| Ze’s Personal Page

Greetings!

Welcome to my personal page. I finished my PhD in the Group of Automation at the Chalmers University of Technology, supervised by Prof. Knut Åkesson. I’m currently working on cloud robotics with Prof. Ahmed Ali-Eldin Hassan. My research interests are in the area of robotics and machine learning, particularly in the development of integrated algorithms for predictive dynamic obstacle avoidance based on multimodal motion prediction. If you are interested in my work, feel free to contact me or raise an issue on the corresponding GitHub repository.

I sucessfully defended my thesis, “Future-Oriented Navigation for Autonomous Mobile Robots”, on May 15, 2025.

Active Work

Dynamic Nonconvex Obstacle Avoidance: One-shot Motion Prediction (EBM) and Control (On-Manifold CBF)

Yifan Xue*, Ze Zhang*, et al. (*equal contribution)

Under review (collaboration with GRASP lab, Univerisity of Pennsylvania) [Code (Not yet)] [Paper (Not yet)] [Video-Demo]

Not yet

Complex Obstacle Avoidance and Fleet Collision Avoidance: Sampling-based Trajectory Planning (DWA) Inspried by Gradient Field (GPDF)

Ze Zhang, Yifan Xue, et al.

IROS 2025 - Hangzhou, CN [Code] [Paper (arXiv)] [Video-Demo]

Gradient Field-Based Dynamic Window Approach for Collision Avoidance in Complex Environments | Non-convex obstacle avoidance | Multi-robot collision avoidance

Dynamic Obstacle Avoidance: One-shot Motion Prediction (EBM) and Control (MPC)

Ze Zhang, ..., et al.

RA-L 2025 [Code] [ROS 2] [Paper] [Video-Demo]

Future-Oriented Navigation: Dynamic Obstacle Avoidance with One-Shot Energy-Based Multimodal Motion Prediction | Autonomous Mobile Robot | Energy-Based Multimodal Motion Prediction

Efficient Obstacle Avoidance and Multi-Agent Coordination: DDPG-Boosted MPC for Collision-Free Navigation

Kristian Ceder*, Ze Zhang*, et al. (*equal contribution)

IROS 2024 (Abu Dhabi, UAE) [Code] [Paper] [Video-Demo]

Bird’s-Eye-View Trajectory Planning of Multiple Robots using Continuous Deep Reinforcement Learning and Model Predictive Control | Deep Reinforcement Learning | Multi-Agent Coordination

Previous Work

Dynamic Obstacle Avoidance: Iterative Motion Prediction (SWTA) and Control (MPC)

Ze Zhang, Hadi Hajieghrary, et al.

RA-L 2023 - Yokohama, JPN (ICRA 2024) [Code] [Paper] [Video-Demo]

[Deprecation soon] Prescient Collision-Free Navigation of Mobile Robots With Iterative Multimodal Motion Prediction of Dynamic Obstacles | Autonomous Mobile Robot | Multimodal Motion Prediction

Efficient Obstacle Avoidance: DQN-Boosted MPC for Collision-Free Navigation

Ze Zhang, Yao Cai, et al.

CASE 2023 - Auckland, NZ [Code] [Paper]

Collision-Free Trajectory Planning of Mobile Robots by Integrating Deep Reinforcement Learning and Model Predictive Control | Deep Reinforcement Learning

Multimodal Motion Prediction: Adaptive and Swarm WTA Loss

Ze Zhang, Emmanuel Dean, et al.

CASE 2022 - Mexico City, MEX [Code] [Paper]

Multimodal Motion Prediction Based on Adaptive and Swarm Sampling Loss Functions for Reactive Mobile Robots | Multiple Choice Learning

Dynamic Obstacle Avoidance: MDN Predictor and MPC