Max Robotics — Global Service Robot Directory + US Certification

About

Yanbo Li is a researcher whose work spans robotics motion planning, autonomous navigation, and natural language processing. He is perhaps best known for his contributions to sampling-based kinodynamic planning, particularly his highly influential 2016 paper "Asymptotically Optimal Sampling-based Kinodynamic Planning," which has garnered over 250 citations and represents a landmark advance in high-dimensional motion planning for dynamically constrained systems. By leveraging random geometric graph theory, this work demonstrated how asymptotic optimality — a property previously difficult to guarantee — could be achieved for robots with complex dynamic constraints, significantly elevating the theoretical rigor of practical planning algorithms. Li's earlier research addressed complementary challenges in robotics, including learning approximate cost-to-go metrics to improve sampling-based planners for non-holonomic systems (2011), and developing Bézier curve-based online trajectory planning for car-like robots navigating geometrically unknown, crowded environments (2009). These contributions collectively reflect a sustained effort to make motion planning both theoretically sound and computationally practical. More recently, Li has expanded into natural language processing, contributing to aspect sentiment triplet extraction using dual graph convolutional networks that integrate affective knowledge and positional information (2023). This breadth demonstrates a versatile research profile that bridges robotics and AI, making Li's work relevant to students across multiple technical disciplines.