Max Robotics — Global Service Robot Directory + US Certification

About

Van-Thach Do is a researcher whose work spans robotics control systems, autonomous path planning, and computer vision-based robot guidance. His most recognized contribution lies in advanced control theory for ballbot systems—dynamically unstable, ball-balancing mobile robots. Beginning with energy-based and LQG control frameworks, Do progressively developed more sophisticated methodologies, culminating in his highly cited 2020 work on robust integral backstepping hierarchical sliding mode control (25 citations), which demonstrated significant improvements in stabilization and transfer performance for these inherently underactuated platforms. His 2019 passivity-based nonlinear control approach further solidified his expertise in tackling complex, nonlinear dynamic systems. Beyond control theory, Do has made meaningful contributions to robotics perception and automation. His 2022 work on Deep Feature-Based Visual Servoing (DFBVS, 13 citations) addresses critical limitations of classical visual servoing by leveraging deep neural network features for improved generalizability. More recently, his geometry-aware coverage path planning research (15 citations) introduced a novel constrained centroidal Voronoi tessellation approach for efficient surface coverage on complex 3D geometries—a practically important advance for post-processing in additive manufacturing. Collectively, Do's research reflects a versatile and growing impact across control engineering, computer vision, and intelligent robotic autonomy.