search
HomeTechnology peripheralsAIA little bit about the implementation of BEV lane lines

A seed was planted in 2021

Students who have read the BEV obstacle story should know that our group started doing BEV obstacles around October 21 material. At that time, I didn’t dare to think about doing BEV lane markings because there was no manpower. But I remember that around December, we met with a candidate. During the interview, we heard that they had been working on BEV lane markings for more than half a year. The entire technical route was used as a BEV lane marking network through high-precision maps. Train the true value and say that the effect is not bad. Unfortunately, that candidate did not come to us in the end. Combined with the content of lane markings taught at Telsa AI day in 2021, the seed of making BEV lane markings was planted in the group.

Taking the right first step in 2022

Throughout 2022, the manpower in our team was very tight. I remember that in June and July, We just have the manpower to explore the BEV lane lines. But at that time, there was only one classmate in our group (let’s call him Xiaoxuan for now) who had 2 months to do this. Then the seeds of 2021 began to sprout. We were going to start with the data. Student Xiaoxuan was still very good (very imaginative, and Xiaoxuan also made more things that surprised everyone in the future), and it was almost used. In February, we can extract lane line data around the corresponding car through high-speed high-precision maps. When it was made, I remember everyone was still very excited.

A little bit about the implementation of BEV lane lines

Figure 1: The effect of high-precision map lane lines projected onto the image system

As you can see from Figure 1, there are still some fitting problems problem, so Xiaoxuan made a series of optimizations. Two months later, Xiaoxuan went to do other tasks. Looking back now, we have taken the right step in exploring BEV lane lines. Because in 2021 and 22, many excellent BEV lane line papers and codes have been gradually open sourced. Seeing this, you may think that there must be a perfect story about the implementation of BEV lane lines in 2023. However, ideals are often very fulfilling, but the reality is very cruel.

23 years of stumbling

Because our BEV obstacles have proven that BEV can go down this road, and it has also shown good results in road tests. The group began to have more resources to consider lane lines. Note that this is not BEV. why? Because at this time, we were facing a lot of pressure to go online, and we did not have enough experience in BEV lane lines. In other words, there were almost no people in the entire group who had done mass production of 2D lane lines. In the first half of 2023, it can really be described as stumbling. We had many heated discussions internally, and finally decided to form two lines, one of which is the 2D lane line: most of the manpower is on the 2D lane line, and the focus is on the 2D lane line. Post-processing, light model, and accumulation of lane line post-processing mass production experience through 2D lane lines. One line is the BEV lane line: there is only a small number of manpower (actually only 1-2 manpower), focusing on the model design of the BEV lane line and accumulating model experience. There are already many BEV lane marking networks. I will post two papers that have a great impact on us here for your reference. "HDMapNet: An Online HD Map Construction and Evaluation Framework" and "MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction"

A little bit about the implementation of BEV lane lines

##Figure 2: HDMapNet

A little bit about the implementation of BEV lane lines

Figure 3 MapTR

Fortunately, in April and May, we accumulated a lot of experience in mass production of lane line post-processing in the 2D lane line. , our BEV lane line network was also designed, and at the end of May, BEV lane lines were successfully put on the bus soon. I have to say here that our classmate Dahai who is responsible for lane line post-processing is still very capable. However, just when you think things are going well, the nightmare is often about to begin. After the BEV lane lines were deployed, the vehicle control effect was not ideal. At this time, everyone fell into a stage of self-doubt. Is it because of the cubic spline fitting problem of the BEV lane lines or the problem of poor adaptation of downstream parameters. Fortunately, we have the supplier's results on our car. We saved the supplier's lane line results during the road test, and then compared them with our results in the visualization tool. When the vehicle control effect is not good, we must first prove that there is no problem with the quality of our own lane lines, so that the downstream drivers can adapt to our BEV lane lines. It took a month, a whole month, for us to have stable control of the car. I remember very clearly that we also ran from Shanghai to Suzhou. It was still a Saturday. Everyone in the group was very excited to see the high-speed car control effect.

However, a story often has twists and turns. We can only use high-speed high-precision maps to produce lane line data. What to do about the city? There are still so many bad cases that need to be solved. At this time, the important person will finally appear. Let's call him Classmate Xiaotang (the big steward of our data group). Classmate Xiaotang and the others used point cloud reconstruction to reconstruct the clip for us ( This process was quite painful. I remember those two months were the most stressful time for them, haha. Of course, classmate Xiaotang and we often fell in love and killed each other. , after all, I often say that there is no data again during meetings. ). Then how to label after reconstruction? Looking at the suppliers at the time, none of them had such labeling tools, let alone labeling experience. Together with Xiaotang and others, after a long month, the annotation tool was finally polished with the supplier. (We often joke that we are empowering the entire self-driving annotation industry. This process is really painful, and rebuilding clips is really slow to load). However, the whole labeling is still relatively slow or expensive. At this time, Xiaoxuan made his debut with his large model of lane line pre-labeling (the effect of the large model of lane line pre-labeling is still outstanding), and everyone looked at him with amazement. In sparkling. After this set of combinations, our lane line data production is finally almost ready. In August, our BEV lane line control lane line has been iterated well, which is suitable for simple high-speed piloting functions. Now Xiaoxuan is still bringing us more surprises in the pre-marked direction of the large model. We and Xiaotang are still in love with each other.

