Max Robotics — Global Service Robot Directory + US Certification

About

Adam Misik is a rising researcher at the intersection of robotics, computer vision, and 3D perception, with a focus on enabling machines to understand and interact with their environments more intelligently. His work spans visual SLAM, point cloud registration, surface material classification, and CAD model retrieval—each addressing a critical bottleneck in autonomous systems. Misik’s most cited paper, “HPF-SLAM” (2024, 7 citations), introduces a hybrid point feature approach that overcomes the limitations of purely hand-crafted or learnable features, advancing the robustness of visual SLAM for applications like robot navigation and extended reality. He further pushes 3D alignment with “HEGN” (2024), a hierarchical equivariant graph neural network for 9-degree-of-freedom point cloud registration, tackling category-level pose estimation. In “SMCNet” (2025), he innovates by using mmWave radar and complex-valued CNNs for surface material classification, a novel sensor modality for indoor perception. His work “HypCAD” (2025) explores hyperbolic geometry for CAD model retrieval, enhancing object-level mapping for robotics and mixed reality. Though early in his career, Misik’s diverse contributions—from SLAM to material sensing—demonstrate a clear trajectory toward building more perceptive and autonomous robotic systems.