添加小助理微信AIDriver005，备注：昵称+机构/学校+进群。 自动驾驶之心L4交流群来了，关注L4赛道融资、技术进展、RoboTaxi、RoboBus、RoboVan、无人配送、无人 矿卡、无人重卡等方向~ ...

点击下方 卡片 ，关注" 自动驾驶之心 "公众号 戳我-> 领取 自动驾驶近30个 方向 学习 路线 >>自动驾驶前沿信息获取 → 自动驾驶之心知识星球 论文作者 | Fengyi Zhang等 编辑 | 自动驾驶之心 3D视觉基础模型：从离线重建到在线增量重建 最近， 3D视觉基础模型 的出现，如 VGGT、π³、MapAnything，标志着三维重建领域迈入了一种端到端、数据驱动的新范式。这类模型能够在一次前向推理中，直 接从输入图像预测相机内参、相机位姿以及稠密几何结构，极大地简化了传统三维重建流程，并展现出强大的跨场景泛化能力。基础模型的成功建立在大规模、有 标注的3D数据集以及在其上训练的大型 Transformer 架构，这使得模型能够同时学习多视几何、视角关系以及场景结构先验。 然而，现有的大多数基础模型主要被设计用于 离线场景重建 ，即在推理阶段可以 一次性访问完整的图像序列 。而在自动驾驶、机器人操作等现实应用场景中，系 统通常需要具备 在线重建能力 ：模型应当能够随着新数据的到来， 增量式地重建新区域 ，而非在获取全部图像后再统一处理。尽管已有少数工作如 CUT3R 尝试 在模型层面直接支 ...

Core Viewpoint - The article emphasizes the rising importance of end-to-end (E2E) systems in the autonomous driving industry, highlighting the shift from modular perception to direct environmental sensing and action generation, which simplifies system complexity and enhances the ability to handle complex driving scenarios [2]. Group 1: End-to-End Systems - The success of Horizon HSD has prompted a reevaluation of the significance of E2E systems in smart driving, moving away from heavy reliance on modular perception and strict rule-based systems [2]. - E2E systems face challenges in practical applications, such as trajectory instability, primarily due to the lack of continuous correction capabilities based on environmental feedback [3]. - Reinforcement Learning (RL) offers a new approach for E2E systems, transitioning from imitation to optimization by incorporating reward signals to refine action strategies and address limitations of pure imitation learning [4][5]. Group 2: Industry Trends and Talent Demand - Leading companies in the industry have developed a comprehensive model iteration approach, which includes imitation learning training, closed-loop reinforcement learning, and rule-based planning, indicating a high barrier to entry for talent in E2E production [6]. - The high barrier to entry and scarcity of skilled professionals have resulted in generous salaries, with top talents earning starting salaries of 1 million and above [7]. Group 3: Challenges in Mass Production - The mass production of E2E systems encounters numerous challenges, including complex scenarios like congestion, static yaw, and collision situations, necessitating both data mining and data cleaning [8]. - There is a notable gap in practical experience among many candidates, as many have only theoretical knowledge without real-world application experience [8]. Group 4: Course Offering - The article introduces a specialized course aimed at bridging the gap in practical skills for E2E systems, led by top-tier algorithm engineers from the industry [9]. - The course covers various aspects of E2E systems, including task overview, two-stage and one-stage algorithms, navigation information applications, RL algorithms, trajectory optimization, and production experiences [12][14][15][16][17][18][19][20][21]. Group 5: Target Audience and Prerequisites - The course is designed for advanced learners with a foundational understanding of autonomous driving perception, reinforcement learning, and programming skills, although those with weaker backgrounds can still participate [22][23].

该消息也侧面印证了长安汽车取消年终奖一事不实，且内部已经进入到落实阶段。随着长安汽车官方辟谣，网 络上的争议也随之反转，有来自其他车企的员工在社交平台上表示，"两天前还在嘲笑长安，现在嘲笑我自己 了"。还有网友表示："小丑竟是我自己"、"长安汽车，对不起，我承认我之前笑的太大声了"。（快科技） 点击下方 卡片 ，关注" 自动驾驶之心 "公众号 戳我-> 领取 自动驾驶近30个 方向 学习 路线 据雷锋网报道，1月7日消息，近日，有媒体爆料称，国内某车企发出一则内部通知称：鉴于今年公司销量、利 润率等指标未达成年终目标，所以今年没有年终激励奖。虽然该车企年度销量目标未达标，但销量完成率达到 了97%，有媒体据此推断，取消年终奖的车企是长安汽车，且在社交平台上，疑似有长安汽车员工证实年终奖 取消，此事引发热议。 7日，长安汽车不实信息举报中心发文称，针对近期网络上出现的"长安汽车取消年终奖"等不实信息，公司严 正声明如下：2025年，长安汽车整体经营态势稳健，公司已根据年度经营实绩，按照激励标准制定并推进相应 激励计划，切实保障员工权益，助力企业可持续发展。对此，有媒体从多位接近长安汽车的业内人士处获悉， 部分部 ...

