David Fan

Papers

Total Citations

H-Index

About

David Fan is a roboticist advancing autonomous navigation in the most challenging, unstructured environments. His research centers on three key areas: object-goal navigation, risk-aware off-road traversal, and novel state estimation using physical interactions. Fan’s work is distinguished by its focus on real-world deployment, particularly in inspection and disaster-response scenarios. His most cited paper, “SEEK: Semantic Reasoning for Object Goal Navigation in Real World Inspection Tasks” (2024, 14 citations), introduces a semantic reasoning framework that enables robots to efficiently locate target objects within vast, complex spaces—a critical capability for autonomous industrial inspections. In “Contact Inertial Odometry: Collisions are your Friends” (2022, 12 citations), Fan pioneered a counterintuitive approach, leveraging deliberate collisions to improve odometry accuracy in cluttered environments. His contributions to the DARPA Subterranean Challenge, detailed in “STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation” (2023, 2 citations), demonstrate his commitment to extreme terrain autonomy, where he developed stochastic methods for evaluating and planning safe paths through rubble, caves, and post-disaster sites. Fan’s work bridges the gap between controlled lab settings and the unpredictable real world, making him a leading voice in resilient, field-ready robotics.