Legal & Compliance - Nvidia 将面临一位工程师泄露自动驾驶商业机密案件的审判，该工程师被指控从前雇主处窃取了这些机密 [1]

Core Insights - The article emphasizes the importance of accurately predicting the motion of road agents for the safety of autonomous driving, introducing a reward-driven intent reasoning mechanism to enhance trajectory prediction reliability and interpretability [3][5][10]. Summary by Sections Introduction - Trajectory prediction is a critical component of advanced autonomous driving systems, linking upstream perception with downstream planning modules. Current data-driven models often lack sufficient consideration of driving behavior, limiting their interpretability and reliability [5][10]. Methodology - The proposed method adopts a "reasoning first, then predict" strategy, where intent reasoning provides prior guidance for accurate and reliable multimodal motion prediction. The framework is structured as a Markov Decision Process (MDP) to model agent behavior [8][10][12]. - A reward-driven intent reasoning mechanism is introduced, utilizing Maximum Entropy Inverse Reinforcement Learning (MaxEnt IRL) to learn agent-specific reward distributions from demonstrations and relevant driving environments [8][9][10]. - A new query-centered IRL framework, QIRL, is developed to efficiently aggregate contextual features into a structured representation, enhancing the overall prediction performance [9][10][18]. Experiments and Results - The proposed method, referred to as FiM, is evaluated on large-scale public datasets such as Argoverse and nuScenes, demonstrating competitive performance against state-of-the-art models [28][30][32]. - In the Argoverse 1 dataset, FiM achieved a minimum average displacement error (minADE) of 0.8296 and a minimum final displacement error (minFDE) of 1.2048, outperforming several leading models [32][33]. - The results indicate that the intent reasoning module significantly enhances prediction confidence and reliability, confirming the effectiveness of the proposed framework in addressing complex motion prediction challenges [34][36]. Conclusion - The work redefines the trajectory prediction task from a planning perspective, highlighting the critical role of intent reasoning in motion prediction. The proposed framework establishes a promising baseline for future research in trajectory prediction [47].

Summary of Horizon Robotics Conference Call Company Overview - **Company**: Horizon Robotics (9660.HK) - **Industry**: Autonomous Driving Technology Key Financial Highlights - **1H25 Revenue**: Rmb1.6 billion, representing a **68% YoY increase** and **8% HoH increase**, exceeding estimates by **6%** and **9%** respectively [1][3] - **Gross Margin**: 65.1% in 1H25, consistent with expectations [3] - **Operating Loss**: Rmb1.855 billion in 1H25, higher than the estimated loss of Rmb1.412 billion due to increased cloud service fees [3][7] - **Net Loss**: Rmb5.233 billion in 1H25, significantly worse than the expected loss of Rmb1.4 billion [3][7] Product Development and Market Strategy - **Mass Production Plans**: The company plans to start mass production of the Horizon Robotics SuperDrive (HSD) on the Journey 6P platform in **2H25**, targeting urban NOA features in vehicles [1][2] - **Product Mix Upgrade**: Anticipated ramp-up of HSD and J6P platform in **2026**, with expectations for higher dollar content per vehicle due to increased ASP [2] - **Urban NOA Penetration**: The HSD solution is expected to penetrate lower-priced car models, enhancing the product mix towards higher-end integrated solutions [1][2] Market Performance and Future Outlook - **Highway NOA Shipments**: Shipments of highway NOA-capable products reached **0.98 million** in 1H25, accounting for **50%** of total shipments, contributing to improved blended ASP [1] - **Revenue Projections**: Revenue estimates for 2025E revised up to Rmb3.605 billion, reflecting a **1% increase** from previous estimates [8][16] - **Target Price**: The 12-month target price is set at **HK$14.00**, indicating a potential upside of **76.3%** from the current price of **HK$7.94** [16] Risks and Challenges - **Competitive Landscape**: Risks include increased competition and pricing pressure in the auto supply chain amid slow demand [15] - **Product Mix Transition**: Potential delays in the transition towards advanced driver-assistance systems (ADAS) could impact growth [15] - **Supply Chain Vulnerabilities**: Geopolitical tensions may pose supply chain risks [15] Conclusion - Horizon Robotics is positioned for growth with strong revenue increases driven by product innovation and market expansion. However, the company faces significant challenges, including operational losses and external market pressures. The outlook remains positive with a maintained "Buy" rating based on anticipated product advancements and market penetration strategies.