Core Viewpoint - The concept of "data closed loop" in the autonomous driving industry is still largely limited to small internal loops within algorithm teams, rather than achieving the grand vision of a comprehensive system that directly solves problems through data [1]. Group 1: Definition of "True Data Closed Loop" - A "true closed loop" must meet three levels: automated problem discovery, quantifiable and reviewable solution effects, and a comprehensive trigger system that integrates real-time and historical data [4][5]. - The ideal state involves a system that can automatically classify issues, route them to the appropriate teams, and assist in developing trigger rules, thereby reducing reliance on manual processes [5]. Group 2: Current Industry Practices - Many companies' so-called "data closed loops" are more accurately described as "data-driven development processes with some automation tools," primarily limited to the perspective of individual algorithm teams [8]. - Typical workflows are often module-level and algorithm-focused, lacking a system-wide perspective [9]. Group 3: Reasons for Lack of True Closed Loops - The starting point for many companies is a "passive closed loop," where problems are identified reactively rather than through automated data analysis [10]. - Attribution of issues is often difficult, as multiple interrelated factors contribute to the same phenomenon [12]. - The data-to-solution chain often stops at data-to-model, failing to address real-world problems effectively [16]. Group 4: Data Closed Loop Practices - The company has developed a more aggressive approach to data closed loops, treating data as a product and metrics as primary citizens [24]. - The overall strategy involves quantifying real-world pain points and using triggers to convert these into actionable data [25]. Group 5: Trigger Mechanism - The trigger mechanism is designed to be lightweight and high-recall, ensuring that significant events are captured without overwhelming the system [32]. - Once a trigger is activated, it generates a micro log that is uploaded for further analysis, leading to more detailed data collection if necessary [35]. Group 6: Unified Trigger Framework - A unified trigger framework using Python allows for consistent implementation across vehicle data mining, cloud data analysis, and simulation validation [50]. - This framework enables non-technical team members to participate in writing rules, thus democratizing the process of data analysis [54]. Group 7: Distinction Between World Labels and Algorithm Labels - The company maintains two types of labels: world-level labels that describe objective physical conditions and model-level labels that depend on algorithm performance [61]. - This distinction is crucial for effective data analysis and problem-solving in the autonomous driving context [61]. Group 8: Use of Generative and Simulation Data - Generative data is primarily used to address long-tail scenarios that are difficult to encounter in real life, but real data remains essential for evaluation and validation [67]. - The company emphasizes the importance of filtering data through structured labels before applying vector retrieval methods to ensure efficiency and accuracy [64].

Core Viewpoint - The article discusses an advanced course on end-to-end (E2E) autonomous driving, focusing on the latest technologies such as BEV perception, Visual Language Models (VLM), diffusion models, and reinforcement learning, aimed at equipping participants with cutting-edge skills in the field [1][4][8]. Group 1: Course Structure - The course is divided into several chapters, starting with an introduction to end-to-end algorithms, covering the historical development and advantages of E2E methods over modular approaches [4]. - The second chapter focuses on background knowledge essential for understanding E2E technologies, including VLA, diffusion models, and reinforcement learning, which are crucial for job interviews in the next two years [5][9]. - The third chapter delves into two-stage E2E methods, discussing their emergence, advantages, and notable algorithms like PLUTO and CarPlanner [5][6]. - The fourth chapter highlights one-stage E2E methods and VLA, exploring various subfields and their contributions to achieving the ultimate goals of E2E systems [6][10]. Group 2: Practical Application - The course includes a major project on RLHF fine-tuning, allowing participants to apply their knowledge in practical scenarios, including building pre-training and reinforcement learning modules [7]. - The course aims to help participants reach a level equivalent to one year of experience as an E2E autonomous driving algorithm engineer, covering various methodologies and key technologies [13]. Group 3: Target Audience and Requirements - The course is designed for individuals with a foundational understanding of autonomous driving, familiar with basic modules, and concepts like transformer models, reinforcement learning, and BEV perception [11]. - Participants are expected to have a background in probability theory and linear algebra, as well as proficiency in Python and PyTorch [11].

