Core Viewpoint - Horizon Robotics-W (09660) has seen a significant stock increase of over 6%, currently trading at 9.18 HKD with a transaction volume of 1.801 billion HKD, following a strategic partnership announcement with autonomous driving company Carl Power [1] Group 1: Strategic Partnership - Horizon Robotics has entered into a comprehensive strategic cooperation with Carl Power to develop efficient, safe, and scalable autonomous driving solutions for trunk logistics [1] - The collaboration aims to leverage deep integration of data and scenarios to create a robust L4 autonomous freight system, accelerating the technology and commercialization process of L4 heavy-duty trucks [1] Group 2: Financial Outlook - Citi has raised its estimated R&D expenditure for Horizon Robotics for 2026-2027 by nearly 1 billion RMB [1] - The firm believes that the current stock price of Horizon Robotics reflects all negative factors, indicating greater upside potential [1] - Key catalysts expected in the coming months include customer certification for the J6P and adoption of the HSD600 by leading domestic vehicle manufacturers [1]

Core Insights - The founder and CEO of WeRide, Han Xu, emphasized the importance of having a fleet of at least 20-30 vehicles operating autonomously for a company to claim it is at Level 4 (L4) autonomy [1] - Han criticized the industry for misleading claims, stating that some companies merely rebrand existing technologies without developing their own [3] - He highlighted the significant difference in difficulty between achieving Level 2+ (high-level assisted driving) and L4 autonomy, comparing it to the difference between operating a small boat and a transoceanic ship [3] - Han made a bold prediction regarding Tesla's Full Self-Driving (FSD) capabilities, suggesting that within three years, Tesla will not reach the same level of performance as WeRide in San Francisco using mass-produced vehicles [5] - He anticipates that advancements in AI will lead to the emergence of "super human drivers" by the end of 2033, surpassing 99.99% of human drivers [5] - Han shared insights from his entrepreneurial journey, advising current entrepreneurs to maintain sufficient funding and prioritize their health [5] Industry Context - The dialogue took place at the MEET2026 Smart Future Conference, highlighting the critical phase of commercialization in the autonomous driving sector [5] - Han's perspectives provide a clear reflection of industry standards, technological pathways, and future trends, which are essential for stakeholders in the autonomous driving field [5]

Core Insights - The core viewpoint emphasizes that the key to successful autonomous driving lies in the integration of the VLA model with the entire embodied intelligence system, where data plays a crucial role in determining effectiveness [1][4]. Summary by Sections VLA Model - The VLA is fundamentally a generative model, utilizing a GPT-like approach for autonomous driving, generating trajectories and control signals instead of text. User feedback indicates that VLA exhibits emergent behaviors in certain scenarios, reflecting a growing understanding of the physical world [2]. - The world model is better suited for creating "test environments" rather than acting as "test subjects," due to its high computational demands. Ideal is currently leveraging cloud-based data generation and realistic simulation testing, utilizing several exaFLOPS of computational power for simulation tests, which cannot be matched by even the most powerful vehicle chips [2]. - Discussions about model architecture are less relevant than the actual performance outcomes. In autonomous driving, focusing on vast amounts of real data is essential, and Ideal's commitment to VLA is supported by a data loop created from millions of vehicles, enabling near-human driving levels with current computational resources [2]. Embodied Intelligence - To excel in autonomous driving, it is essential to treat it as a complete embodied intelligence system, where all components must work together during development to maximize value. Human drivers do not require extraordinary abilities; rather, coordination among various parts is crucial [3]. - The embodied intelligence system comprises perception (eyes), models (brain), operating systems (nervous system), chips (heart), and the body (vehicle). Full-stack self-research is necessary, encompassing both software and hardware. Ideal's autonomous driving team collaborates with foundational model, chip, and chassis teams to create a comprehensive autonomous driving system [3]. Data Utilization - The key to effective modeling is its compatibility with the entire embodied intelligence system, with data being the decisive factor. While data acquisition is challenging in robotics, it is not a significant issue for companies in the autonomous driving sector that have established data loops. Ideal can mine and filter from over 1 billion kilometers of accumulated data and continuously gather new data from 1.5 million vehicle owners [4]. - During data filtering, interesting patterns were observed, such as nearly 40% of human driving data showing a tendency to drive on one side and not strictly adhering to speed limits. This behavior aligns with typical human driving patterns, leading to the decision not to eliminate these data samples. The VLA model is expected to serve both current and future automotive forms of embodied robots [4].

