Michal Adamkiewicz

Papers

Total Citations

H-Index

About

Michal Adamkiewicz is a roboticist whose work sits at the intersection of computer vision, neural scene representation, and autonomous navigation. His primary research focuses on enabling robots to understand and move through complex, unstructured environments using only visual input—a critical challenge for real-world deployment. Adamkiewicz is best known for his pioneering work on integrating Neural Radiance Fields (NeRFs) into robot navigation pipelines. In his highly cited 2022 paper, “Vision-Only Robot Navigation in a Neural Radiance World,” he demonstrated how NeRFs—which represent 3D scenes as continuous neural networks of volumetric density and color—can serve as a dense, photorealistic map for a robot to plan and execute collision-free paths from novel viewpoints. This work, which has already garnered 11 citations, was among the first to bridge the gap between state-of-the-art 3D scene representation and practical, vision-only robotic control. By showing that a robot could navigate a real-world environment using only a pre-trained NeRF model, Adamkiewicz opened a new direction for research in sample-efficient, simulation-to-real transfer. His contributions are particularly impactful for applications in search-and-rescue, inspection, and autonomous exploration where GPS and LiDAR are unavailable.