Michael Pabst
Papers
1
Total Citations
34
H-Index
1
About
Michael Pabst is a leading researcher in autonomous aerial robotics and human motion capture, with a focus on integrating deep reinforcement learning into multi-robot systems. His most cited work, "AirCapRL: Autonomous Aerial Human Motion Capture using Deep Reinforcement Learning" (2020, 34 citations), introduces a pioneering deep RL-based formation controller for vision-based aerial MoCap. This work addresses the challenge of estimating a moving person's body pose and shape using a team of drones, advancing the field of autonomous cinematography and human-robot interaction. Pabst's contributions lie in developing robust, adaptive control strategies that enable drones to autonomously track and capture complex human motions in real-time, overcoming limitations of traditional motion capture systems. His research has significant implications for sports analytics, film production, and assistive technologies. With a growing citation impact, Pabst continues to push boundaries in aerial robotics, earning recognition for bridging reinforcement learning and practical MoCap applications. His work inspires students and researchers exploring the intersection of robotics, computer vision, and AI-driven autonomy.
Research Focus
Key Achievements
Top Papers
- 1