Max Robotics — Global Service Robot Directory + US Certification

About

Jason Ford is a leading researcher in autonomous aerial robotics, with a career focused on enabling safe, vision-based navigation for unmanned aerial vehicles (UAVs). His foundational work on collision detection systems is widely recognized; his 2010 paper on an "Airborne vision‐based collision‐detection system" has garnered 122 citations, establishing a core methodology for using low-cost, lightweight machine vision as an alternative to radar for sense-and-avoid applications. Expanding on this, his 2010 study on "Vision-based detection and tracking of aerial targets for UAV collision avoidance" (79 citations) provided critical algorithms for tracking potential collision courses in real time. More recently, Ford has advanced the field of Visual Place Recognition (VPR) for robot localization. His 2022 work on "Predicting to Improve: Integrity Measures for Assessing Visual Localization Performance" (15 citations) introduced novel self-assessment metrics that allow robots to gauge the reliability of their own position estimates. His latest 2024 paper further refines this by using a Multi-Layer Perceptron to verify localization integrity, directly improving autonomous navigation decisions. Through this trajectory, Ford has moved from enabling basic aerial collision avoidance to building trustworthy, self-aware navigation systems.