端到端作为这两年的量产关键词，是各家车企核心的招聘岗位。但市面上真正的量产人才少之又少，模型优化、场景优化、数据优化，再到下游的规划兜底，可以 说端到端是一个全栈的岗位。 从技术的成熟度和工业界的需求来看，端到端需要攻克的难题还有很多。导航信息的引入、强化学习调优、轨迹的建模及优化都有很多门道，目前也是量产第一 线。 为此我们花了三个月的时间设计了端到端量产进阶课程，从实战到落地层层展开。 该课程涉及的核心算法包括：一段式端到端、两段式端到端、导航信息的量产应用、开闭环强化学习、扩散模型+强化学习、自回归+强化学习、时空联合规划等 等，最后分享一些实际的量产经验。很多想进阶或者跳槽的同学苦于没有专家辅导，想转行但实际工作中无法接触到实际的量产优化，简历上往往不够亮眼，遇到 问题连个请教的人都没有。 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 这门课程是自动驾驶之心联合工业界算法专家开设的《面向量产的端到端实战小班课》！课程只有一个重点：聚焦量产。从一段式、两段式、强化学习、导航应 用、轨迹优化、兜底方案再到具体量产经验分享。面向就业直击落地，所以这门课 ...

Summary of Key Points from the Conference Call Industry Overview - The conference call discusses the autonomous driving (AD) industry, focusing on various companies and their technological advancements in the sector. Key Companies and Market Share - **Momenta** holds a leading position in the third-party autonomous driving market with a market share of 55%, while **Huawei** has a 25% share [1][3]. - **DJI** excels in low-computing power chip solutions but is shifting towards mid-to-high computing power solutions due to market demand [1][5]. - **Horizon Robotics** has developed self-researched hardware-software integrated solutions, currently in mass production with Chery's models, but faces challenges in NPU computing power and algorithm upgrades [1][6]. Technological Routes and Developments - The AD industry is divided into three main technological routes: 1. **End-to-End Algorithms**: Gaining traction since Tesla's AI Day in 2021, with companies like Momenta and Tesla implementing these algorithms in production vehicles [2]. 2. **Vision Language Action (VLA) Models**: Used by companies like Li Auto and XPeng, requiring high computing power (minimum 500 TOPS) and significant resources for training [2]. 3. **World Models**: Developed by companies like Huawei and Momenta, capable of understanding and predicting environmental changes [2]. Performance and Capabilities of Key Players - **Momenta** offers two product lines: a cost-effective single Orin X solution and a high-end dual Orin X solution, showcasing strong engineering capabilities [3]. - **DJI** has strong engineering capabilities but relatively weaker algorithm capabilities, allowing it to effectively implement complex algorithms in practical scenarios [3]. - **Horizon Robotics** is in the second tier of the industry, with its HSD and G6P series solutions providing decent user experience but needing more vehicle validation [6]. Market Trends and Shifts - The market is shifting from low-computing power chips to mid-to-high computing power solutions, prompting companies like DJI to develop new chip solutions [4][5]. - The demand for **fusion perception** routes combining Lidar and other sensors is expected to grow due to regulatory requirements and the need for handling complex scenarios [12]. Challenges and Future Outlook - The differences in autonomous driving capabilities among companies are primarily determined by data, computing power, and algorithms [8][9]. - Long-term, the accumulation of data will be crucial for competitive advantage, with a critical mass of road testing data needed to trigger significant improvements [10]. - The **Robot Taxi** market is seen as a positive growth area, with profitability dependent on vehicle efficiency, cost management, and competitive pricing [18][19]. Conclusion - Companies transitioning from L2+ to L4 levels of autonomous driving have a natural advantage due to lower resource investment and existing experience in mass production [20].

