Jack E. Saunders

Reactive Collision Avoidance Using Deep Reinforcement Learning for the Application of UAV Delivery

Project Summary

Unmanned aerial vehicles (UAV) lack the required safety technologies for regulations to allow for delivery applications.  Current legislation is very restrictive, only permitting their operation within line of sight and during certain daylight hours.  This is for good reasons as UAVs can weigh up to 25kg and travel at speeds approaching 45 m/s which presents enormous threat to individual safety with several reports describing injuries or property damage from UAV crashes.    

I hope to research the dynamic environments delivery UAVs will encounter mid-flight for collision avoidance systems.  More specifically pop-up collisions that require highly reactive manoeuvres.

 

Research Interests

Training manoeuvres using deep reinforcement learning and exploring new ways that visual intelligence can impact the trajectory generation of UAVs. Then finding ways this research can help increase trust for UAV delivery.

Background

MEng Mechanical Engineering at Cardiff University

Supervisors

Dr Wenbin Li

Dr Alan Hunter

Prof Özgür Şimşek