Max Robotics — Global Service Robot Directory + US Certification

About

Brad Saund’s research lies at the intersection of robotics, perception, and artificial intelligence, with a focus on enabling robots to operate robustly in uncertain and partially observed environments. His major contributions center on planning and state estimation under contact sensing uncertainty, particularly for manipulation tasks. In his most-cited work, “The Blindfolded Robot: A Bayesian Approach to Planning with Contact Feedback” (2022, 11 citations), Saund introduces a framework that allows robots to reason probabilistically about contact events, enabling effective motion planning even when visual feedback is unavailable. This work builds on his earlier “Motion Planning for Manipulators in Unknown Environments with Contact Sensing Uncertainty” (2020, 6 citations), which addresses the challenge of planning in cluttered, unknown spaces. Saund also advances shape perception with PSSNet, a network that generates diverse plausible 3D reconstructions from ambiguous depth images, and CLASP, which refines object shape estimates by integrating robot contact data with visual priors. His work has been recognized for its practical impact on autonomous manipulation, with cumulative citations exceeding 20. Saund’s research is notable for bridging Bayesian reasoning with deep learning, offering principled solutions to real-world robotic challenges.