← Search

Martin Schuck

4 accepted papers

2026

A Primer on SO(3) Action Representations in Deep Reinforcement Learning

ICLR 2026poster

Many robotic control tasks require policies to act on orientations, yet the geometry of SO(3) makes this nontrivial. Because SO(3) admits no global, smooth, minimal parameterization, common representations such as Euler angles, quaternions, rotation matrices, and Lie algebra coordinates introduce di…

Cited by 0SourcecodeScholar
2026

SwarmGPT: Combining Large Language Models with Safe Motion Planning for Drone Swarm Choreography

ICRA 2026poster

Drone swarm performances---synchronized, expressive aerial displays set to music---have emerged as a captivating application of modern robotics. Yet designing smooth, safe choreographies remains a complex task requiring expert knowledge. We present SwarmGPT, a language-based choreographer that lever…

2025

SwarmGPT: Combining Large Language Models With Safe Motion Planning for Drone Swarm Choreography

RA-L 2025

Drone swarm performances—synchronized, expressive aerial displays set to music—have emerged as a captivating application of modern robotics. Yet designing smooth, safe choreographies remains a complex task requiring expert knowledge. We present SwarmGPT, a language-based choreographer that leverages

Cited by 3SourceScholar