Max Robotics — Global Service Robot Directory + US Certification

About

Anders Glent Buch is a robotics researcher whose work sits at the intersection of robot learning, assembly automation, and intelligent manipulation. His research has made significant contributions to programming by demonstration, robotic assembly, and grasp affordance learning — areas critical to advancing flexible industrial automation. Buch's most influential work, "Solving Peg-in-Hole Tasks by Human Demonstration and Exception Strategies" (2014, 78 citations), introduced a novel algorithm enabling robots to learn precise assembly operations through kinesthetic guidance, dramatically lowering the barrier to programming complex manipulation tasks. This was complemented by his development of a three-level cognitive system for teaching robots the semantics of assembly tasks (2017, 64 citations), bridging sensorimotor learning with higher-level planning in an elegant and transferable architecture. His earlier work on learning grasp affordance models from experience (2010, 40 citations) demonstrated robust 3D object-gripper reasoning on realistic autonomous platforms. Beyond individual contributions, Buch has consistently pushed toward agile, high-mix/low-volume industrial production, evident in his involvement with the World Robot Challenge 2018 and research on fast, vision-based robot cell setup. Collectively accumulating over 290 citations, his body of work reflects a sustained commitment to making adaptive, easily programmable robots a practical reality for modern manufacturing.