預(yù)測(cè)車(chē)輛間的行駛軌跡是否存在沖突,并定義了沖突風(fēng)險(xiǎn)指數(shù)來(lái)評(píng)估車(chē)輛間的沖突風(fēng)險(xiǎn)程度。3.對(duì)“人-車(chē)-路”多因素影響下的汽車(chē)碰撞危險(xiǎn)態(tài)勢(shì)辨識(shí)方法進(jìn)行了研究。綜合考慮了駕駛意圖、車(chē)間時(shí)距、路面濕滑程度等因素對(duì)行車(chē)安全狀態(tài)的影響,并應(yīng)用態(tài)勢(shì)感知理論建立了汽車(chē)碰撞危險(xiǎn)態(tài)勢(shì)辨識(shí)的模型結(jié)構(gòu)。結(jié)合變精度粗糙集方法形成了汽車(chē)碰撞危險(xiǎn)態(tài)勢(shì)評(píng)估規(guī)則,再通過(guò)屬性加權(quán)相似度量方法比較當(dāng)前行車(chē)狀態(tài)與決策規(guī)則庫(kù)中條件屬性的相似程度,進(jìn)而得出汽車(chē)碰撞危險(xiǎn)態(tài)勢(shì)的評(píng)估結(jié)果。4.綜合考慮駕駛意圖和動(dòng)態(tài)交通環(huán)境對(duì)行車(chē)安全性的影響,以及道路邊界等條件對(duì)汽車(chē)運(yùn)動(dòng)狀態(tài)的約束,提出了改進(jìn)的道路勢(shì)場(chǎng)模型來(lái)規(guī)劃汽車(chē)避碰路徑。根據(jù)被控汽車(chē)與道路障礙物間的相對(duì)運(yùn)動(dòng)狀態(tài)以及道路車(chē)輛的行駛意圖,結(jié)合柵格法對(duì)傳統(tǒng)人工勢(shì)場(chǎng)模型進(jìn)行改進(jìn),確保被控汽車(chē)在動(dòng)態(tài)道路交通環(huán)境下沿規(guī)劃的避碰路徑行駛時(shí),能有效避免碰撞事故的發(fā)生。本文針對(duì)復(fù)雜道路交通環(huán)境下汽車(chē)智能避碰系統(tǒng)涉及的關(guān)鍵理論、方法與技術(shù)問(wèn)題進(jìn)行了深入研究。一方面,將駕駛意圖引入到汽車(chē)碰撞危險(xiǎn)態(tài)勢(shì)辨識(shí)研究中,提高了汽車(chē)沖突危險(xiǎn)態(tài)勢(shì)辨識(shí)的準(zhǔn)確性;另一方面,在研究汽車(chē)避碰路徑規(guī)劃問(wèn)題中,考慮了駕駛意圖、汽車(chē)運(yùn)動(dòng)狀態(tài)和道路邊界約束等因素提出了改進(jìn)的道路勢(shì)場(chǎng)模型,進(jìn)而規(guī)劃出汽車(chē)避碰路徑更能適應(yīng)復(fù)雜多變的道路交通環(huán)境。本文提出的模型與方法可以為實(shí)現(xiàn)車(chē)路協(xié)同式條件下的汽車(chē)智能避碰系統(tǒng)提供理論基礎(chǔ)。研究成果對(duì)于提高道路交通安全水平,防止汽車(chē)碰撞事故的發(fā)生,以及促進(jìn)智能交通系統(tǒng)在我國(guó)的發(fā)展及實(shí)現(xiàn)具有重要意義。
[Abstract]:The frequent occurrence of road traffic accidents seriously affects people's life and property safety and road traffic passing efficiency. The automobile collision accident is one of the most important accident patterns in road traffic accidents, and how to effectively prevent the occurrence of automobile collision accidents and to improve the running safety of road vehicles has always been a common problem faced by many scholars in the field of automobile safety and auxiliary driving. In the actual road traffic environment, the driver's decision-making/ control behavior, the car's motion state, the road traffic environment (road surface wet-slip degree, road line type, etc.) can lead to the occurrence of the automobile collision accident. The domestic and foreign scholars have carried out in-depth research on the automobile intelligent collision avoidance technology, but so far, there are many problems to be solved for the traffic safety state identification method under the complicated road traffic environment and the automobile collision avoidance decision in the dynamic road traffic environment. how to combine that driver's factor with the dynamic road traffic environment to evaluate the effect of the driving intention/ driving behavior, the car's motion state and the vehicle's outside environment on the safety of the vehicle; How to solve the problem of handling and integration of the multi-source and heterogeneous information related to the traffic safety under the cooperative-sensing environment of the 鈥淢an-Vehicle-Road鈥，

本文編號(hào)：2358236