Group 1 - The event showcased various technological innovations aimed at enhancing the experience of the upcoming sports event, including autonomous vehicles and smart assistive devices [1][2] - The Hong Kong University of Science and Technology introduced micro-nano cooling technology that can reduce surface temperatures by at least 15 degrees Celsius, and indoor navigation technology has been implemented for audience convenience [2] - Technologies such as L4 autonomous driving for athlete and audience transport, smart inspection robots, and AI-driven sports systems were highlighted as part of the event's operational support [2][3] Group 2 - Health technology plays a crucial role in the event, with exoskeleton devices designed for athlete rehabilitation and wellness solutions like ultrasonic medicine baths and sleep aid sofas being presented [3] - The integration of innovative technologies aims to create a superior competition environment for athletes and a more convenient viewing experience for spectators [3]

Core Insights - The article introduces a novel "perception-in-plan" paradigm for end-to-end autonomous driving, implemented in the VeteranAD framework, which integrates perception directly into the planning process, enhancing the effectiveness of planning optimization [5][39]. - VeteranAD demonstrates superior performance on challenging benchmarks, NAVSIM and Bench2Drive, showcasing the benefits of tightly coupling perception and planning for improved accuracy and safety in autonomous driving [12][39]. Summary by Sections Introduction - The article discusses significant advancements in end-to-end autonomous driving, emphasizing the need to unify multiple tasks within a single framework to prevent information loss across stages [2][3]. Proposed Framework - VeteranAD framework is designed to embed perception into planning, allowing the perception module to operate more effectively in alignment with planning needs [5][6]. - The framework consists of two core modules: Planning-Aware Holistic Perception and Localized Autoregressive Trajectory Planning, which work together to enhance the performance of end-to-end planning tasks [12][39]. Core Modules - **Planning-Aware Holistic Perception**: This module interacts across three dimensions—image features, BEV features, and surrounding traffic features—to achieve a comprehensive understanding of traffic elements [6]. - **Localized Autoregressive Trajectory Planning**: This module generates future trajectories in an autoregressive manner, progressively refining the planned trajectory based on perception results [6][16]. Experimental Results - VeteranAD achieved a PDM Score of 90.2 on the NAVSIM navtest dataset, outperforming previous learning methods and demonstrating its effectiveness in end-to-end planning [21]. - In open-loop evaluations, VeteranAD recorded an average L2 error of 0.60, surpassing all baseline methods, while maintaining competitive performance in closed-loop evaluations [25][33]. Ablation Studies - Ablation studies indicate that the use of guiding points from anchored trajectories is crucial for accurate planning, as removing these points significantly degrades performance [26]. - The combination of both core modules results in enhanced performance, highlighting their complementary nature [26]. Conclusion - The article concludes that the "perception-in-plan" design significantly improves end-to-end planning accuracy and safety, paving the way for future research in more efficient and reliable autonomous driving systems [39].

Core Insights - WeRide has launched WePilot AiDrive, a one-stage end-to-end ADAS solution, in collaboration with Bosch, marking a significant advancement in autonomous driving technology [1][5] - The new system integrates sensing and decision-making into a single architecture, enhancing response times and operational efficiency [2][5] Product Features - WePilot AiDrive is designed to handle complex driving scenarios, including lane changes in heavy traffic, detours around construction, and interactions with pedestrians [4] - The system offers three main advantages: scalable computing power, adaptability across sensor setups, and rapid daily iteration using extensive driving data [4] Market Position - WeRide is recognized as a leader in the autonomous driving industry, being the first publicly traded Robotaxi company and having tested vehicles in over 30 cities across 10 countries [6] - The company has received autonomous driving permits in six markets, including China and the US, showcasing its regulatory compliance and market reach [6]

