Mirco Theile

About

Mirco Theile is a rising researcher at the intersection of robotics, reinforcement learning, and cyber-physical systems. His primary research focuses on developing intelligent, data-driven control strategies for complex autonomous systems, with a particular emphasis on unmanned aerial vehicles (UAVs) and safety-constrained environments. Theile’s most notable contribution is in coverage path planning (CPP) for battery-limited UAVs, where his work “Learning to Recharge: UAV Coverage Path Planning through Deep Reinforcement Learning” (2023, 6 citations) introduces a novel deep RL framework that enables drones to autonomously plan efficient paths while managing energy constraints through strategic recharging. This addresses a critical bottleneck in real-world UAV deployment. His more recent work, “Learning to Generate All Feasible Actions” (2024, 2 citations), tackles the fundamental challenge of enforcing hard safety and operational constraints in RL, proposing a method to ensure agents only consider viable actions—a crucial step toward trustworthy autonomous systems. Theile’s research is characterized by its practical focus on bridging the gap between theoretical RL advances and real-world robotic applications, making him a promising voice in the field of autonomous navigation and constrained learning.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning to Recharge: UAV Coverage Path Planning through Deep Reinforcement Learning

   6 citations · 2023
2. 2
   Learning to Generate All Feasible Actions

   2 citations · 2024

Key Collaborators

Contact & Links