Justin Wasserman

Papers

Total Citations

H-Index

About

Justin Wasserman is a rising star in embodied AI and agricultural robotics, whose work bridges the gap between structured indoor environments and the unstructured, real-world challenges of autonomous navigation. His research centers on three key areas: simultaneous localization and mapping (SLAM) for agriculture, semantic embodied navigation, and long-horizon visual goal-seeking. Wasserman’s major contributions include the creation of the "Under-canopy dataset," a critical resource that exposes the failure of conventional SLAM systems in dense agricultural settings—a problem he highlights with 9 citations. He also pioneered "Exploitation-Guided Exploration," a modular policy framework that redefines how agents balance searching for and zeroing in on goals, and introduced "Last-Mile Embodied Visual Navigation," which tackles the precise calibration an agent needs once a goal is discovered. With multiple papers already garnering 7–9 citations in top venues, Wasserman’s work is rapidly shaping how robots navigate from the field to the final doorstep. His achievements signal a promising career dedicated to making autonomous systems robust, efficient, and ready for deployment in the most demanding environments.