Max Robotics — Global Service Robot Directory + US Certification

About

Tobias Lang is a leading researcher at the intersection of robotics, machine learning, and relational reasoning. His work is defined by two major thrusts: advancing terrain modeling through adaptive statistical methods, and enabling robots to learn abstract, relational knowledge for intelligent interaction. Lang’s foundational paper on adaptive non-stationary kernel regression for terrain modeling (79 citations) introduced a powerful approach to creating accurate 3D digital terrain models, balancing data smoothing with the preservation of critical discontinuities—a challenge fundamental to geoscience and outdoor robotics. In parallel, he has made significant contributions to relational reinforcement learning, pioneering exploration algorithms (42 citations) that allow robots to efficiently balance exploration and exploitation in large, stochastic relational domains. His research on active learning for teaching robots grounded relational symbols (68 citations) demonstrates how robots can learn generalizable abstract models from human interaction, a key step toward flexible, autonomous manipulation. Lang’s work on extracting kinematic background knowledge from exploratory interactions further showcases his commitment to building robots that can understand and adapt to novel objects. With a portfolio of highly cited, methodologically rigorous papers, Tobias Lang has established himself as a key figure in creating robots that can learn, reason, and act in complex, unstructured environments.