Group 1 - The core viewpoint of the article highlights that Pony.ai (PONY.US) has seen a pre-market increase of 1.55%, reaching a price of $14.42, due to the nearing production readiness of the fourth-generation autonomous heavy truck developed in collaboration with SANY Heavy Truck, with the first batch set for commercial operation next year [1]. Group 2 - The closing price of Pony.ai on December 9 was $14.20, with a slight decrease of 0.14% [1]. - The pre-market price on December 10 was $14.42, reflecting an increase of $0.22 [1]. - The stock's highest price during the trading session was $14.215, while the opening price was $13.830 [1]. - The trading volume was approximately 3.1786 million shares, with a total transaction value of about $44.4971 million [1]. - The company's total market capitalization stands at $6.156 billion, with a total share count of 434 million [1]. - The stock has a 52-week high of $24.92 and a low of $4.11, indicating significant volatility [1].

Core Insights - The current ride-hailing services account for only 1% of the annual driving mileage in the U.S., which is approximately 3 trillion miles, highlighting a significant growth opportunity for tech giants like Tesla, Google, and Amazon in the autonomous vehicle market [1][5][18] - If autonomous driving technology can reduce the cost per mile to $1.5-$2.0, the market size could reach $0.9-$1.2 trillion within 15 years, assuming a 20% penetration rate [1][8] - The cost per mile for current ride-hailing services is around $2.5-$3.0, while private car ownership costs range from $0.70 to $1.06, indicating a substantial price gap that limits the adoption of ride-hailing services [1][6][7] Market Potential - The U.S. total driving mileage is projected to be about 3.3 trillion miles by July 2025, with passenger vehicles accounting for approximately 3 trillion miles after excluding large trucks [2] - In 2024, ride-hailing mileage is expected to remain at only 1% of the total, based on assumptions regarding Uber and Lyft's order distribution and average trip length [5][6] Cost Structure and Profitability - The average cost per mile for private car ownership is significantly lower than that of ride-hailing services, which creates a barrier for consumer adoption [6][7] - A critical threshold for the widespread adoption of autonomous ride-hailing is achieving a cost per mile below $2.00 [7][8] - The report analyzes three business models: ownership, leasing, and agency, detailing the break-even points for each model under various cost scenarios [11][13][15][16] Business Model Analysis - In the ownership model, a cost of $1.95 per mile is needed to maintain a 10% profit margin, assuming a vehicle cost of $75,000 [13] - The leasing model requires a pricing of $2.08 per mile to achieve the same profit margin, with a baseline leasing fee of $0.54 per mile [15] - The agency model necessitates a price of $2.15 per mile to sustain profitability, with a payout to vehicle owners of $1.5 per mile [16] Competitive Landscape - Uber currently holds a market share of 70%-80% in the U.S. ride-hailing market, with projections indicating that even if its share drops to 50%, its order volume could still grow to $589 billion by 2040 [18][21] - The entry of well-funded competitors like Waymo, Tesla, and Zoox poses a risk of market share erosion for Uber [18][27] - The report highlights the potential for a price war among major players, as they may leverage aggressive pricing strategies to capture market share [27] Future Outlook - The report suggests that despite competitive pressures, the ride-hailing industry benefits from significant network effects, which may limit the number of viable competitors and support sustainable profit margins [25] - Early data from California indicates that the presence of autonomous vehicles may expand the overall market rather than cannibalize existing services, as seen with Waymo's growth [26]

Core Viewpoint - The company has made significant advancements in L4 autonomous driving technology, focusing on multi-scenario operational services and integrated vehicle-road-cloud solutions [1] Group 1: Technology Development - The company has accumulated years of technology in the L4 autonomous driving field, demonstrating capabilities in sensor fusion, decision planning, and redundant control [1] - The L4 system architecture has the potential to extend into the Robotaxi sector, particularly in areas such as computing platform, functional safety, and OTA upgrades [1] Group 2: Product Offerings - The company has launched several autonomous driving vehicles, including heavy-duty autonomous flatbed trucks, autonomous electric tractors (Robotruck), and autonomous electric minibuses (RoboBUS), as well as industrial autonomous vehicles (AGV) [1] Group 3: Operational Achievements - The company has achieved regular L4-level autonomous driving operations in closed campuses, demonstrating full autonomy [1] - Currently, there are no commercial partnerships in the RoboTaxi sector [1]

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]

在过去几年，自动驾驶圈流行一句话： 「大模 型会说话，但不会开 车。」 一方面，大规模视觉语言模型（VLM）在文本理解和逻辑推理上突飞猛进；另一方面，一旦把它们放到真实道路上，让它们处理长尾场景、远距离目标和复杂博 弈时，这些 "聪明大脑" 却常常犯低级错误：看不清、定位不准、反应不稳定。深层原因在于 —— 现有 VLM 在空间感知和几何理解上的能力，远远跟不上它们在 语义层面的 "表达能力" 。 为了让大模型真的能 "看懂世界"，在很多现有方案中，研究者会在训练中加入一些 "感知类 QA" 问题，比如问 "左前方有没有车""两车距离有多远"。但这类监督 更多停留在语义标签和粗略相对关系层面，并没有让模型真正学会可用于控制决策的强 2D/3D 感知能力 —— 例如精确、稳定的检测框、分割结果和 BEV 感知信 息。换句话说，今天很多 VLA 仍然停留在「会回答关于世界的问题」，而不是「真的看清这个世界」。这种 "弱感知的大模型"，显然不足以支撑自动驾驶和广义 具身智能对空间理解的高要求。 近日，来自引望智能与复旦大学的研究团队联合提出了一个面向自动驾驶的新一代大模型 ——Percept-WAM（Percept ...

格隆汇12月10日丨万马科技(300698.SZ)在投资者互动平台表示，目前无人驾驶行业正在步入商业化落 地阶段，对公司的车联网以及自动驾驶相关业务均有积极的影响。在Robotaxi领域，公司目前已与百度 阿波罗、哈啰、曹操出行等厂商达成合作。在Robovan领域，公司目前已与九识、智行者等厂商达成合 作。具体盈利情况需结合市场实际变化、公司经营策略等多种因素综合判断，公司将持续关注市场动 态，积极应对市场变化，努力提升盈利能力，敬请广大投资者注意风险，理性投资。 ...

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].