Group 1 - The article discusses the importance of the autumn recruitment season, highlighting a student's experience of receiving an offer from a tier 1 company but feeling unfulfilled due to a desire to transition to a more advanced algorithm position [1] - The article encourages perseverance and self-challenge, emphasizing that pushing oneself can reveal personal limits and potential [2] Group 2 - A significant learning package is introduced, including a 299 yuan discount card for a year of courses at a 30% discount, various course benefits, and hardware discounts [4][6] - The focus is on cutting-edge autonomous driving technologies for 2025, particularly end-to-end (E2E) and VLA autonomous driving systems, which are becoming central to the industry [7][8] Group 3 - The article outlines the development of end-to-end autonomous driving algorithms, emphasizing the need for knowledge in multimodal large models, BEV perception, reinforcement learning, and more [8] - It highlights the challenges faced by beginners in synthesizing knowledge from fragmented research papers and the lack of practical guidance in transitioning from theory to practice [8] Group 4 - The introduction of a new course on automated 4D annotation algorithms is aimed at addressing the increasing complexity of training data requirements for autonomous driving systems [11][12] - The course is designed to help students navigate the challenges of data annotation and improve the efficiency of data loops in autonomous driving [12] Group 5 - The article discusses the emergence of multimodal large models in autonomous driving, noting the rapid growth of job opportunities in this area and the need for a structured learning platform [14] - It emphasizes the importance of practical experience and project involvement for job seekers in the autonomous driving sector [21] Group 6 - The article mentions various specialized courses available, including those focused on perception, model deployment, planning control, and simulation in autonomous driving [16][18][20] - It highlights the importance of community engagement and support through dedicated VIP groups for course participants [26]

Core Viewpoint - The article emphasizes the importance of active safety technology in smart electric vehicles, highlighting Xiaopeng's advancements in this area to regain a competitive edge in the market [2][3][14]. Group 1: Active Safety Technology Developments - Xiaopeng has demonstrated its AEB (Automatic Emergency Braking) capabilities at speeds of up to 130 km/h in various challenging conditions, including night and wet roads [2][4]. - The company has redefined its active safety architecture and software, with daily updates to enhance performance and address market competition [2][3]. - Xiaopeng's AEB system is designed to operate effectively in a full speed range of 0-150 km/h, with a focus on real-world scenarios [4][5]. Group 2: Technical Innovations - Xiaopeng employs a "two-stage braking" strategy to enhance user comfort during emergency braking, initially applying a moderate deceleration before engaging full braking if necessary [5][6]. - The introduction of the AES (Automatic Emergency Steering) system allows vehicles to navigate around obstacles on slippery surfaces, utilizing a unique "single-side braking" technique [8][9]. - The company aims to tackle complex driving conditions, such as icy roads, to ensure stability and effective obstacle avoidance [9][10]. Group 3: Strategic Focus and Team Dynamics - Xiaopeng has established dedicated teams and "war rooms" to enhance collaboration and expedite the development of active safety features [15][16]. - The company has shifted its focus to prioritize active safety, responding to consumer demand for improved vehicle safety [14][18]. - The development process has been streamlined to ensure rapid iteration and effective communication among team members [16][17]. Group 4: Market Position and Future Goals - Xiaopeng's advancements in active safety are part of a broader strategy to maintain its leadership in the smart driving sector amid increasing competition [14][18]. - The ultimate goal of the active safety technology is to achieve "zero collisions" by expanding the coverage of AEB and AES systems [22][23]. - Future efforts will focus on enhancing scene coverage based on real-world collision data to prioritize high-frequency and high-severity scenarios [23][24].

Core Viewpoint - The article emphasizes the importance of understanding end-to-end (E2E) algorithms and Visual Language Models (VLA) in the context of autonomous driving, highlighting the rapid development and complexity of the technology stack involved [2][32]. Summary by Sections Introduction to End-to-End and VLA - The article discusses the evolution of large language models over the past five years, indicating a significant technological advancement in the field [2]. Technical Foundations - The Transformer architecture is introduced as a fundamental component for understanding large models, with a focus on attention mechanisms and multi-head attention [8][12]. - Tokenization methods such as BPE (Byte Pair Encoding) and positional encoding are explained as essential for processing sequences in models [13][9]. Course Overview - A new course titled "End-to-End and VLA Autonomous Driving" is launched, aimed at providing a comprehensive understanding of the technology stack and practical applications in autonomous driving [21][33]. - The course is structured into five chapters, covering topics from basic E2E algorithms to advanced VLA methods, including practical assignments [36][48]. Key Learning Objectives - The course aims to equip participants with the ability to classify research papers, extract innovative points, and develop their own research frameworks [34]. - Emphasis is placed on the integration of theory and practice, ensuring that learners can apply their knowledge effectively [35]. Industry Demand and Career Opportunities - The demand for VLA/VLM algorithm experts is highlighted, with salary ranges between 40K to 70K for positions requiring 3-5 years of experience [29]. - The course is positioned as a pathway for individuals looking to transition into roles focused on autonomous driving algorithms, particularly in the context of emerging technologies [28].

