作者 | 蔡道清 编辑 | 自动驾驶之心 原文链接： https://zhuanlan.zhihu.com/p/1932480841222723066 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 本文只做学术分享，如有侵权，联系删文 作者阵容挺强的，代码也开源了，值得follow。 Motivation 自动驾驶世界模型需同时满足长时程高分辨率场景生成与实时精准轨迹规划，但现有方法存在明显局限： 因而，本文提出一个 既能生成长时高分辨率视频，又能端到端输出连续轨迹 的统一框架。 Contribution Paper link ： https://arxiv.org/pdf/2506.24113 Code link ： https://github.com/Kevin-thu/Epona 扩散模型（如Vista）：固定长度视频生成（≤15秒），无法支持灵活长时预测（>2分钟）和多模态轨迹控制； GPT式自回归模型（如GAIA-1）：可无限延伸，却需把图像 离散成 token ，导致视觉质量下降，且缺乏连 ...

Financial Data and Key Metrics Changes - Total revenues for Q2 reached $21.5 million, a 76% increase year over year, driven by strong growth in robotaxi services and licensing applications [39][41] - Robotaxi service revenues grew to $1.5 million, reflecting a 158% year over year increase, with fare charging revenues expanding by over 300% [39][40] - Gross margin improved to 16.1%, with gross profit of $3.5 million in Q2 [42] - Net loss for Q2 was $53.3 million, up from $30.9 million in the same period last year [44] Business Line Data and Key Metrics Changes - Robotaxi service revenues surged by 150% year over year, with fare charging revenues growing more than 300% [15][39] - Licensing and application revenues reached $10.4 million, a 902% increase year over year [41] - Global truck services revenue decreased by 10% year over year [41] Market Data and Key Metrics Changes - Registered users surged by 136% year over year in Q2, with a user satisfaction rate above 4.8 out of 5 [8][17] - The company operates across 2,000 square kilometers in Tier one cities in China, significantly expanding its market reach [56] Company Strategy and Development Direction - The company aims for mass production of Gen seven robotaxis, targeting over 1,000 vehicles by year-end 2025 [7][23] - A strategic partnership with Hehu Group aims to deploy over 1,000 robotaxis in Shenzhen [16] - The focus is on scaling up operations and enhancing user experience to drive higher demand [23][56] Management's Comments on Operating Environment and Future Outlook - Management expressed confidence in achieving positive unit economics for Gen seven vehicles, citing significant cost reductions and operational efficiencies [51] - The company is well-positioned for large-scale commercialization, with a solid plan and execution strategy in place [45][36] Other Important Information - The company has secured Shanghai's first fully driverless commercial license, enabling operations in all four Tier one cities [18][32] - The bond cost of Gen seven robotaxis has been reduced by 70% compared to previous generations [51] Q&A Session Summary Question: Production plan throughout 2025 - Management confirmed they are on track to exceed 1,000 robotaxi vehicles by year-end, with over 200 already produced [47][49] Question: Key drivers behind robotaxi revenue growth - Management highlighted user adoption, demand in Tier one cities, and an increased fleet as key drivers of revenue growth [55][56] Question: Impact of government comments on L4 robotaxi industry - Management noted that recent comments clarify the distinction between L2 and L4 systems, which is beneficial for public understanding and safety standards [60][62] Question: Key technical requirements for new market expansion - Management emphasized the ability to handle corner cases and the robustness of their software system as critical for entering new geographies [66][68] Question: Timetable for potential Hong Kong IPO - Management refrained from commenting on market speculation but stated they are monitoring market conditions closely [73][74] Question: Future plans for overseas market expansion - Management outlined a focus on markets with strong mobility demand and supportive regulatory environments, with ongoing operations in Dubai, South Korea, and Luxembourg [78][80]

Key Highlights & Growth - Pony AI produced over 200 Gen-7 vehicles as of August 11, 2025 [7] - The company aims to produce over 1,000 vehicles by the end of 2025 [7, 22] - Registered user growth increased by 136% year-over-year from 2Q24 to 2Q25 [7, 32] - Total revenue grew by 76% in 2Q25 [7] - Fare-charging revenue experienced a growth of over 300% in 2Q25 [7, 35, 70] Commercialization & Operations - Pony AI is the only company with fully driverless commercial licenses in all four Tier-1 cities in China (Beijing, Shanghai, Guangzhou, Shenzhen) [20, 31] - Robotaxis receive approximately 15 average daily orders [20] - Accumulated autonomous driving kilometers reached 488 million+ as of June 30, 2025 [36] - Accumulated autonomous driverless kilometers reached 87 million+ as of June 30, 2025 [36] Financial Performance - Robotaxi services revenue increased by 1578% from $06 million in 2Q24 to $15 million in 2Q25 [65] - Total revenue increased by 9018% from $122 million in 2Q24 to $104 million in 2Q25 [69]

