Max Robotics — Global Service Robot Directory + US Certification

About

Jordy Sehn is a robotics researcher whose work centers on autonomous navigation, particularly long-term path following and obstacle avoidance in unstructured environments. His major contributions lie in advancing the Visual Teach and Repeat (VT&R) framework, most notably through VT&R3, which enables robust, long-term autonomous path-following using topometric mapping from a single sensor stream. Sehn’s 2023 paper on this system, with 7 citations, demonstrates how LiDAR-based implementations can reliably detect and avoid obstacles while maintaining a taught path. He has also pioneered unsupervised deep learning for LiDAR change detection, as shown in his 2024 work (3 citations), which reformulates semantic segmentation as binary change detection—a critical innovation for robots operating in environments where defining closed semantic classes is impractical. Additionally, Sehn introduced laterally weighted motion planning (2023–2024, 5 combined citations), a novel edge-cost metric that generates naturally smooth, obstacle-avoiding paths during long-range navigation. His research directly addresses real-world challenges in field robotics, making autonomous systems more resilient and adaptable. With a growing citation record and a focus on practical, deployable solutions, Sehn is establishing himself as a rising voice in mobile robot autonomy.