【摘要】：無(wú)人駕駛車(chē)輛是智能交通系統(tǒng)的重要組成部分,主要包括環(huán)境感知、規(guī)劃決策和控制執(zhí)行等子系統(tǒng)。多層激光雷達(dá)憑借其測(cè)量精度高、數(shù)據(jù)多、速度快、魯棒性強(qiáng)等優(yōu)點(diǎn)在無(wú)人駕駛車(chē)的環(huán)境感知系統(tǒng)中得到了廣泛應(yīng)用。論文對(duì)基于多層激光雷達(dá)提取無(wú)人駕駛車(chē)周?chē)牡缆放c障礙物信息進(jìn)行研究,主要內(nèi)容如下:(1)根據(jù)路沿?cái)?shù)據(jù)點(diǎn)特征從眾多的激光雷達(dá)數(shù)據(jù)中提取出路沿?cái)?shù)據(jù)集。應(yīng)用相似性度量方法對(duì)COBWEB算法進(jìn)行改進(jìn),以提高路沿?cái)?shù)據(jù)集聚類分析的準(zhǔn)確率。提出多層融合表示規(guī)則能夠融合多層激光雷達(dá)數(shù)據(jù)、剔除干擾路沿、分清左右路沿,并通過(guò)最小二乘法擬合出最終路沿,將道路分割為可行駛區(qū)域和不可行駛區(qū)域。在可行駛區(qū)域內(nèi)根據(jù)三維激光雷達(dá)不同掃描層之間數(shù)據(jù)點(diǎn)的相對(duì)位置關(guān)系提出道路坡度檢測(cè)算法,能夠判別平坦路、上坡路和下坡路等路況信息。(2)為剔除路面數(shù)據(jù)點(diǎn),應(yīng)用多層激光雷達(dá)數(shù)據(jù)的三維信息建立三維局部柵格地圖。為解決動(dòng)態(tài)環(huán)境下應(yīng)用DS證據(jù)理論(Dempster-Shafer Theory,DST)融合局部地圖與全局地圖時(shí)的不匹配問(wèn)題,本文提出首先根據(jù)無(wú)人駕駛車(chē)輛的運(yùn)動(dòng)速度、運(yùn)動(dòng)方向等信息將局部柵格地圖進(jìn)行位置估計(jì)后,再使用DST融合規(guī)則將兩地圖進(jìn)行融合,提高了基于DS證據(jù)理論建立柵格地圖的精確度。(3)利用DST中的沖突系數(shù)檢測(cè)動(dòng)態(tài)障礙物,并采用膨脹、侵蝕算法組合而成的閉運(yùn)算填補(bǔ)障礙物的漏洞和裂縫。針對(duì)經(jīng)典區(qū)域標(biāo)記算法重復(fù)訪問(wèn)堆棧和大量冗余鄰域搜索等問(wèn)題進(jìn)行改進(jìn),并應(yīng)用改進(jìn)的八鄰域區(qū)域標(biāo)記算法對(duì)動(dòng)態(tài)障礙物進(jìn)行聚類分析,以提取障礙物的長(zhǎng)度、寬度和中心位置等靜態(tài)信息。(4)考慮到Kalman濾波器具有出色的穩(wěn)定性,本文提出基于Kalman濾波器的障礙物動(dòng)態(tài)信息提取方法。并提出應(yīng)用Kalman濾波器為每個(gè)被跟蹤目標(biāo)建立一個(gè)隨目標(biāo)中心位置、長(zhǎng)度、寬度和航向角實(shí)時(shí)變化的可變跟蹤門(mén),增加了障礙物目標(biāo)跟蹤系統(tǒng)的自適應(yīng)能力。針對(duì)最近鄰數(shù)據(jù)關(guān)聯(lián)算法在密集環(huán)境下容易產(chǎn)生錯(cuò)誤跟蹤等問(wèn)題,提出基于多特征馬氏距離改進(jìn)的最近鄰數(shù)據(jù)關(guān)聯(lián)算法,能夠在密集環(huán)境下準(zhǔn)確地為多被跟蹤目標(biāo)匹配最優(yōu)關(guān)聯(lián)目標(biāo)。最后,通過(guò)實(shí)車(chē)試驗(yàn)驗(yàn)證了上述方法能夠穩(wěn)定、準(zhǔn)確、快速地完成檢測(cè)路沿信息、道路坡度信息、檢測(cè)并跟蹤測(cè)障礙物目標(biāo)、提取目標(biāo)的動(dòng)靜態(tài)信息等工作。
[Abstract]:Driverless vehicle (UAV) is an important part of Intelligent Transportation system (its), which includes environment perception, planning decision and control execution. Multi-layer lidar has been widely used in the environment sensing system of driverless vehicles because of its advantages of high measurement accuracy, high speed, high speed and high robustness. In this paper, the road and obstacle information around driverless vehicle is extracted based on multilayer lidar. The main contents are as follows: (1) the road edge data sets are extracted from many lidar data according to the road edge data points. The similarity measure method is used to improve the COBWEB algorithm in order to improve the accuracy of data cluster analysis along the road. It is proposed that the multilayer fusion representation rule can fuse the multilayer lidar data, eliminate the interference path edges, distinguish the left and right edges, and fit the final path edge by the least square method, and divide the road into drivable and non-drivable areas. According to the relative position relation of data points between different scanning layers of 3D lidar, a road slope detection