Core Insights - The article discusses the advancements in autonomous driving technology, particularly the transition from Level 2 (L2) to Level 4 (L4), indicating that high-level assisted driving has reached a "quasi-L4" stage, with the same model being applicable for both L2 and L4 [4] - The autonomous driving industry in China has seen over 30 billion yuan in financing in 2025, primarily focused on the L4 sector, suggesting a significant shift in industry attention towards L4 technology [4] - A roundtable discussion on L4 autonomous driving is scheduled, featuring leading companies in the field, to explore the technological and commercial realities of L4, including its evolution and future market landscape [4] Group 1 - The article highlights the comparison between Tesla's FSD V14.2 and Robotaxi, emphasizing the advancements in high-level assisted driving technology [4] - It notes that the L4 sector is gaining new attention due to recent changes, prompting discussions on whether it has reached a critical juncture [4] - The upcoming roundtable aims to provide diverse perspectives from top L4 companies, focusing on the interplay between technological ideals and commercial realities [4] Group 2 - Key speakers at the roundtable include industry leaders with extensive backgrounds in autonomous driving technology and research, such as He Bei, founder of Sinian Intelligent Driving, and Miao Qian Kun, CTO of New Stone Age Autonomous Vehicles [5][6] - The article mentions the impressive achievements of Miao Qian Kun's L4 urban logistics delivery vehicles, which have been widely deployed across over 300 cities in China and more than 10 countries, with a total of 15,000 vehicles delivered and over 60 million kilometers driven [6] - The discussion will also feature experts with significant experience in AI and autonomous vehicle development, ensuring a comprehensive exploration of the topic [7][8]

最近在复盘各家如何使用世界模型的，今天和大家盘一下理想在这方面的工作。理想对世界模型的定义在 重建+生成 ，利用重建技术（3DGS）建模自动驾驶场 景，再利用生成方法实现闭环仿真或者场景生成。 这里面核心的技术是3DGS和生成。 ICCV2025中稿的Hierarchy UGP，自动驾驶场景重建。 具有时空一致性的多风格自动驾驶场景生成算法StyledStreets。 整合多模态驾驶意图与潜在世界模型实现合理规划的World4Drive，中稿ICCV 2025。 自动驾驶的视频生成扩散世界模型GeoDrive。 统一生成视觉与lidar的自驾世界模型框架OmniGen，中稿ACMMM2025。 结合强化学习的自动驾驶视频生成世界模型RLGF，中稿NeurIPS 2025。 利用稀疏注意力实现4D OCC世界模型预测算法 SparseWorld-TC。 世界模型端到端闭环强化学习框架AD-R1。 整体上来看，世界模型是围绕视频为核心搭建的时空认知系统 ，这一点也和蔚来任少卿的观点一致。通过跨模态的互相预测和重建，促使系统学习时空和物理规 律，让机器能像人一样理解环境。 通过重建+生成，既可以做云端的数据生成，也 ...

点击下方 卡片 ，关注" 自动驾驶之心 "公众号 戳我-> 领取 自动驾驶近30个 方向 学习 路线 >>自动驾驶前沿信息获取 → 自动驾驶之心知识星球 论文作者 | Xiaobao Wei等 编辑 | 自动驾驶之心 高斯泼溅的风，刮到了自驾的每个角落。 一大早看到了小米&杭电在泊车场景重建中的工作ParkGaussian。 相比英伟达3DGUT和OmniRe提升挺大，分享给大家。 泊车是自动驾驶系统（ADS）的关键任务，在车位拥挤且无GPS信号的环境中面临独特挑战。现有研究主要集中于二维车位感知、建图与定位，而三维重建领域的探 索仍显不足——该技术对于捕捉泊车场景中的复杂空间几何结构至关重要。单纯提升重建泊车场景的视觉质量并不能直接助力自动泊车，因为泊车系统的核心入口是 车位感知模块。 为解决这些局限，小米汽车联合杭州电子科技大学构建了首个专为泊车场景重建设计的基准数据集ParkRecon3D，其包含来自四台已完成外参标定的环视鱼眼相机的 传感器数据，以及密集的车位标注信息。在此基础上，本文提出了ParkGaussian框架，这是首个将3D高斯Splatting（3DGS）融入泊车场景重建的方案。为进一步提 ...

点击下方 卡片 ，关注" 自动驾驶之心 "公众号 戳我-> 领取 自动驾驶近30个 方向 学习 路线 最近有同学在自动驾驶之心社区里咨询柱哥，全球自动驾驶未来的发展趋势究竟如何？中国在其中又能扮演怎 样的角色？刚好我之前关注到摩根斯坦利的一份研究报告，里面的分析很有参考价值，今天就整理出来和大家 做个分享。 报告中对 L4/L5 级自动驾驶汽车（AV）的全球市场渗透趋势划分得很清晰： 尤其值得关注的是中国的表现，完全称得上"引领者" 角色 ：预计2026年，中国占全球 L4+自动驾驶车辆的比 例会快速飙升至接近 80%，之后虽有缓慢回落，但长期仍能保持 20% 以上的高占比；从全球总量贡献来看， L4+车辆 2024 年几乎为零，后续逐步稳步增长，中国的贡献始终占据突出地位；即便到 2040 年后，美国、欧 洲及其他地区的 L4+车辆数量均呈现明显增长态势，中国在全球市场中的占比依然能保持领先。 以上就是柱哥整理的核心信息，欢迎大家加入我们的自驾社区一起讨论！ 近期柱哥也会邀请嘉宾在星球内部 和大家聊一聊最近的一些技术进展，我们准备了大额新人优惠...... 名额有限，仅限前「5名」 扛内卷，一个足够有料的社 ...