Max Robotics — Global Service Robot Directory + US Certification

About

Johan Ekekrantz is a robotics researcher whose work sits at the intersection of autonomous mobile systems, spatial perception, and long-term robot operation in dynamic environments. His research addresses some of the most challenging practical problems in deploying service robots in real-world settings, where environments continuously change and static assumptions quickly become liabilities. Ekekrantz's most influential contribution, cited 40 times, introduced a spectral map-based approach to topological localisation that explicitly embraces environmental change rather than treating it as noise — a significant conceptual shift from conventional methods. Building on this foundation, he developed techniques for the unsupervised learning of spatial-temporal object models from RGB-D data, enabling robots to autonomously understand how objects move and evolve over extended periods without human annotation. His later work on detection and tracking of general movable objects in large 3D maps, cited 20 times, tackled the scalability problem inherent in long-term autonomy: robots cannot observe everything simultaneously, yet must maintain coherent models of a dynamic world. His adaptive iterative closest keypoint algorithm further contributed robust 3D view registration methods essential for SLAM and object recognition pipelines. Collectively, Ekekrantz's research meaningfully advances the goal of robots that reason intelligently about a changing world over time.