Dominik Kellner

Papers

Total Citations

H-Index

About

Dominik Kellner is a leading researcher in autonomous driving perception, specializing in dynamic object tracking and state estimation for mobile robots. His work addresses a critical challenge in self-driving technology: accurately tracking surrounding traffic participants to enable safe maneuver planning. Kellner’s most influential contribution, the 2019 paper "Grid-Based Object Tracking With Nonlinear Dynamic State and Shape Estimation" (47 citations), introduces a novel multi-stage processing framework that transforms raw sensor measurements into high-level object abstractions, such as vehicles. This approach integrates nonlinear dynamic models with shape estimation, allowing for robust tracking of objects with varying geometries and motion patterns—a key advancement over traditional methods. By bridging the gap between low-level sensor data and actionable environmental understanding, Kellner’s research directly supports the development of reliable autonomous systems. His work is widely cited in the autonomous driving community, reflecting its practical impact on real-world vehicle perception stacks. For students and researchers entering the field, Kellner’s contributions offer a foundational understanding of how grid-based methods can enhance object tracking accuracy in complex, dynamic environments.