Research Fellow (Multi-Agent RL for Autonomous Drone Swarm)
Core
Develop learning-based algorithms for cooperative target tracking and autonomous coordination of drone swarms in complex, urban environments.
Role type
Research Fellow (Multi-Agent Reinforcement Learning)
Builds
Learning-based frameworks for cooperative multi-agent robotic systems
Domain
Robotics, Autonomous Systems, AI
Deliverable
production ML models
Required skills
Multi-agent reinforcement learning, Decentralized control, Simulation-based validation, Python programming, Deep learning frameworks (PyTorch/TensorFlow), Perception-aware decision-making, Task allocation algorithms
Preferred skills
Graph neural networks, Attention mechanisms, Computer vision, Sensor fusion, Real-world UAV experimentation
Technologies
PyTorch, TensorFlow, Unity, ROS/ROS2, Gazebo, AirSim
Responsibilities
Develop reinforcement learning algorithms for autonomous coordination under uncertainty; Formulate multi-agent decision-making problems including state representation and reward design; Integrate perception, decision-making, and control modules within simulation frameworks; Design and conduct simulation experiments to evaluate system performance; Mentor junior researchers and support system integration; Prepare technical reports and research publications
Seniority
Mid-Senior, hands-on IC researcher
