Wenchao Ding

Wenchao Ding | 丁文超

I am a tenure-track associate professor at the Academy for Engineering and Technology (FAET), Fudan University. I am looking for self-motivated students who are interested in physicial AI (robotics, embodied intelligence or autonomous driving).

From Sept. 2020 to Jan. 2023, I was a research scientist and technical lead at Autonomous Driving Solution (ADS), Huawei, where I led a team working on cutting-edge prediction and decision-making problems for autonomous vehicles. At Huawei, I am honored to be one of the Huawei TopMinds (天才少年). I was one of the core contributors to the comprehensive product-level prediction solution (incl. urban and highway env.) in ADS.

Before joining ADS, I received my PhD from the Hong Kong University of Science and Technology in 2020, where I was supervised by Prof. Shaojie Shen, and worked in HKUST Aerial Robotics Group.

Email / Google Scholar / Group Website

Research

I'm interested in AI for robotics, especially the application in physicial AI (embodied AI/autonomous driving). Much of my research is about learning general decision intelligence for physicial AI. Unlike extensive literature which remains in simulation or datasets, many of my methods are deployed on real physicial robots.

Journal papers

	VINGS-Mono: Visual-Inertial Gaussian Splatting Monocular SLAM in Large Scenes Ke Wu, Zicheng Zhang, Muer Tie, Ziqing Ai, Wenchao Ding^⁎ Arxiv, 2025 paper/ project page Lightweight online implicit SLAM for super large scenes.
	Drive in Corridors: Enhancing the Safety of End-to-end Autonomous Driving via Corridor Learning and Planning Zhiwei Zhang, Ruichen Yang, Ke Wu, Zijun Xu, Jingchu Liu, Lisen Mu, Zhongxue Gan, Wenchao Ding^⁎ Arxiv, 2025 paper Learning safe end-to-end policy for physicial AI.
	HGS-Mapping: Online Dense Mapping Using Hybrid Gaussian Representation in Urban Scenes Ke Wu, Kaizhao Zhang, Zhiwei Zhang, Muer Tie, Shanshuai Yuan, Jieru Zhao, Zhongxue Gan, Wenchao Ding^⁎ IEEE Robotics and Automation Letters (RA-L), 2024 paper Online implicit dense mapping for large scenes.
	Traffic Flow-Based Crowdsourced Mapping in Complex Urban Scenario Tong Qin, Haihui Huang, Ziqiang Wang, Tongqing Chen, Wenchao Ding^⁎ IEEE Robotics and Automation Letters (RA-L), 2023 paper / video Crowdsourced semantic mapping for mapless autonomous driving.
	EPSILON: An Efficient Planning System for Automated Vehicles in Highly Interactive Environments Wenchao Ding^⁎, Lu Zhang^⁎, Jing Chen, Shaojie Shen (^⁎ equal contribution) IEEE Transactions on Robotics (TRO), 2021 paper / video / code EPSILON enables human-like autonomous driving in real-world dense city traffic by effectively modeling social interaction with other human drivers.
	An Efficient B-spline-Based Kinodynamic Replanning Framework for Quadrotors Wenchao Ding, Wenliang Gao, Kaixuan Wang, Shaojie Shen IEEE Transactions on Robotics (TRO), 2019 paper / video Enabling efficient replanning for quadrotors in real-world cluttered environments by properly using B-spline properties.
	Safe Trajectory Generation For Complex Urban Environments Using Spatio-temporal Semantic Corridor Wenchao Ding^⁎, Lu Zhang^⁎, Jing Chen, Shaojie Shen (^⁎ equal contribution) IEEE Robotics and Automation Letters (RA-L), 2019 paper / video / code Safe trajectory generation in convex corridors with safety guarantee.
	Autonomous Aerial Robot Using Dual-fisheye Cameras Wenliang Gao, Kaixuan Wang, Wenchao Ding^⁎ (Corresponding author), Fei Gao, Tong Qin, Shaojie Shen Journal of Field Robotics (JFR), 2020 paper Achieving spherical omnidirectional sensing coverage with a minimum sensor suite (two ultrawide field-of-view (FOV) fisheye cameras and a low-cost IMU).