⼀、 端到端盛行的当下，轨迹预测这个方向还有研究价值吗？ 最近有同学后台问我们，现在都是搞端到端了，前面的轨迹预测和规划控制还有啥研究的价值吗？端到端真的 上车的并不多，很多依然沿用分层方案，其中轨迹预测作为后半段的核心算法，依然是许多公司和机构研究的 热点。包括联合轨迹预测和目标轨迹预测。相关的会议和期刊依然有较大量的工作产出。 自动驾驶之心针对目前比较火的基于扩散模型的多智能体轨迹预测方法研究展开了首个1v6小班课！本课题聚 焦于"基于扩散模型的多智能体轨迹预测方法"。多智能体轨迹预测旨在根据多个交互主体的历史轨迹，预测其 未来运动轨迹，这在自动驾驶、智能监控和机器人导航等场景中至关重要。然而，由于人的行为具有不确定性 和多模态性，预测任务十分困难。传统方法通常依赖循环神经网络、卷积网络或图神经网络建模社会交互，而 生成模型（如GAN和CVAE）虽然可以模拟多模态分布，但效率不高。 扩散模型是一类通过逐步去噪实现复杂分布生成的新型模型，近年来在图像生成等领域取得了重大突破。研究 者发现将扩散模型应用于轨迹预测可以显著提升多模态建模能力。例如，LeapfrogDiffusionModel（LED）采 用可训 ...

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 DRIVE 约束感知自动驾驶的动态规则推断与验证评估框架 斯坦福大学和微软提出了 DRIVE 框架，通过动态规则推断和验证评估技术，实现了自动驾驶中概率软约束 的学习与规划集成，在 inD、highD 和 RoundD 数据集上达成 0.0% 软约束违反率，并显著提升轨迹平滑性 与泛化能力。 主要贡献： 算法框架： 实验结果： 可视化： 论文标题：DRIVE: Dynamic Rule Inference and Verified Evaluation for Constraint-Aware Autonomous Driving 论文链接：https://arxiv.org/abs/2508.04066 代码：https://github.com/genglongling/DRIVE 1. 提出 DRIVE 框架，通过指数族似然建模从专家驾驶演示中学习概率性软约束，克服了传统方法依赖固 定约束形式或纯奖励建模的局限，实现了动态规则推理与轨迹级决策的紧密耦合。 2. 将学习到的约束分布嵌入凸优化规划模块，生成 ...

Core Viewpoint - The article discusses the advancements in autonomous driving technology, particularly focusing on the LLaMA Factory framework and the Qwen2.5-VL model, which enhance the capabilities of vision-language-action models for autonomous driving applications [4][5]. Group 1: LLaMA Factory Overview - LLaMA Factory is an open-source low-code framework for fine-tuning large models, gaining popularity in the open-source community with over 40,000 stars on GitHub [3]. - The framework integrates widely used fine-tuning techniques, making it suitable for developing autonomous driving assistants that can interpret traffic conditions through natural language [3]. Group 2: Qwen2.5-VL Model - The Qwen2.5-VL model serves as the foundational model for the project, achieving significant breakthroughs in visual recognition, object localization, document parsing, and long video understanding [4]. - It offers three model sizes, with the flagship Qwen2.5-VL-72B performing comparably to advanced models like GPT-4o and Claude 3.5 Sonnet, while smaller versions excel in resource-constrained environments [4]. Group 3: CoVLA Dataset - The CoVLA dataset, comprising 10,000 real driving scenes and over 80 hours of video, is utilized for training and evaluating vision-language-action models [5]. - This dataset surpasses existing datasets in scale and annotation richness, providing a comprehensive platform for developing safer and more reliable autonomous driving systems [5]. Group 4: Model Training and Testing - Instructions for downloading and installing LLaMA Factory and the Qwen2.5-VL model are provided, including commands for setting up the environment and testing the model [6][7]. - The article details the process of fine-tuning the model using the SwanLab tool for visual tracking of the training process, emphasizing the importance of adjusting parameters to avoid memory issues [11][17]. - After training, the fine-tuned model demonstrates improved response quality in dialogue scenarios related to autonomous driving risks compared to the original model [19].

