Wenchao Ding (丁文超)

I am Wenchao Ding, a fourth-year Ph.D. student from the Electronic and Computer Engineering Department at Hong Kong University of Science and Technology, where I am advised by Prof. Shaojie Shen and working in the HKUST Aerial Robotics Group.


My main research interest lies in planning. During my first year into robotics, I mainly worked on planning problems for macro aerial robots such as quadrotors. I loved developing methods which are elegantly formulated and at the same time have practical impacts.


After that, I devoted to the field of autonomous driving. I solved several interesting problems in prediction and motion planning for autonomous vehicles. And I am working on the behavior planning currently. My big picture is to finish the prediction->motion planning->behavior planning pipeline and verify my planning methods on a real vehicle.

Publications

News

Safe Trajectory Generation For Complex Urban Environments Using Spatio-temporal Semantic Corridor

Wenchao Ding*, Lu Zhang*, Jing Chen, and Shaojie Shen (*: equal contribution)

IEEE Robotics and Automation Letters (RA-L)

Predicting Vehicle Behaviors Over an Extended Horizon Using Behavior Interaction Network

Wenchao Ding, Jing Chen, and Shaojie Shen

International Conference on Robotics and Automation (ICRA) 2019

Online Vehicle Trajectory Prediction using Policy Anticipation Network and Optimization-based Context Reasoning

Wenchao Ding and Shaojie Shen

International Conference on Robotics and Automation (ICRA) 2019

Trajectory Replanning for Quadrotors Using Kinodynamic Search and Elastic Optimization

Wenchao Ding, Wenliang Gao, Kaixuan Wang, and Shaojie Shen

International Conference on Robotics and Automation (ICRA) 2018

Quadtree-accelerated Real-time Monocular Dense Mapping

Kaixuan Wang, Wenchao Ding, and Shaojie Shen

International Conference on Intelligent Robots and Systems (IROS) 2018

Journal papers

Conference papers

An Efficient B-spline-Based Kinodynamic Replanning Framework for Quadrotors

Wenchao Ding, Wenliang Gao, Kaixuan Wang, and Shaojie Shen

IEEE Transactions on Robotics (TRO)

Jan 2019 - Two papers accepted by ICRA2019!

June 2019 - One paper accepted by IEEE Transactions on Robotics (T-RO)! (Check out the paper!)

June 2019 - One paper accepted by IEEE RA-L! (Check out the paper! code is coming soon!)

Jan 2018 - One paper accepted by ICRA2018!

Email: wdingae@connect.ust.hk

Bio

Last update: June 9 2019

Ph.D. Candidate in HKUST Aerial Robotics Group

Robotics Institute, Hong Kong University of Science and Technology

Wechat: dwc277310782; Skype: denny.wcding@gmail.com

On-going project

I am currently working on behavior planning/decision making for complex urban environments. The main focus is to generate safe and efficient behavioral plan given uncertain hidden intention (e.g., pedestrian intention, interaction intention, prediction error) in dense traffic. (RA-L with ICRA 2020 Expected)

Past projects

Prediction for Autonomous Vehicles

1) Novel learning-based network to model and predict future behaviors of agent vehicles. The key feature is modeling the interaction among vehicles to enhance prediction accuracy and extend the prediction horizon. (Accepted by ICRA 2019)

2) Two-level behavior & trajectory prediction framework: online hierarchical prediction framework for modeling multimodal behaviors and contextual factors in complex urban environments. (Also accepted by ICRA 2019)

Motion planning for Autonomous Vehicles

A safe and unified motion planning framework for modeling numerous semantic elements in complex urban environments based on spatiotemporal information. The key feature is that it can work in complex urban environments and has a safety guarantee. (IEEE RA-L with IROS 2019)

Planning for Micro Aerial Vehicles

Trajectory planning for monocular vision-based quadrotors: efficient trajectory replanning framework for onboard autonomous flight in unknown indoor and outdoor environments with only one camera and one IMU. (ICRA 2018 & IEEE Transactions on Robotics)