Core Viewpoint - Leap Motor reported strong financial results for the first half of 2025, achieving revenue of 24.25 billion yuan, a year-on-year increase of 174%, and becoming the second Chinese new energy vehicle manufacturer to achieve half-year profitability [1] Financial Performance - The company's gross margin reached a historical high of 14.1%, with net profit attributable to shareholders at 30 million yuan, and adjusted net profit at 330 million yuan [1] - The actual net profit for Q2 2025 exceeded market expectations by 115 million yuan, with a reported net profit of 163 million yuan [1] - Operating cash flow generated during the period was 2.86 billion yuan, with cash reserves amounting to 29.58 billion yuan [6] Sales and Market Position - Leap Motor delivered approximately 222,000 vehicles in the first half of 2025, marking a year-on-year growth of 155.7%, leading the new energy vehicle sector in terms of delivery volume [1] - The company achieved a record monthly delivery of 50,129 vehicles in July 2025, maintaining its position as the top-selling new energy vehicle brand in China [4] - The B series and C series models have been well-received, with the C10 and C16 models leading sales in their respective categories [4] Product Strategy and Innovation - Leap Motor has adopted a high-end strategy, increasing the average selling price of its vehicles by 76% year-on-year, contrasting with the overall market trend of declining prices [5] - The company has invested heavily in R&D, with a nearly 100% increase in its autonomous driving team and computing resources [7] - The B10 model, launched in April 2025, features advanced technology and has quickly become a best-seller, achieving over 10,000 deliveries in its first month [8] International Expansion - Leap Motor exported 24,980 vehicles from January to July 2025, leading among new energy vehicle brands in China [9][12] - The company has established over 600 sales and service outlets across approximately 30 international markets, with plans to set up a local production base in Europe by the end of 2026 [12] - The stock performance has been strong, with a 125% increase in market value this year, and several investment banks have raised their target prices for the company [12]

Core Viewpoint - Leap Motor has achieved profitability in its mid-term results and has raised its annual net profit guidance to between RMB 500 million and RMB 1 billion, while also increasing its annual sales target to 580,000 to 650,000 units [1][2] Group 1: Financial Performance - In the first half of 2025, Leap Motor reported a net profit of RMB 30 million, with an adjusted net profit of RMB 330 million [1] - The company delivered 221,700 vehicles in the first half of 2025, marking a 155.7% increase compared to the same period in 2024 [1] - Revenue reached RMB 24.25 billion, a 174% increase year-on-year, with a gross margin of 14.1% [1] - The gross margin decreased from 14.9% in Q1 to below 14% in Q2 [1][2] Group 2: Sales and Production Goals - Leap Motor aims for a monthly sales target of 60,000 units in the next five months to meet its revised annual sales goal [2] - The company has completed sales of 271,800 units in the first seven months of the year, indicating a significant ramp-up in sales for the latter half of the year [2] - Leap Motor plans to challenge a sales target of 1 million units in the following year [2] Group 3: Strategic Initiatives - Leap Motor has initiated a strategic cooperation with China FAW to jointly develop new energy passenger vehicles and components [2] - The company has exported 24,980 vehicles in the first seven months, with strong performance in the European market [2] - Leap Motor plans to establish a localized production base in Europe by the end of 2026 to enhance its global market presence and optimize cost structure [2]

Core Viewpoint - The article emphasizes the evolving landscape of autonomous driving, particularly the integration of traditional planning and control (PnC) with end-to-end systems, highlighting the necessity for professionals to adapt to these changes in order to remain competitive in the job market [2][4][29]. Group 1: Industry Trends - The shift towards end-to-end and VLA (Vision-Language Alignment) systems is impacting traditional PnC roles, which are now required to incorporate more advanced algorithms and frameworks [2][4]. - As of 2025, end-to-end systems are expected to become more prevalent, yet traditional PnC methods will still play a crucial role, especially in safety-critical applications like Level 4 autonomous driving [4][29]. - The article discusses the importance of understanding both traditional and modern approaches to planning and control, as they are increasingly being integrated in practical applications [4][29]. Group 2: Educational Offerings - The company has launched specialized courses aimed at bridging the gap between theoretical knowledge and practical application in the field of autonomous driving, focusing on real-world challenges and interview preparation [5][7]. - The courses are designed to provide hands-on experience with current industry practices, including classic and innovative solutions in PnC, and are tailored for individuals with some background in the field [8][12]. - The curriculum includes modules on foundational algorithms, decision-making frameworks, and advanced topics such as contingency planning and interactive planning, which are critical for modern autonomous driving systems [20][21][24][26][29]. Group 3: Career Development - The courses not only focus on technical skills but also offer support in job application processes, including resume reviews and mock interviews, to enhance employability [9][10][31]. - Previous participants have successfully secured positions at major companies in the autonomous driving sector, indicating the effectiveness of the training provided [10][12]. - The program aims to equip participants with the skills necessary to construct decision-making systems and address real-world challenges in autonomous driving, thereby enhancing their career prospects [13][29].

