Max Robotics — Global Service Robot Directory + US Certification

About

Yajue Yang is a robotics researcher whose work lies at the intersection of autonomous systems, robot dynamics, and learning from human demonstration. Her most significant contribution is an optimization-based framework for autonomous excavator trajectory generation, which has garnered 58 citations and addresses the limitations of traditional geometric parameterization by expanding the optimization space for complex task-specific constraints. This work has direct applications in construction automation and heavy machinery. Yang has also made notable advances in parallel computation for robotics, developing a GPU-parallelizable framework using prefix sum operations and band sparsity to dramatically accelerate forward and inverse dynamics for articulated robots—a critical enabler for real-time control. Her research extends to learning from demonstration, where she designed a bilateral teleoperation system that uses deep learning to extract scooping motions from human operators, bridging the gap between human skill and robotic autonomy. With a focus on both theoretical rigor and practical deployment, Yang’s work demonstrates how optimization, parallelism, and learning can converge to create more capable and efficient robotic systems for challenging real-world tasks.