Max Robotics — Global Service Robot Directory + US Certification

About

Joachim Clemens is a leading researcher in autonomous robotics and state estimation, with a particular focus on advancing simultaneous localization and mapping (SLAM) under uncertainty. His most impactful work introduces novel evidential and probabilistic frameworks for robust robotic perception. Clemens pioneered the application of Dempster-Shafer theory to the full SLAM problem, as demonstrated in his highly cited 2016 paper on evidential SLAM, path planning, and active exploration (38 citations), which remains a cornerstone reference for handling ambiguous sensor data. He further extended this paradigm with Evidential FastSLAM for grid mapping (2013, 16 citations) and β-SLAM (2018, 13 citations), which leverages beta distributions to model occupancy uncertainty. His 2014 work on "Dimensions of Uncertainty in Evidential Grid Maps" (11 citations) systematically categorizes sources of uncertainty in robotic mapping. Beyond SLAM, Clemens has made notable contributions to autonomous driving, developing a Kalman filter with a moving reference for jump-free multi-sensor odometry (2020, 9 citations), and to multi-robot localization in extreme environments like in-ice probes (2017). His recent work on state estimation of articulated vehicles using deformed superellipses (2021) demonstrates his ongoing commitment to solving complex perception challenges, with his research collectively shaping modern approaches to reliable autonomous navigation.