Core Viewpoint - The article discusses the impact of end-to-end autonomous driving technology on traditional rule-based control (PNC) methods, highlighting the shift towards data-driven approaches and the complementary relationship between the two systems [2][6]. Summary by Sections Differences Between Approaches - Traditional PNC relies on manually coded rules and logic for vehicle planning and control, utilizing algorithms like PID, LQR, and various path planning methods. Its advantages include clear algorithms and strong interpretability, suitable for stable applications [4]. - End-to-end algorithms aim to directly map raw sensor data to control commands, reducing system complexity and enabling the model to learn human driving behavior through large-scale data training. This approach allows for joint optimization of the entire driving process [4]. Advantages and Disadvantages - **End-to-End Approach**: - Advantages include reduced system complexity, natural driving style emulation, and minimized information loss between modules [4]. - Disadvantages involve challenges in traceability of decision processes, high data scale requirements, and the need for rule-based fallback in extreme scenarios [4]. - **PNC Approach**: - Advantages include clear module functions, ease of debugging, and stable performance in known scenarios, making it suitable for high safety requirements [5]. - Disadvantages consist of high development costs and potential difficulties in handling complex scenarios without suitable rules [5]. Complementary Relationship - The analysis indicates that end-to-end systems require PNC for certain scenarios, while PNC can benefit from the efficiencies of end-to-end approaches. This suggests a complementary rather than adversarial relationship between the two methodologies [6]. Job Opportunities - The article highlights job openings in both end-to-end and traditional PNC roles, indicating a demand for skilled professionals in these areas with competitive salaries ranging from 30k to 100k per month depending on the position and location [8][10][12][14].

Core Insights - The article discusses the results of the 2025 Waymo Open Dataset End-to-End Driving Challenge, highlighting the advancements in end-to-end autonomous driving systems and the shift towards using large-scale public datasets for training models [2][18]. Group 1: Competition Results - The champion of the competition was the EPFL team, which utilized the DiffusionDrive model, nuPlan data, and an ensembling strategy [1]. - The runner-up was a collaboration between Nvidia and Tubingen teams, which also referenced DiffusionDrive and SmartRefine, employing multiple datasets to demonstrate the importance of training data quality [1][22]. - The third place was secured by Hanyang University from South Korea, which focused on a simplified structure using only front-view input and vehicle state [1][3]. Group 2: Methodology - The UniPlan framework was introduced, leveraging large-scale public driving datasets to enhance generalization in rare long-tail scenarios, achieving competitive results without relying on expensive multimodal large language models [3][18]. - The model architecture is based on DiffusionDrive, which employs a truncated diffusion strategy for efficient and diverse trajectory generation [4][6]. - The diffusion decoder utilizes a cross-attention mechanism to refine trajectory predictions based on scene context [5][6]. Group 3: Data Processing - The nuPlan dataset was processed to create a diverse training set, resulting in 90,000 samples by applying a sliding window approach [7]. - A similar filtering strategy was used for the WOD-E2E dataset, generating 35,000 training samples and 10,000 validation samples [8]. - The model was trained on a powerful computing setup with four H100 GPUs, achieving significant training efficiency [10]. Group 4: Experimental Results - The performance was evaluated using Rater Feedback Score (RFS) and Average Displacement Error (ADE), with various configurations tested [12][17]. - The results indicated that the combined training of WOD-E2E and nuPlan datasets led to slight improvements in average RFS, particularly in long-tail categories [23]. - The analysis showed that while additional datasets generally provide benefits, the quality of the data sources is more critical than quantity [39]. Group 5: Conclusion - The article emphasizes the potential of data-centric approaches in enhancing the robustness of autonomous driving systems, as demonstrated by the competitive results achieved with the UniPlan framework [18][39].