Max Robotics — Global Service Robot Directory + US Certification

About

Luc De Raedt is a distinguished researcher whose work sits at the intersection of machine learning, logic, and robotics, with particular expertise in statistical relational learning and probabilistic logic programming. His landmark textbook *Logical and Relational Learning* (2008, 327 citations) established foundational frameworks for learning from structured, relational data — a cornerstone reference for researchers working beyond conventional flat-feature representations. De Raedt has made substantial contributions to robotic cognition, especially through his innovative application of relational affordance models. His research extended affordance-based reasoning from single-object scenarios to complex multi-object manipulation tasks, enabling robots to better understand action possibilities within their environments. This thread of work spans grasping, occluded object search, and navigation, demonstrating both breadth and continuity of vision. Equally significant is his development of probabilistic logic programming frameworks for hybrid relational domains, including particle filter approaches capable of handling dynamic environments with unknown numbers of objects. His more recent work on probabilistic anchoring bridges symbolic and sub-symbolic AI — a pressing challenge in modern robotics. Across his career, De Raedt has consistently pushed toward systems that reason richly, learn efficiently, and operate meaningfully in real-world conditions.