Max Robotics — Global Service Robot Directory + US Certification

About

Max Argus is a roboticist whose research bridges the gap between human dexterity and autonomous robot manipulation. His work centers on three key areas: power grasp planning, one-shot imitation learning, and accessible robotics tooling. Argus’s foundational contribution, “Power grasp planning for anthropomorphic robot hands” (2012, 57 citations), introduced a method for computing stable grasps by sampling object surfaces, enabling robots to mimic human grasping strategies—a cornerstone for anthropomorphic hand control. More recently, he has advanced one-shot imitation with “DITTO: Demonstration Imitation by Trajectory Transformation” (2024, 12 citations), which uses RGB-D video to teach robots new skills from a single human demo, and “FlowControl: Optical Flow Based Visual Servoing” (2020), which leverages learning-based optical flow for real-time task execution. Argus also developed “RobotIO: A Python Library for Robot Manipulation Experiments” (2022, 12 citations), a tool that simplifies real-world robotic testing, lowering barriers for researchers. His work on conditional visual servoing for multi-step tasks and pre-training deep RL agents under domain randomization further showcases his impact, with over 88 total citations. Argus’s contributions are driving a future where robots learn tasks as intuitively as humans—from a single glance.