Max Robotics — Global Service Robot Directory + US Certification

About

Aditya Sagi is a robotics researcher specializing in legged locomotion, reinforcement learning, and robot control systems, with a particular focus on quadrupedal robots. His work sits at the intersection of deep learning and robotic motion planning, advancing how autonomous robots learn and execute complex walking behaviors. Sagi's most impactful contribution, "Trajectory based Deep Policy Search for Quadrupedal Walking" (2019, 8 citations), introduced a novel deep reinforcement learning framework that optimizes policies at the trajectory level rather than individual time steps — a meaningful shift in how locomotion problems are framed. His follow-up work on gait library synthesis using Augmented Random Search demonstrated practical deployment of multiple learned gaits — including trot, side-step, and turn — on real low-cost hardware (the custom-built Stoch 2 robot), earning 4 citations and highlighting his commitment to bridging simulation and physical implementation. More recently, his research on linear policies for force-controlled quadruped locomotion (2023) reflects a growing interest in agile, dynamic motion using computationally efficient methods. His early work comparing robot leg architectures further demonstrates a solid foundation in mechanical design. Collectively, Sagi's research contributes meaningfully to making legged robots more capable, adaptable, and deployable in real-world environments.