Max Robotics — Global Service Robot Directory + US Certification

About

Colin Kohler is a roboticist focused on making intelligent, adaptable manipulation a reality for assistive and open-world applications. His research sits at the intersection of robotic manipulation, deep reinforcement learning, and human-centered design. Kohler’s major contributions include developing novel learning frameworks that enable robots to generalize across varying object poses and leverage force feedback for more robust control. His work on "Deictic Image Mapping" provides a powerful abstraction for learning pose-invariant policies, while his recent research on "Symmetric Models for Visual Force Policy Learning" demonstrates how integrating tactile and visual data dramatically improves sample efficiency. To accelerate the field, he co-created BulletArm, an open-source benchmarking and learning framework for robotic manipulation. Kohler’s impact is also deeply practical; his work on a scooter-mounted robot arm directly addresses the challenges faced by individuals with motor disabilities, aiming to increase independence in activities of daily life. With his most-cited papers accumulating dozens of citations and his focus on both foundational algorithms and real-world assistive systems, Kohler is a rising voice in the drive toward capable, general-purpose robotic assistants.