作者 | Sakura 编辑 | 自动驾驶之心 原文链接： https://zhuanlan.zhihu.com/p/716867464 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 VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions 来源 ECCV 2024 开源数据集 在这项工作中，我们提出了一种新方法，该方法还结合了来自环视摄像头的视觉输入，使模型能够利用视觉线索，如人类的凝视和手势、道路状况、车辆转向信号 等，这些线索在现有方法中通常对模型隐藏。此外，我们使用视觉语言模型（VLM）生成并由大型语言模型（LLM）细化的文本描述作为训练期间的监督，以指 导模型从输入数据中学习特征。尽管使用了这些额外的输入，但我们的方法实现了53毫秒的延迟，使其可用于实时处理，这比之前具有类似性能的单代理预测方法 快得多。 我们的实验表明，视觉输入和文本描述都有助于提高 ...

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 近年来，以LLM、VLM和VLA为代表的基础模型在自动驾驶决策中扮演着越来越重要的角色，吸引了学术界和 工业界越来越多的关注。许多小伙伴们询问是否有系统的分类汇总。本文按照模型类别，对决策的基础模型进行 汇总，后续还将进一步梳理相关算法，并第一时间汇总至『自动驾驶之心知识星球』，欢迎大家一起学习交流~ 基于LLM的方法 基于LLM的方法主要是利用大模型的推理能力描述自动驾驶，输入自动驾驶和大模型结合的早期阶段，但仍然 值得学习~ Distilling Multi-modal Large Language Models for Autonomous Driving LearningFlow: Automated Policy Learning Workflow for Urban Driving with Large Language Models CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain ...

Group 1 - Yangquan City, located in Shanxi Province, has transformed from a coal-centric economy to a digital and intelligent mining hub, with 95.84% of its coal production now coming from advanced capacity [2][3] - The city has established 12 smart mines, utilizing 5G technology to enhance operational efficiency, resulting in a 50% reduction in underground personnel and a 50% increase in efficiency [3] - Yangquan has become the first city in China to fully open up for autonomous driving, implementing smart traffic management systems that have reduced average vehicle delay rates by 45% and parking frequency by 70% [5] Group 2 - The local government has prioritized the development of the digital economy, establishing platforms such as the China Electric Digital Economy Industrial Park and "Jinchuan Valley·Yangquan," which have accelerated the growth of industries like smart terminals, data security, and big data [7] - In 2024, the core revenue of Yangquan's digital economy is projected to grow by 13.3%, and the city has been recognized as one of the "Top 100 New Smart Cities in China" for 2023-2024 [7]

Core Viewpoint - The article emphasizes the recent advancements in autonomous driving research, highlighting various innovative approaches and frameworks that enhance the capabilities of autonomous systems in dynamic environments [2][4]. Group 1: End-to-End Autonomous Driving - The article discusses several notable papers focusing on end-to-end autonomous driving, including GMF-Drive, ME³-BEV, SpaRC-AD, IRL-VLA, and EvaDrive, which utilize advanced techniques such as gated fusion, deep reinforcement learning, and evolutionary adversarial strategies [8][10]. Group 2: Perception and VLM - The VISTA paper introduces a vision-language model for predicting driver attention in dynamic environments, showcasing the integration of visual and language processing for improved situational awareness [7]. - The article also mentions the development of safety-critical perception technologies, such as the progressive BEV perception survey and the CBDES MoE model for functional module decoupling [10]. Group 3: Simulation Testing - The article highlights the ReconDreamer-RL framework, which enhances reinforcement learning through diffusion-based scene reconstruction, indicating a trend towards more sophisticated simulation testing methodologies [11]. Group 4: Datasets - The STRIDE-QA dataset is introduced as a large-scale visual question answering resource aimed at spatiotemporal reasoning in urban driving scenarios, reflecting the growing need for comprehensive datasets in autonomous driving research [12].