Reference Number: ARL-SRP-00087
Project Description
The goal of this project is to investigate the concept of objective-driven shared autonomy for uncrewed aerial system (UAS) swarms through the development of a minimal simulation based proof of concept. UAS have revolutionized the ability to operate in critical situations such as disaster response. However, operators remain responsible for supervising and micromanaging individual vehicles or small centralized groups, limiting scalability and creating single points of failure. This project investigates how operators can communicate mission objectives rather than individual vehicle commands, enabling autonomous agents to collaboratively determine task allocation, coordination, and adaptation to dynamic environments.
Participants will design and implement a proof-of-concept simulation framework for decentralized multi-agent autonomy, enabling a single operator to communicate mission objectives to a team of UAS. The project focuses on decentralized communication, multi-agent coordination, and autonomous decision-making through representative scenarios such as collaborative mapping. In detail, the tools/tech participants will use include software development environments (Python/C++), gain experience in computer science or robotics, based on their interest in autonomous and multi-agent systems.
Expected outcome:
Multi-agent communication and coordination, autonomous decision-making architectures, multi-agent simulation and software architecture, objective-driven shared autonomy, systems engineering
Technical Skills
- Advanced Sensing
- Aerospace Engineering
- Artificial Intelligence/Machine Learning
- Computer Modeling/Simulation
- Computer Science
- Communication and Networking Technologies
- Electrical Engineering
- Electronics
- Mathematics
- Mechanical Engineering
- Software Development
- UI/UX Design
- Human Factors Engineering/Human Systems Integration
- Python/C++ ; Autopilots: PX4 or Ardupilot, familiarity with UAS/drones, embedded systems software engineering
