Benyang Tang

Jet Propulsion Laboratory, California Institute of Technology

Papers

Total Citations

168

H-Index

About

Benyang Tang is a leading researcher in autonomous off-road navigation, with a focus on end-to-end learning and stereo-vision-based perception for robotic ground vehicles. His major contributions include pioneering the use of end-to-end learning from proprioceptive sensors, operator input, and stereo cameras to enable real-time, adaptive navigation in unstructured terrain. Tang’s work addresses the critical challenge of limited sensor lookahead by extending terrain classification into the far field, preventing myopic behavior in autonomous systems. His most cited paper, "Autonomous off‐road navigation with end‐to‐end learning for the LAGR program" (2008, 84 citations), demonstrates a fully integrated system that learns traversability directly from data, while his earlier foundational work, "Towards learned traversability for robot navigation" (2006, 72 citations), laid the groundwork for this approach. Tang also contributed to the U.S. Army Research Laboratory’s Robotics Collaborative Technology Alliances (RCTA) program, developing stereo-vision-based perception capabilities that advanced military and space exploration robotics. With a career spanning key defense and academic collaborations, Tang’s research has significantly influenced the field of autonomous navigation, providing scalable, learning-based solutions for real-world off-road environments.