Core Viewpoint - The report from Credit Lyonnais maintains a target price of HKD 11 for Horizon Robotics (09660), suggesting that the current stock price has fully reflected negative factors such as share issuance, indicating greater upside potential [1] Group 1: Company Performance and Outlook - Credit Lyonnais expects that the customer certification of J6P and the adoption of HSD600 by leading domestic automakers will serve as key catalysts in the coming months [1] - The firm has raised its estimates for the company's R&D expenditure for 2026-2027 by nearly RMB 1 billion, reflecting confidence in existing technology routes and the need for accelerated product iteration [1] Group 2: Market Conditions and Competitive Landscape - The report highlights the intense competition in the high-level autonomous driving (AD) algorithm sector, which is influencing the company's strategic decisions [1]

Core Viewpoint - The article discusses the limitations of current large visual language models (VLMs) in autonomous driving, emphasizing the need for enhanced spatial perception and geometric understanding to support robust decision-making in real-world scenarios [2][3]. Group 1: Model Introduction - A new model named Percept-WAM (Perception-Enhanced World–Awareness–Action Model) has been proposed, aiming to integrate perception, world awareness, and vehicle action into a cohesive framework for autonomous driving [3][4]. - Percept-WAM is designed to create a complete link from perception to decision-making, addressing the shortcomings of existing models that struggle with real-world complexities [3][4]. Group 2: Model Architecture - The architecture of Percept-WAM incorporates a general reasoning VLM backbone while introducing World-PV and World-BEV tokens to unify 2D/3D perception representations [5]. - The model employs a grid-conditioned prediction mechanism and IoU-aware confidence outputs to enhance the accuracy and efficiency of its outputs, along with a lightweight action decoding head for efficient trajectory prediction [5][6]. Group 3: Training Tasks - Percept-WAM is trained using multi-view streaming video, LiDAR point clouds (optional), and text queries, optimizing various tasks such as 2D detection, instance segmentation, semantic segmentation, and 3D detection [6][9]. - The model's training approach allows for joint optimization across multiple tasks, enhancing the overall performance through shared geometric and semantic information [23]. Group 4: Performance Evaluation - In public benchmarks, Percept-WAM demonstrates competitive performance in PV perspective perception, BEV perspective perception, and end-to-end trajectory planning compared to existing models [21][30]. - Specifically, in the PV perspective, Percept-WAM achieves a 49.9 mAP in 2D detection, surpassing the performance of specialized models like Mask R-CNN [22][24]. - In the BEV perspective, the model achieves a 58.9 mAP in 3D detection, outperforming traditional BEV detection methods [27][28]. Group 5: Confidence Prediction - The introduction of IoU-based confidence prediction significantly improves the alignment between predicted confidence scores and actual localization quality, enhancing the reliability of dense detection [25]. Group 6: Decision-Making Integration - Percept-WAM integrates World–Action tokens for action and trajectory prediction, allowing for a seamless transition from world modeling to decision output, thus aligning perception and planning in a unified representation space [16][17]. - The model employs a query-based trajectory prediction method that leverages multiple feature groups, enhancing the efficiency and accuracy of trajectory planning [19]. Group 7: Future Implications - Percept-WAM represents a forward-looking evolution in autonomous driving, emphasizing the importance of a unified model that can perceive, understand, and act within the world, moving beyond traditional models that merely process language [41].

Group 1 - The core viewpoint of the article is that the autonomous driving industry is entering a stage of commercialization, positively impacting the company's vehicle networking and autonomous driving-related businesses [1] Group 2 - In the Robotaxi sector, the company has established partnerships with Baidu Apollo, Hello, and Cao Cao Mobility [1] - In the Robovan sector, the company has formed collaborations with Jiushi and Zhixingzhe [1] - The company's profitability will depend on various factors, including market changes and business strategies, and it will continue to monitor market dynamics to enhance profitability [1]

Core Viewpoint - The article emphasizes the rapid advancements in 3D Gaussian Splatting (3DGS) technology within the autonomous driving sector, highlighting the need for structured learning pathways for newcomers in the field [2][4]. Group 1: Technology Highlights - Tesla's introduction of 3D Gaussian Splatting at ICCV has garnered significant attention, indicating a shift towards feed-forward GS algorithms for scene reconstruction [2]. - The iterative development of 3DGS technology includes static 3D reconstruction, dynamic 4D reconstruction, and surface reconstruction, showcasing its evolving nature [4]. Group 2: Course Offering - A comprehensive course titled "3DGS Theory and Algorithm Practical Tutorial" has been designed to provide a structured learning roadmap for 3DGS, covering both theoretical foundations and practical applications [4]. - The course will be taught by an expert with extensive experience in 3D reconstruction and algorithm development, ensuring high-quality instruction [5]. Group 3: Course Structure - The course consists of six chapters, starting with foundational knowledge in computer graphics and progressing through principles, algorithms, and specific applications in autonomous driving [8][9][10][11][12]. - Each chapter is designed to build upon the previous one, culminating in discussions about current industry needs and research directions in 3DGS [11][12][13]. Group 4: Target Audience and Prerequisites - The course is aimed at individuals with a background in computer graphics, visual reconstruction, and programming, particularly those interested in pursuing careers in the autonomous driving industry [17]. - Participants are expected to have a foundational understanding of relevant mathematical concepts and programming languages, which will facilitate their learning experience [17].

