AI-based Co-Pilot System for Helicopter

Description

Multiple PhD positions with full scholarships are available to work on Robust Planning and Learning for AI-Based Helicopter Co-Pilot. In many emergency medical services and search and rescue missions, pilots must make multiple critical decisions that might mean the difference between life and death. However, they often have to make such critical decisions alone, as the aforementioned missions often have no co-pilot. In this project we will develop scalable integrated task and motion planning under uncertainty that can help helicopter pilots in such scenarios. We will explore various components and types of uncertainty in this problem, including uncertainty due to a priori unknown model, changing missions and weather, disturbances due to weather, as well as the pilot's cognitive ability and characteristics.

This project is in collaboration with Safran, with funding top-ups and opportunities for research visits and internship at Safran head-quarter in France.

Requirements

  • A first class honours or equivalent in Computer Science, Software Engineering, Mathematics, Mechatronics, or related fields.
  • Fluent in programming with C/C++ (preferred) or python
  • Have good understanding of basic probability.
  • Have done well in AI class is a plus

Keywords

Task planning, motion planning, planning under uncertainty, POMDP

Updated:  10 August 2021/Responsible Officer:  Dean, CECS/Page Contact:  CECS Marketing