However, a story does not end so easily. In September, we started working on multi-modal (Lidar, camera, Radar) multi-task (lane lines, obstacles, Occ) pre-fusion models. It will also subsequently support City Navigation (NCP), a so-called solution that emphasizes perception and ignores maps. Based on the experience of BEV obstacles and BEV lane lines, we will soon deploy the converged network on vehicles, probably by the end of September. Many subtasks have also been added to lane lines, such as road sign recognition, intersection topology, etc. In this process, we upgraded the post-processing of BEV lane lines, abandoned the lane line cubic spline fitting, and adopted a point tracking scheme. The output of the point tracking scheme and our lane line model can be easily Good combination. This process was also painful. We held a special meeting once a week for 2 consecutive months. After all, we have done well based on the fitting plan, but in order to reach a higher limit, we can only suffer from pain and happiness. Finally, we have already put the basic functions into road testing.

Let me briefly explain Figure 4. The left side is the effect of lane line point tracking. Currently, the perception range of our model is only the first 80 meters. You can see that there are some points behind the car, which are left by tracking. On the right is the real-time perceptual map we have established. Of course, it is still in a rapid iteration process, and there are still many problems being solved.

The new beginning of 24 years

At this moment, standing in 24 years and looking back at our growth and accumulation from 21 years to now, I am very fortunate to be at that point in 21 years , I have the opportunity to do BEV, and I am very fortunate to have a group of like-minded friends who can help each other along the way. In 24 years, there are many things for us to pursue, including the mass production of pre-fusion models, efforts in data direction, exploration of timing models, end-to-end imagination, etc.

The above is the detailed content of A little bit about the implementation of BEV lane lines. For more information, please follow other related articles on the PHP Chinese website!

Statement
This article is reproduced at:51CTO.COM. If there is any infringement, please contact admin@php.cn delete
在 CARLA自动驾驶模拟器中添加真实智体行为在 CARLA自动驾驶模拟器中添加真实智体行为Apr 08, 2023 pm 02:11 PM

arXiv论文“Insertion of real agents behaviors in CARLA autonomous driving simulator“,22年6月,西班牙。由于需要快速prototyping和广泛测试,仿真在自动驾驶中的作用变得越来越重要。基于物理的模拟具有多种优势和益处,成本合理,同时消除了prototyping、驾驶员和弱势道路使用者(VRU)的风险。然而,主要有两个局限性。首先,众所周知的现实差距是指现实和模拟之间的差异,阻碍模拟自主驾驶体验去实现有效的现实世界

特斯拉自动驾驶算法和模型解读特斯拉自动驾驶算法和模型解读Apr 11, 2023 pm 12:04 PM

特斯拉是一个典型的AI公司,过去一年训练了75000个神经网络,意味着每8分钟就要出一个新的模型,共有281个模型用到了特斯拉的车上。接下来我们分几个方面来解读特斯拉FSD的算法和模型进展。01 感知 Occupancy Network特斯拉今年在感知方面的一个重点技术是Occupancy Network (占据网络)。研究机器人技术的同学肯定对occupancy grid不会陌生,occupancy表示空间中每个3D体素(voxel)是否被占据,可以是0/1二元表示,也可以是[0, 1]之间的

一文通览自动驾驶三大主流芯片架构一文通览自动驾驶三大主流芯片架构Apr 12, 2023 pm 12:07 PM

当前主流的AI芯片主要分为三类,GPU、FPGA、ASIC。GPU、FPGA均是前期较为成熟的芯片架构,属于通用型芯片。ASIC属于为AI特定场景定制的芯片。行业内已经确认CPU不适用于AI计算,但是在AI应用领域也是必不可少。 GPU方案GPU与CPU的架构对比CPU遵循的是冯·诺依曼架构,其核心是存储程序/数据、串行顺序执行。因此CPU的架构中需要大量的空间去放置存储单元(Cache)和控制单元(Control),相比之下计算单元(ALU)只占据了很小的一部分,所以CPU在进行大规模并行计算

