Yves Kompis
Papers
2
Total Citations
73
H-Index
2
About
Yves Kompis is a leading researcher in autonomous robotics, specializing in online 3D reconstruction, motion planning, and deep reinforcement learning for aerial systems. His most influential work, “Voxfield: Non-Projective Signed Distance Fields for Online Planning and 3D Reconstruction” (52 citations), introduces a novel mapping framework that enables resource-constrained robots to build accurate, real-time volumetric maps of complex, unknown environments—a critical capability for truly autonomous navigation. This contribution directly addresses the computational and energy limitations of mobile systems, advancing the state of the art in simultaneous localization and mapping (SLAM) and path planning. In parallel, Kompis’s paper “Autonomous Emergency Landing for Multicopters using Deep Reinforcement Learning” (21 citations) pioneers a deep RL pipeline that allows UAVs to autonomously execute safe emergency landings under sensor or GPS failure, mechanical malfunctions, or sudden battery drops. This work has significant implications for drone safety and reliability in real-world operations. Together, Kompis’s research bridges perception, planning, and robust control, earning recognition for pushing the boundaries of autonomous flight and field robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2