Max Robotics — Global Service Robot Directory + US Certification

About

Ambrose Chan is a robotics researcher whose work sits at the intersection of visual servoing, robot motion planning, and constrained manipulation. His research has made significant contributions to enabling robots to operate intelligently in cluttered, real-world environments — a challenge that remains central to industrial automation and human-robot collaboration. Chan is perhaps best known for developing the Constrained Manipulator Visual Servoing (CMVS) framework, which allows robots to navigate complex workspaces without requiring precise calibration or pre-taught positions. His 2011 papers on CMVS and collision-free visual servoing — together accumulating 17 citations — introduced model-free optimization approaches that brought practical robustness to eye-in-hand robotic systems. He later extended this work to handle nonconvex workspace constraints learned from demonstrations, further bridging the gap between classical control theory and data-driven robotics. His 2017 paper on vision-based motion planning from multiple demonstrations, his most cited work with 13 citations, reflects a broader trajectory toward learning-from-demonstration paradigms. Additional contributions to bin-picking and trajectory specification through sparse waypoints round out a body of work that consistently prioritizes applicability in unstructured settings, making Chan a notable contributor to practical robot programming and autonomous manipulation research.