作者 | 大懒货 来源 | https://weibo.com/2062985282/Q0LWSft0j 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 根据目前短暂本地体验，并对比了和E2E+VLM的差异 我认为是狭义的VLA 这里用几个场景差异来作证这个观点【如果觉得不对，那就是我错了~】 ①：VLA后具备了非常好【比较少漏报或者虚惊】情况下的防御性驾驶，即在无遮挡的十字路口会开的比较快且稳健；在有遮挡的、视野不佳的路口会出现明显的基于可 行驶剩余距离丝滑减速的防御性驾驶。 >>自动驾驶前沿信息获取 → 自动驾驶之心知识星球 以下为原文：写一点 #理想mindvla让每个人都有专职司机# 到底是不是 真的VLA❓ 或者更加收敛一点： 是不是机器人领域 基于一个大语言模型LLM作为主干网络，串行的神经网络实现：多模态信息整合编码【包含但不限于视觉、激光雷达、语言、地图、定位】后，基于大 语言模型整合后输出决策并将决策转换成轨迹后再转换成控制细节❓ 这类狭义的VLA 而过去E2E模型很难学会这种丝滑的减速，加上了VLM模块是可以实现特定场景，例如丁字路口的 ...

Investment Rating - The report emphasizes the importance of 3D data assets and physical simulation engines, indicating a positive outlook on China's physical AI as a scarce asset [3]. Core Insights - The report outlines the five stages of biological intelligence and maps them to embodied intelligence, highlighting that the current missing elements are simulation and planning capabilities [4][10]. - It discusses the evolution of intelligent driving algorithms and their relevance to understanding the development of embodied intelligence models, noting that many core teams in humanoid robotics have extensive experience in the intelligent driving sector [39][41]. - The report identifies the need for physical AI to facilitate real-world interactions for robots, contrasting this with intelligent driving, which inherently avoids physical interactions [4][41]. Summary by Sections 1. Mapping Biological Intelligence to Embodied Intelligence - The report details the five stages of biological intelligence, emphasizing that the current stage of humanoid robots is still early, with a significant gap in simulation learning capabilities [10][35]. - It highlights the importance of understanding the evolutionary history of biological intelligence to inform the development of embodied intelligence [10]. 2. Intelligent Driving and Its Implications - The report reviews the history of intelligent driving algorithms, concluding that the architecture has evolved from 2D images to 3D spatial understanding, which is crucial for developing initial spatial intelligence [39]. - It notes that the transition from traditional algorithms to model-based reinforcement learning is essential for both intelligent driving and humanoid robotics, affecting their usability [39][41]. 3. The Role of Physical AI - The report emphasizes that physical AI is critical for enabling robots to interact with the physical world, addressing the challenges of data scarcity in the robotics industry [4][10]. - It contrasts the requirements for physical interaction in humanoid robots with the goals of intelligent driving, which focuses on avoiding physical collisions [41].

Investment Rating - The report rates the industry as "Outperform" [1] Core Insights - The report emphasizes that advanced intelligent driving is expected to be the first application of physical AI, driven by rapid technological iterations, competitive strategies from Chinese automakers, and supportive regulatory policies [1][5][35] - The report identifies that the current focus of competition among automakers has shifted from the number of cities where autonomous driving is available to achieving nationwide coverage and from basic functionalities to more advanced features like parking assistance [1][20] - The report highlights that the penetration of L2+ intelligent driving functions is increasing, with expectations for significant growth in urban NOA (Navigation on Autopilot) capabilities in the coming years [1][23][35] Summary by Sections Industry Overview - Intelligent driving is positioned as the first scenario for physical AI implementation, with the potential to provide significant societal benefits such as reducing accidents and improving traffic efficiency [18][19] - The report notes that the penetration rate of L2+ intelligent driving functions in China is projected to reach 57.4% by 2024, with L3 level vehicles expected to be commercially available soon [13][35] Technological Developments - The report discusses a paradigm shift in intelligent driving technology from rule-based to data-driven and knowledge-driven approaches, enhancing the performance and safety of autonomous systems [36][37] - It highlights the transition from modular architectures to end-to-end architectures, which optimize data flow and reduce information loss, thus improving the overall efficiency of intelligent driving systems [36][46] Competitive Landscape - The report indicates that competition among automakers is intensifying, with companies like BYD pushing advanced driving features down to lower-priced models, thereby accelerating the adoption of high-level intelligent driving [1][35] - It also mentions that regulatory support is crucial for the commercial rollout of L3 and L4 level autonomous vehicles, with various regions in China expanding pilot programs for these technologies [35][36] Investment Opportunities - The report suggests that companies involved in the supply chain for automotive components, particularly those focusing on SoC (System on Chip), sensors, and communication technologies, are likely to benefit from the increasing penetration of advanced intelligent driving [1][5][35] - Specific companies highlighted for potential investment include Horizon Robotics, Black Sesame Technologies, Rockchip, and others involved in the intelligent driving ecosystem [1][5]