algorithm is proposed in the traveling region, which can distinguish the road condition information such as flat road, uphill road and downhill road. (2) in order to eliminate the road surface data points, Three-dimensional local raster map is built by using three-dimensional information of multi-layer lidar data. In order to solve the mismatch problem when using DS evidence theory (Dempster-Shafer Theory,DST) to fuse the local map with the global map in dynamic environment, this paper proposes a method based on the velocity of driverless vehicle. The location of the local raster map is estimated by moving direction and other information, and then the two maps are fused by using the DST fusion rule. The accuracy of building grid map based on DS evidence theory is improved. (3) the collision coefficient in DST is used to detect the dynamic obstacle, and the closed operation composed of expansion and erosion algorithm is used to fill the hole and crack of the obstacle. Aiming at the problems of repeated access stack and redundant neighborhood search in classical region marking algorithm, the improved eight-neighborhood region marking algorithm is applied to cluster analysis of dynamic obstacles to extract the length of obstacles. Static information such as width and center position. (4) considering the excellent stability of Kalman filter, an obstacle dynamic information extraction method based on Kalman filter is proposed in this paper. A variable tracking gate based on the center position, length, width and heading angle of each tracked target is proposed by using Kalman filter, which increases the adaptive ability of the obstacle target tracking system. Aiming at the problem that the nearest neighbor data association algorithm is easy to generate error tracking in dense environment, an improved nearest neighbor data association algorithm based on multi-feature Markov distance is proposed. It can accurately match the optimal target association for multiple tracked targets in dense environment. Finally, the method is proved to be stable, accurate and fast in detecting road edge information, road slope information, detecting and tracking obstacle targets, and extracting static and dynamic information of targets.
【學(xué)位授予單位】：北京工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：U495;U463.6;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 許天野;徐雪松;;交互多模型算法在目標(biāo)跟蹤領(lǐng)域的應(yīng)用[J];四川兵工學(xué)報(bào);2013年11期

2 茍光磊;崔貫勛;王柯柯;;基于屬性重要性的Cobweb算法[J];重慶理工大學(xué)學(xué)報(bào)(自然科學(xué));2012年12期

3 劉楓;吳小俊;;一種改進(jìn)的聯(lián)合概率數(shù)據(jù)關(guān)聯(lián)算法[J];數(shù)據(jù)采集與處理;2011年01期

4 曹長(zhǎng)虎;李亞非;;一種二值圖像連通區(qū)域標(biāo)記快速算法[J];科學(xué)技術(shù)與工程;2010年33期

5 張?jiān)普?趙海;宋純賀;景巍;;一種新的連通區(qū)域標(biāo)記算法[J];計(jì)算機(jī)應(yīng)用研究;2010年11期

6 齊鑫;;基于膨脹腐蝕算法的數(shù)字信號(hào)處理技術(shù)[J];自動(dòng)化技術(shù)與應(yīng)用;2010年10期

7 周武;趙春霞;張浩峰;;動(dòng)態(tài)聯(lián)合最近鄰算法[J];電子學(xué)報(bào);2010年02期

8 鮑慶勇;李舜酩;沈\，

本文編號(hào)：2304983