


Recently, with the rise of generative AI technology, many new car-making forces are exploring new methods of visual language models and world models. End-to-end intelligent driving new technologies seem to have become a common research direction. Last month, Li Auto released the third-generation autonomous driving technology architecture of end-to-end + VLM visual language model + world model. This architecture has been pushed to thousands of people for internal testing. It personifies intelligent driving behavior, improves the information processing efficiency of AI, and enhances the ability to understand and respond to complex road conditions. Li Xiang once said in a public sharing that in the face of rare driving environments that are difficult for most algorithms to identify and process, VLM (Visual Language Model) can systematically improve the capabilities of autonomous driving. This method can be achieved theoretically A breakthrough.
This set of autonomous driving technology architecture is inspired by the fast and slow system theory of Nobel Prize winner Daniel Kahneman. Simulating human thinking and decision-making processes in the field of autonomous driving also requires "fast systems" and "slow systems" Collaborate. Among them:
・ The fast system (System 1) is good at handling simple tasks and is human intuition formed based on experience and habits; in autonomous driving, it is composed of an end-to-end large model, including perception and planning, which is enough to handle 95% of the problems when driving a vehicle. Routine scenario.
・ The slow system (System 2) is the logical reasoning, complex analysis and computing capabilities formed by humans through deeper understanding and learning; in the autonomous driving system, it is mainly the VLM model, which is used to solve complex or even unknown problems when driving a vehicle Traffic scenes account for about 5% of daily driving scenes.
Last week, at an event held at Li Auto’s Beijing R&D headquarters, Li Auto’s Vice President of Intelligent Driving Lang Xianpeng emphasized that Li Auto’s intelligent driving has now fully integrated into the end-to-end + large model solution, which allows vehicles to understand complex road conditions and traffic rule.
"Both end-to-end and traditional perception decision-making models require a large amount of data for training. One potential problem is that the system will not work well if it encounters unseen scenes," Lang Xianpeng said. "We are exploring the ability of vehicles to think and make decisions like humans."
Since the second half of last year, Ideal began to adjust its strategy and change its trajectory. In February this year, in the DriveVLM paper submitted by Tsinghua University's Cross-Information Research Institute and Li Auto, researchers applied the visual language model (VLM) that has recently emerged in the field of generative AI and demonstrated extraordinary capabilities in visual understanding and reasoning.
In the industry, this is the first work to propose an autonomous driving speed system. Its method fully combines the mainstream autonomous driving pipeline and a large model pipeline with logical thinking, and is the first to complete the large model work of end test deployment ( Based on NVIDIA Orin platform).
DriveVLM consists of a Chain-of-Though (CoT) process with three key modules:
- Scenario Description: Use language to describe the driving environment and identify key objects.
- Scene Analysis: Dive into the characteristics of key objects and their impact on the ego vehicle.
- Hierarchical planning: Step-by-step plan development from meta-action and decision descriptions to waypoints.
These modules correspond to the perception, prediction and planning components in the traditional autonomous driving system process. The difference lies in their ability to handle object perception, intention-level prediction and task-level planning, which have been extremely challenging in the past.
Technical verification
Ideal verification technology is effective in long-tail scenarios:
- Disassemble real environment data
- Use generative models to supplement new perspectives
- Customize changes to weather, time, traffic flow and other conditions
Practical application
Li Auto’s end-to-end model and VLM model run in real time:
- End-to-end model: higher frame rate
- VLM model: larger number of parameters, lower frame rate
In complex cities In the scenario, VLM plays a role in situations where decision-making is impossible and delivers decision results and trajectories to the end-to-end model.
End-to-end approach
The end-to-end approach has become a technological watershed, marking the beginning of the real use of AI.
The new generation AI model
The new generation AI model can serve as the question maker:
- Select the data of users who meet the standard of private car drivers as "real questions"
- Combined with the world model to generate "simulation questions"
Computing power challenge
車両側での VLM などのモデルの展開は、次のようなコンピューティング能力の課題に直面しています:
- パラメータの数を最適に保つ
- 意思決定の待ち時間を改善するためのエンジニアリングの最適化
競争の見通し
Tesla FSD は間もなく国内スマートドライビング分野への参入 新たな競争ステージへの参入:
- 理想のクルマの目標: エンドツーエンド+VLM自動運転の量産化
The above is the detailed content of L3 will be launched in the first half of next year at the latest: ideal end-to-end autonomous driving and greatly improved performance. For more information, please follow other related articles on the PHP Chinese website!

6月30日消息,理想汽车旗下的L系列车型,包括L7、L8和L9,在各自的价格区间中取得了可观的销售成绩。然而,据小编了解,理想汽车希望进一步提升销量,关注点落在了另一款新车——理想L6的表现上。近日,一位博主在高速服务区疑似拍到了理想L6的伪装车。根据博主所拍照片显示,疑似理想L6的伪装车并没有正常行驶,而是停放在一辆拖车上。与旁边的白色蔚来SUV相比,即使作为L系列中定位最低的车型,理想L6的体积也显得相当庞大。据悉,理想L6被定位为一款中型五座SUV。尽管这些照片未能提供太多有关外观细节的信

