Max Robotics — Global Service Robot Directory + US Certification

About

Tianhao Wei is an emerging researcher at the forefront of safe reinforcement learning and autonomous control systems, with a focus on bridging the gap between simulation-based RL successes and reliable real-world deployment. His work centers on three interconnected themes: safe reinforcement learning, safety index synthesis, and safe control under uncertainty. Wei's most influential contribution, "State-wise Safe Reinforcement Learning: A Survey" (2023, 41 citations), has quickly become a key reference for researchers navigating the complex landscape of constraint satisfaction in RL, systematically organizing state-wise safety approaches that are critical for real-world applicability. Complementing this, his work on Safety Index Synthesis via Sum-of-Squares Programming (21 citations) offers formal, mathematically rigorous methods for designing safety guarantees even under control limitations — a notoriously difficult problem. His research further extends into neural network-based dynamic models for safe control, human-robot interaction under multimodal uncertainty, and practical robotic applications such as precision industrial insertion tasks. This breadth demonstrates Wei's commitment to translating theoretical safety frameworks into tangible engineering solutions. With a growing citation record and contributions spanning theory, algorithms, and robotics applications, Wei represents a promising voice in making autonomous systems both capable and trustworthy.