Dr Hanlin Niu

Research Associate

Full contact details
View graph of relations


Hanlin is a Postdoctoral Research Associate at the University of Manchester, being involved in Project Digital twin-based Bilateral Teleautonomous System for Nuclear Remote Operation, funded by EPSRC and  Project Robotics and AI in Nuclear (RAIN), funded by EPSRC.

Before joining the University of Manchester, Dr Hanlin Niu worked as a Postdoc in Cardiff University working on robotic system and computer vision. He obtained bachelor degree from Tianjin University and obtained PhD degree in Autonomous and Intelligent System Group of Cranfield University (UK). He has worked on guidance, navigation and control of Unmanned Aerial Vehicles and Unmanned Surface Vehicles for more than 5 years. His research area covers collision avoidance algorithm, path following algorithm, path planning algorithm, decision making, deep learning, computer vision and system formal verification.

Hanlin has a strong project experience and he has participated in several projects during his PhD, which includes two industrial projects and funded by Innovative UK, National Oceanography Centre (NOC), Technology Strategy Board (TSB) and the Defence, Science, Technology Laboratories (DSTL). Hanlin was also the first president of Unmanned and Intelligent Systems Society of Cranfield University and he proposed, developed, and demonstrated 5 drone projects. In part time, Hanlin also developed and demonstrated multi-drone platform independently.

Hanlin has a strong industrial experience and he has a strong programming skill in Matlab, Simulink, C++ and Python. He also has extended experience in embedded systems, robotics and systems integration. Hanlin also developed and implemented collision avoidance algorithm and precise path following algorithm on C-Enduro USV and C-worker USV for ASV Global, Ltd (Portsmouth, UK). Hanlin also developed randomly pick and place solution using Kuka iiwa robot arm in Astute Project of Cardiff University. 


  • Path Planning, Collision Avoidance, Deep Reinforcement Learning, Formal Verification, Deep Learning

Related information

Publication highlights

Research output: Contribution to journalArticlepeer-review

Research output: Contribution to journalArticlepeer-review

View all publications (7)