Max Robotics — Global Service Robot Directory + US Certification

About

Tamir Blum is a robotics and artificial intelligence researcher whose work sits at the intersection of deep reinforcement learning, autonomous locomotion, and space robotics. His research has made notable contributions to the challenge of enabling robots to navigate complex, unstructured environments — from inclined terrain to the lunar surface — without relying on handcrafted rules or prior environmental knowledge. Blum's most cited work, "Adaptive Slope Locomotion with Deep Reinforcement Learning" (2020, 10 citations), demonstrates a model-free approach to quadruped motion planning across variable terrain, a technically demanding problem with broad implications for field robotics. Complementary papers such as the PPMC RL Training Algorithm and the RL STaR Platform further establish his focus on generalizable, simulation-trained robotic systems suited for high-uncertainty environments like lunar exploration. His SegVisRL series (2021) extends this vision by integrating proprioceptive and camera-based sensing into learned visuomotor systems for rover hazard avoidance. More recently, Blum has broadened his scope into agricultural robotics, contributing to the development of an autonomous grass-cutting platform (2025). With a cumulative body of work spanning space robotics, path planning, and autonomous systems, Blum represents an emerging voice in applied reinforcement learning for real-world robotic deployment.