据了解，萝卜快跑是百度Apollo自动驾驶出行服务平台。2022年6月10日，萝卜快跑正式在重庆永川区 投入运营。截至2025年3月，百度"萝卜快跑"自动驾驶出行服务平台，已在永川建立近4000多个站点， 运营面积超130平方公里。 凤凰网科技讯 8月7日，多名网友发布视频称，重庆永川区试运营的"萝卜快跑"无人驾驶网约车在行驶 中坠入市政施工沟槽。视频显示，车辆部分陷入坑内，车内女乘客在工作人员和群众帮助下脱困。截至 目前，萝卜快跑方面尚未就此事作出回应。 ...

[Music] Good evening everyone. So today I'll be talking about learning for a world that does not exist. Of course I'm coming it from the technical point of view.Today we are living in a world which is technically very dynamic. We are producing a lot of techni technological advancement and for young engineers and aspirants of engineering. Uh this can be a very challenging moment because um by the time we finish our education new industries emerge, lots of industries saturate and we need to be prepared by the ...

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15个 方向 学习 路线 知识星球最近有小伙伴面了新势力的提前批，结果面试官最后来个三连问，都是开放性的非技术问题。 面试快结束的时候，面试官问了我很多非技术问题，感觉从来没思考过，被问懵了。。。 彻底懵了，而且感觉回答的，面试官并不满意，主要是这些问题，我不知道面试官关注的点在哪里？ 星主回答： 1、这个就几何你自己的兴趣和经验展开来说就好，没什么标准的答案。但你最好思考过，这里面试官隐含的考察你有没有自己的主见。其实很多校招生都不知 道自己想做什么。。。找学长学姐或者网上提前了解面试大部门的业务，如果觉得不错可以靠一靠，一方面会吸引面试官感兴趣，甚至最后分配的时候会被点名 要过去。另一方面你在回答这个问题的时候也可以适当问问面试官团队是在做什么方向工作，这样也算是有个渠道了解业内实际的工作方向。 2、面试官是想了解，你沟通能力怎么样？是不是一个"好带的人"。没有实习经历的人可能没这种体会，如果在实验室和学长学姐沟通也类似。你可以这么说： 我习惯接手一个任务时先判断熟悉程度，一般会先自己整体调研下这个方向，遇到不会的地方记录下来，跟 ...

Core Viewpoint - WeRide has received approval for late-night testing of its Robotaxi in Beijing, marking a significant step towards establishing a 24/7 autonomous ride-hailing network in the city [1][6] Group 1: Testing and Technology - The approval allows testing from 10pm to 7am in the Beijing High-Level Autonomous Driving Demonstration Zone, which is crucial for developing all-weather, all-day autonomous mobility services [1][6] - WeRide's Robotaxi is equipped with over 20 sensors, including high-precision cameras and LiDARs, achieving 360-degree coverage with a detection range of up to 200 meters, ensuring stable perception and rapid decision-making in low-light conditions [3][4] - The company has conducted Robotaxi testing or operations in 10 cities across four countries, accumulating over 2,200 days of safe open-road experience [5] Group 2: Challenges and Solutions - Night-time road conditions in Beijing present challenges such as low lighting and environmental interference, which require advanced perception and decision-making capabilities [2] - WeRide addresses visibility issues with a proprietary multi-sensor fusion algorithm and a high-performance computing platform, ensuring effective sensor fusion under adverse conditions [3] - The company employs automotive-grade sensors and a smart sensor cleaning system to maintain reliable perception in extreme weather conditions [4] Group 3: Future Outlook - The launch of 24/7 Robotaxi testing in Beijing validates WeRide's technology and safety systems, enhancing public transportation availability during off-peak hours [6] - WeRide aims to leverage its full-stack autonomous driving technology to expand its ride-hailing services and contribute to smarter, more sustainable urban transportation [7] - The company is recognized as a leader in the autonomous driving industry, being the first publicly traded Robotaxi company and having received permits in six markets [9]