Conference papers

	HGS-Planner: Hierarchical Planning Framework for Active Scene Reconstruction Using 3D Gaussian Splatting Zijun Xu, Rui Jin, Ke Wu, Yi Zhao, Zhiwei Zhang, Jieru Zhao, Fei Gao Zhongxue Gan, Wenchao Ding IEEE International Conference on Robotics and Automation (ICRA), 2025 paper Active perception and planning for indoor robot.
	O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation Muer Tie, Julong Wei, Ke Wu, Zhengjun Wang, Shanshuai Yuan, Kaizhao Zhang, Jie Jia, Jieru Zhao, Zhongxue Gan, Wenchao Ding European Conference on Computer Vision (ECCV), 2024 code / paper Integrating spatial temporal reasoning and implicit mapping.
	DeepPointMap2: Accurate and Robust LiDAR-Visual SLAM with Neural Descriptors Xiaze Zhang, Ziheng Ding, Qi Jing, Ying Cheng, Wenchao Ding^⁎, Rui Feng^⁎ ACM International Conference on Multimedia (ACM MM), 2024 paper Learning-based multimodal fusion and alignment.
	OpenAnnotate3D: Open-Vocabulary Auto-Labeling System for Multi-modal 3D Data Yijie Zhou, Likun Cai, Xianhui Cheng, Zhongxue Gan, Xiangyang Xue^⁎ Wenchao Ding^⁎, IEEE International Conference on Robotics and Automation (ICRA), 2024 code / paper Open-vocabulary auto-Labeling system for multi-modal 3D data
	DeepPointMap: Advancing LiDAR SLAM with Unified Neural Descriptors Xiaze Zhang, Ziheng Ding, Qi Jing, Yuejie Zhang, Wenchao Ding^⁎, Rui Feng^⁎ AAAI Conference on Artificial Intelligence (AAAI), 2024 code / paper Neural descriptors for next-gen SLAM.
	Swift-Mapping: Online Neural Implicit Dense Mapping in Urban Scenes Ke Wu, Kaizhao Zhang, Mingzhe Gao, Jieru Zhao, Zhongxue Gan^⁎, Wenchao Ding^⁎ AAAI Conference on Artificial Intelligence (AAAI), 2024 Code comming soon / Paper comming Neural implicit representation for next-gen SLAM.
	FlowMap: Path Generation for Automated Vehicles in Open Space Using Traffic Flow Wenchao Ding, Jieru Zhao, Yubin Chu, Tong Qin, Chunjing Xu, Yuxiang Guan, Zhongxue Gan IEEE International Conference on Robotics and Automation (ICRA), 2023 video / paper Online path planning for automated vehicles in open space for mapless autonomous driving.
	Learning to Predict Vehicle Trajectories with Model-based Planning Haoran Song, Di Luan, Wenchao Ding, Michael Yu Wang, Qifeng Chen Conference on Robot Learning (CoRL), 2021 project page / paper Make accurate, feasible, and robust trajectory prediction by a novel architecture with a model-based generator and a learning-based evaluator.
	PiP: Planning-informed Trajectory Prediction for Autonomous Driving Haoran Song, Wenchao Ding, Yuxuan Chen, Shaojie Shen, Michael Yu Wang, Qifeng Chen European Conference on Computer Vision (ECCV), 2020 project page / paper Inform the multi-agent future prediction with ego vehicle's planning in a novel planning-prediction-coupled pipeline.
	Efficient Uncertainty-aware Decision-making for Autonomous Vehicles Using Guided Branching Lu Zhang^⁎, Wenchao Ding^⁎, Jing Chen, Shaojie Shen (^⁎ equal contribution) IEEE International Conference on Robotics and Automation (ICRA), 2020 paper / video / code Capable of modeling uncertainties while being much more efficient than POMDP.
	Predicting Vehicle Behaviors Over an Extended Horizon Using Behavior Interaction Network Wenchao Ding, Jing Chen, Shaojie Shen IEEE International Conference on Robotics and Automation (ICRA), 2019 paper / video Learning social interaction among vehicles for long-term intention prediction.