理想汽车官方商城日前发布了一款专为副驾驶设计的单人充气床垫。这款床垫特别设计,可以方便地连接到中控台的点烟器接口,同时配备了电动充气泵,让用户只需短短2分钟即可轻松充气,提供舒适的休息环境。这款充气床垫售价为499元,为用户提供了一个舒适的车内休息选择。据小编了解,这款充气床垫由理想汽车原厂开模定制,确保尺寸与座椅完美贴合,为用户提供最佳的睡眠体验。床垫设计采用多气囊结构,能有效填充座椅间隙,提供饱满的身体承托。材质上,表面选用了细腻柔软的仿麂皮绒面料,触感舒适;里层则使用耐磨、抗皱的优质PVC

2月4日消息,理想汽车宣布即将推出一款全新的“7kW交流充电桩”,并计划于明天在理想商城上线。据官方微博介绍,这款充电桩是理想汽车自主研发的,专为理想L系列车型设计,售价为4999元。该充电桩官方声称享有长达4年的质保期,同时具备智能功能,支持错峰充电。据称,相较于公共充电桩,每次使用该充电桩可节省约47元电费。此外,充电桩还提供私用和公用两种模式切换,用户可根据需求选择。有趣的是,充电枪充电口盖能够自动打开,为用户提供更加便捷的充电体验。根据小编的了解,在理想商城下单后,用户需要与授权服务商联

理想汽车宣布推出全新的5C超充桩,标志着电动车充电速度迈入新纪元。据理想汽车官方介绍,这款5C超充桩在高速充电模式下,仅需12分钟即可为电动汽车补充500km的续航里程,其单桩峰值充电功率高达520kw。而在城市充电模式下,虽然速度有所放缓,但25分钟内同样可以达到500km的补能效果,此时的单桩峰值充电功率为250kw。这一速度大大超过了市场上大多数充电设备的性能,无疑将极大提升电动汽车用户的使用体验。此外,理想超充站还提供了800V的高效补能服务,而其充电枪的设计也充分考虑到了用户体验,重量

2月4日,理想汽车宣布其AEB系统已经超越行业标准,证明了其出色的智能化和安全性能。这一消息是在理想汽车成功为其L系车型推送OTA5.0.4升级后发布的,该升级显著提升了车辆的主动安全性能。理想汽车的AEB系统为驾驶员提供了更高级别的安全保护,减少了碰撞的风险。这个系统不仅能够主动感知前方的障碍物,并及时发出警报,还能在驾驶员未能及时反应时自动刹车,以避免或减轻碰撞事故的发生。通过超越行业标准,理想汽车进一步巩固了其在智能为了更直观地展示AEB系统的性能,理想汽车发布了一段视频,强调其AEB系统

理想汽车宣布推出新春优惠活动,为L7、L8和L9全系车型提供了特别的降价优惠。根据消息,不同版本的车型的降价幅度在3.3万至3.8万元之间。其中,理想L7的价格降至28.69万元,首次进入30万元以下市场。此外,购买理想L7和L8的Max车型的消费者还将免费获赠21英寸轮圈,而购买理想L9车型的消费者则可享受全系赠送的电动踏板。如果消费者选择放弃这两项赠品,还能额外获得5000元的优惠。这一系列优惠活动将为消费者提供更多的购车选择和实惠。针对此次降价活动,理想汽车方面表示,这是为了应对日益激烈的

理想汽车日前宣布,深圳嘉乐道和广州广园路的两家旗舰级零售中心正式开业,进一步拓展了其在零售领域的布局。这一举措显示了理想汽车在中国市场的重要地位和战略意义。这些新开业的零售中心,是理想汽车基于“人文科技、幸福和连接”的设计理念的全新尝试。这种设计理念在店铺设计、店铺体验和店铺功能等方面都带来了显著的提升。通过通透温暖的空间设计和豪华舒适的细节品质,这些零售中心为家庭用户提供了理想汽车专业产品和服务的理想场所。深度交互的体验连接不仅使顾客获得了更好的购车体验,还为他们创造了一种温馨的“家”的氛围。

本站1月10日消息,理想汽车发布了最新的周销量榜,数据显示:2024年第1周(1.1-1.7),理想汽车销量为0.43万辆,而AITO问界为0.59万,超过理想1600台。如果是看新能源榜单,那么2024年第一周比亚迪以4.44万辆的成绩登上榜一,五菱以1.02万辆紧随其后,AITO问界第三,长安汽车、广汽埃安和理想汽车分别位列4、5、6名,大众汽车、深蓝汽车、特斯拉、蔚来汽车位列7、8、9、10名;“晚点Auto”之前表示,在理想汽车内部,很多员工之间存在这样的共识——今年是理想跟华为的主战场


Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

AI Hentai Generator
Generate AI Hentai for free.

Hot Article

Hot Tools

Zend Studio 13.0.1
Powerful PHP integrated development environment

EditPlus Chinese cracked version
Small size, syntax highlighting, does not support code prompt function

Dreamweaver Mac version
Visual web development tools

Atom editor mac version download
The most popular open source editor

mPDF
mPDF is a PHP library that can generate PDF files from UTF-8 encoded HTML. The original author, Ian Back, wrote mPDF to output PDF files "on the fly" from his website and handle different languages. It is slower than original scripts like HTML2FPDF and produces larger files when using Unicode fonts, but supports CSS styles etc. and has a lot of enhancements. Supports almost all languages, including RTL (Arabic and Hebrew) and CJK (Chinese, Japanese and Korean). Supports nested block-level elements (such as P, DIV),
