Max Robotics — Global Service Robot Directory + US Certification

About

Adrian Zwiener’s research lies at the intersection of robotics, machine learning, and tactile perception, with a focus on enabling safer, more intelligent physical interactions for articulated manipulators. His major contributions center on contact point localization—a critical capability for robots to detect and respond to collisions during grasping and manipulation tasks. In his most cited work, “Contact Point Localization for Articulated Manipulators with Proprioceptive Sensors and Machine Learning” (2018, 25 citations), Zwiener introduced a model-based ML approach that uses only proprioceptive sensors (joint positions, velocities, and torques) to localize external contacts on a 6-DOF serial manipulator, eliminating the need for external sensing. He further advanced this with “ARMCL: ARM Contact point Localization via Monte Carlo Localization” (2019, 12 citations), applying probabilistic methods to improve robustness in real-world scenarios. Additionally, his work on “Inverse Recurrent Models” (2016, 11 citations) and “Inherently Constraint-Aware Control” (2017, 8 citations) explores control strategies for many-joint robot arms, addressing the challenge of managing high degrees of freedom with constraint awareness. With a cumulative citation impact of over 56, Zwiener’s research is foundational for developing more adaptive, collision-resilient robotic systems, making him a notable figure in the field of robot manipulation and proprioceptive sensing.