以下文章来源于RoboX ，作者RoboX RoboX . 从AI汽车到机器人，我们关注最具潜力的超级智能体！ 作者 | RoboX 来源 | RoboX 原文链接： 地平线苏箐演讲全文提炼：自动驾驶的曙光、痛苦与轮回 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 演讲者：苏箐 | 地平线副总裁&首席架构师 演讲时间 ：2025.12.9 演讲场合 ：2025地平线技术生态大会 全文提炼如下： 今年，我们确实能看到自动驾驶的技术路径是比较清晰的，但也会看到有更难的问题在前面。你知道这些问题能解掉，但应该怎么解今天还不知道。 绝大多数行业外的人，可能并不理解自动驾驶团队面临的困难和压力。这种智力和体力的双重压榨极度痛苦，因为有SOP的时间压在那儿，然后又有方法论的变化， 还有各种corner case需要去解。 在稠密的世界里连续运行的时候，所有的case都需要解决，这就是这个行业非常痛苦的地方。 曙光：重大分水岭的出现 我刚准备加入地平线的时候，和余凯博士聊过几次， ...

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 | Haicheng Liao等 编辑 | 自动驾驶之心 在自动驾驶的交互场景中，最尴尬的时刻莫过于此： 乘客指着前方复杂的路口说："跟着那辆SUV"。自动驾驶系统看着眼前三辆长得差不多的车，内心OS："哪辆？是左边那辆？还是正在变道那辆？" 现有的自动驾驶视觉定位（Visual Grounding）模型，大多像是一个" 只会看图说话 "的愣头青。它们盯着当前的这一帧画面，试图从 像素 里找答案。一旦指令模糊， 或者目标被遮挡，它们就很容易"指鹿为马"，甚至引发错误推理。 人类司机为什么不会弄错？因为我们会" 预判 "。 当我们听到指令时，大脑里会瞬间推演未来的画面：左边那辆车马上要转弯了，不符合"跟着"的语境；只有中间那辆车在加速直行，才是最可能的意图。 "在行动之前，先思考未来"。 受此启发，来自[澳门大学]的研究团队提出了全新的框架 ThinkDeeper。这是首个将世界模型（World Model）引入自动驾驶视觉定位的研究。这项工作不仅刷 ...

Core Viewpoint - The article introduces a new course titled "World Models and Autonomous Driving Small Class," focusing on advanced algorithms in the field of autonomous driving, including general world models, video generation, and OCC generation [1][3]. Course Overview - The course is developed in collaboration with industry leaders and follows the success of a previous course on end-to-end and VLA autonomous driving [1]. - The course aims to enhance understanding and practical skills in world models, which are crucial for the advancement of autonomous driving technology [11]. Course Structure Chapter 1: Introduction to World Models - This chapter covers the relationship between world models and end-to-end autonomous driving, the history of world models, and current application cases [6]. - It discusses various types of world models, including pure simulation, simulation plus planning, and generating sensor inputs and perception results [6]. Chapter 2: Background Knowledge of World Models - The second chapter focuses on foundational knowledge related to world models, including scene representation, Transformer technology, and BEV perception [6][12]. - It highlights key technical terms frequently encountered in job interviews related to world models [7]. Chapter 3: Discussion on General World Models - This chapter addresses popular general world models and recent trends in autonomous driving jobs, including models from Li Feifei's team and DeepMind [7]. - It provides insights into the core technologies and design philosophies behind these models [7]. Chapter 4: Video Generation-Based World Models - The fourth chapter focuses on video generation algorithms, showcasing significant works such as GAIA-1 & GAIA-2 and recent advancements from various institutions [8]. - It includes practical applications using open-source projects like OpenDWM [8]. Chapter 5: OCC-Based World Models - This chapter explores OCC generation algorithms, discussing three major papers and a practical project that extends to vehicle trajectory planning [9]. Chapter 6: World Model Job Topics - The final chapter shares practical experiences from the instructor's career, addressing industry applications, pain points, and interview preparation for related positions [10]. Target Audience and Learning Outcomes - The course is designed for individuals aiming to deepen their understanding of end-to-end autonomous driving and world models [11]. - Upon completion, participants are expected to achieve a level equivalent to one year of experience as a world model autonomous driving algorithm engineer, mastering key technologies and being able to apply learned concepts in projects [14].