论文链接:https://openaccess.thecvf.com/content/CVPR2024/papers/Shao_LMDrive_Closed-Loop_End-to-End_Driving_with_Large_Language_Models_CVPR_2024_paper.pdf 一、方法 尽管在自动驾驶领域取得了显著的进展,但现代方法在面对长尾未预见事件和挑战性城市场景时仍然存在严重事故的风险。一方面,大型语言模型(LLM)...
[CVPR 2024] LMDrive: Closed-Loop End-to-End Driving with Large Language Models Resources Readme License Apache-2.0 license Activity Custom properties Stars 736 stars Watchers 16 watching Forks 63 forks Report repository Releases No releases published Packages No packages published Cont...
师从李鸿升教授和王晓刚教授,研究方向为端到端自动驾驶,多模态大语言模型,视频理解;曾在CVPR、CoRL、NeurIPS、RSS等顶级会议发表多篇论文;曾获2022年度CARLA端到端自动驾驶挑战赛冠军(sensor track),2020年度ActivityNet挑战赛冠军等。 课程提纲 端到端闭环自动驾驶概述 ...
He won as PI the CVPR 2023 Best Paper Award, and proposed BEVFormer that is renowned for 3D object detection baseline and won the Top 100 AI Papers in 2022. 个人主页: https://opendrivelab.com/ 报告摘要: We present DriveLM, a new task, dataset, metrics, and baseline for end-to-end ...
🏁DriveLMserves as a main track in theCVPR 2024 Autonomous Driving Challenge. Everything you need for the challenge isHERE, including baseline, test data and submission format and evaluation pipeline! News [2025/01/08]Drive-Benchrelease! In-depth analysis in what are DriveLM really benchmarkin...
香港中文大学MMLab在读博士生。师从李鸿升教授和王晓刚教授,研究方向为端到端自动驾驶,多模态大语言模型,视频理解等;曾在CVPR、CoRL、NeurIPS、RSS等顶级会议发表多篇论文;曾获2022年度CARLA端到端自动驾驶挑战赛冠军(sensor track),2020年度ActivityNet挑战赛冠军等。
本期Talk的嘉宾是邵昊,他是香港中文大学的博士生。他的研究领域涵盖了端到端的自动驾驶、多模态大语言模型和视频理解等前沿技术。邵昊在CVPR、CoRL等顶级会议上发表过多篇论文,并在多个竞赛中获得佳绩。其中包括在2022年CARLA端到端自动驾驶挑战赛中摘得桂冠,这无疑证明了他在这一领域的深厚实力。
邵昊,香港中文大学MMLab在读博士;师从李鸿升教授和王晓刚教授,研究方向为端到端自动驾驶,多模态大语言模型,视频理解;曾在CVPR、CoRL、NeurIPS、RSS等顶级会议发表多篇论文;曾获2022年度CARLA端到端自动驾驶挑战赛冠军(sensor track),2020年度ActivityNet挑战赛冠军等。
He won as PI the CVPR 2023 Best Paper Award, and proposed BEVFormer that is renowned for 3D object detection baseline and won the Top 100 AI Papers in 2022. 个人主页: https://opendrivelab.com/ 报告摘要: We present DriveLM, a new task, dataset, metrics, and baseline for end-to-end ...