Tixian Wang

Papers

Total Citations

H-Index

About

Tixian Wang’s research lies at the intersection of reinforcement learning, bio-inspired control, and robotic locomotion. Their major contributions center on developing learning frameworks that enable robots to autonomously discover and refine periodic gaits—such as those seen in biological locomotion. Wang introduced a Q-learning approach tailored for partially observable Markov decision processes (POMDPs) to learn optimal locomotion gaits in systems modeled as coupled rigid bodies. This work, published in 2019, has garnered 3 citations and is complemented by a 2020 study on bio-inspired central pattern generator (CPG) architectures for sensorimotor control of maneuvering gaits, demonstrated on a snake robot model. Together, these papers (totaling 7 citations) showcase Wang’s ability to bridge theoretical learning algorithms with practical robotic systems. Their work is notable for its innovative use of periodic open-loop inputs to shape nominal gaits, offering a scalable pathway for adaptive locomotion in unstructured environments. Wang’s research is particularly relevant for students and researchers interested in how machine learning can unlock more agile, animal-like movement in robots.