GRA Vacancy on Deep Reinforcement Learning aided autonomous navigation for Environment-Aware UAV Applications Project at University of Southampton Malaysia

University: University of Southampton Malaysia

Project Title: Deep Reinforcement Learning aided autonomous navigation for Environment-Aware UAV Applications

Funding agency: MOSTI

Nationality requirements: Applicants must be Malaysian

Contact: ivan.ling@soton.ac.uk

Research on autonomous navigation of Unmanned Aerial Vehicle (UAV) plays a pivotal role in designing reliable industrial UAVs for diverse applications. An interesting application for this technology is the capability of navigating under tree canopies. Such drones will be extremely valuable for security and data collection in farms or plantations. Hence, we propose a Deep Reinforcement Learning (DRL) aided approach that enables the proposed UAV to execute navigation tasks under tree canopies. The mission is formulated by exploiting the Partially Observable Markov Decision Process (POMDP) and solved by a novel DRL algorithm. The successful candidate will work alongside researchers from the University of Southampton Malaysia, Aerodyne Bhd and MIMOS Bhd to develop and implement the required algorithm for DRL aided under-canopy navigation. At the University, the candidate will have access to a dedicated GPU server for AI training tasks and state-of-the-art quadcopters for benchmarking and testing. Candidates having prior experiences in embedded programming, silicon radar, Lidar, or machine learning background are encouraged to apply.

It is worth mentioning that Aerodyne is the top drone service company in the world (as reported by Drone Industry Insights), and University of Southampton is ranked within the 100th best Universities in the world (Number 77th in QS Ranking 2022).

The project will start in Oct/Nov 2022. The minimum English requirement is IELTS 6.5

Full tuition fee waiver and competitive stipend is available for eligible candidate. Stipend: RM2500 per month (3 years)