自动驾驶汽车激光雷达如何做到与GPS时间同步?自动驾驶汽车激光雷达如何做到与GPS时间同步?Mar 31, 2023 pm 10:40 PM

gPTP定义的五条报文中,Sync和Follow_UP为一组报文,周期发送,主要用来测量时钟偏差。 01 同步方案激光雷达与GPS时间同步主要有三种方案,即PPS+GPRMC、PTP、gPTPPPS+GPRMCGNSS输出两条信息,一条是时间周期为1s的同步脉冲信号PPS,脉冲宽度5ms~100ms;一条是通过标准串口输出GPRMC标准的时间同步报文。同步脉冲前沿时刻与GPRMC报文的发送在同一时刻,误差为ns级别,误差可以忽略。GPRMC是一条包含UTC时间(精确到秒),经纬度定位数据的标准格

特斯拉自动驾驶硬件 4.0 实物拆解:增加雷达,提供更多摄像头特斯拉自动驾驶硬件 4.0 实物拆解:增加雷达,提供更多摄像头Apr 08, 2023 pm 12:11 PM

2 月 16 日消息,特斯拉的新自动驾驶计算机,即硬件 4.0(HW4)已经泄露,该公司似乎已经在制造一些带有新系统的汽车。我们已经知道,特斯拉准备升级其自动驾驶硬件已有一段时间了。特斯拉此前向联邦通信委员会申请在其车辆上增加一个新的雷达,并称计划在 1 月份开始销售,新的雷达将意味着特斯拉计划更新其 Autopilot 和 FSD 的传感器套件。硬件变化对特斯拉车主来说是一种压力,因为该汽车制造商一直承诺,其自 2016 年以来制造的所有车辆都具备通过软件更新实现自动驾驶所需的所有硬件。事实证

端到端自动驾驶中轨迹引导的控制预测:一个简单有力的基线方法TCP端到端自动驾驶中轨迹引导的控制预测:一个简单有力的基线方法TCPApr 10, 2023 am 09:01 AM

arXiv论文“Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline“, 2022年6月,上海AI实验室和上海交大。当前的端到端自主驾驶方法要么基于规划轨迹运行控制器,要么直接执行控制预测,这跨越了两个研究领域。鉴于二者之间潜在的互利,本文主动探索两个的结合,称为TCP (Trajectory-guided Control Prediction)。具

一文聊聊自动驾驶中交通标志识别系统一文聊聊自动驾驶中交通标志识别系统Apr 12, 2023 pm 12:34 PM

什么是交通标志识别系统?汽车安全系统的交通标志识别系统,英文翻译为:Traffic Sign Recognition,简称TSR,是利用前置摄像头结合模式,可以识别常见的交通标志 《 限速、停车、掉头等)。这一功能会提醒驾驶员注意前面的交通标志,以便驾驶员遵守这些标志。TSR 功能降低了驾驶员不遵守停车标志等交通法规的可能,避免了违法左转或者无意的其他交通违法行为,从而提高了安全性。这些系统需要灵活的软件平台来增强探测算法,根据不同地区的交通标志来进行调整。交通标志识别原理交通标志识别又称为TS

一文聊聊SLAM技术在自动驾驶的应用一文聊聊SLAM技术在自动驾驶的应用Apr 09, 2023 pm 01:11 PM

定位在自动驾驶中占据着不可替代的地位,而且未来有着可期的发展。目前自动驾驶中的定位都是依赖RTK配合高精地图,这给自动驾驶的落地增加了不少成本与难度。试想一下人类开车,并非需要知道自己的全局高精定位及周围的详细环境,有一条全局导航路径并配合车辆在该路径上的位置,也就足够了,而这里牵涉到的,便是SLAM领域的关键技术。什么是SLAMSLAM (Simultaneous Localization and Mapping),也称为CML (Concurrent Mapping and Localiza

See all articles

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

AI Hentai Generator

AI Hentai Generator

Generate AI Hentai for free.

Hot Article

Repo: How To Revive Teammates
1 months agoBy尊渡假赌尊渡假赌尊渡假赌
R.E.P.O. Energy Crystals Explained and What They Do (Yellow Crystal)
2 weeks agoBy尊渡假赌尊渡假赌尊渡假赌
Hello Kitty Island Adventure: How To Get Giant Seeds
1 months agoBy尊渡假赌尊渡假赌尊渡假赌

Hot Tools

Atom editor mac version download

Atom editor mac version download

The most popular open source editor

MantisBT

MantisBT

Mantis is an easy-to-deploy web-based defect tracking tool designed to aid in product defect tracking. It requires PHP, MySQL and a web server. Check out our demo and hosting services.

Dreamweaver Mac version

Dreamweaver Mac version

Visual web development tools

PhpStorm Mac version

PhpStorm Mac version

The latest (2018.2.1) professional PHP integrated development tool

Safe Exam Browser

Safe Exam Browser

Safe Exam Browser is a secure browser environment for taking online exams securely. This software turns any computer into a secure workstation. It controls access to any utility and prevents students from using unauthorized resources.