Yumeng Xiu
Think geometrically, prove algebraically. ——John Tate
I am a Ph.D. student at Department of Mechanical Engineering, CMU. I am broadly interested in robotics, learning to control and optimization, my research goal is to develop real autonomous intelligent robots. Particularly, my recent researches focus on following directions:
Safe Navigation and robotics: Safe exploration and navigation is one of the most fundamental components of robot autonomy. Therefore, an accurate perception system and safe trajectory planning/prediction algorithms become necessary for safe navigation in complex environments. My goal is to develop rigorous algorithms to enable safe and autonomous actions in the field of robotics and apply them on real-world applications. Toward this goal, I’ve worked on research projects of Vision Aided Path Planning, Perception and Obstacle Avoidance, and Multi-robot Social Navigation to enrich my experince.
Learning to control: While control theory provides useful concepts and tools for machine learning, machine learning can be used the other way around to solve large control problems.I believe that combining these two could help develop reliable algorithms for stabilizing large-scale systems in practice, including power systems, robot teams, etc. Toward this goal, I’ve been working on the project of Learning-based Control on Large Power System
Previously in my Master study, I worked on multi-robot social navigation with Prof. Jiachen Li, developing learning-based control algorithms with Prof. Guannan Qu, developing perceptio and planning algorithms for aerial vehicles with Prof. Kenji Shimada.
My up-to-date Curriculum: CV
Besides research, I enjoy music arranging, photography and philosophy. I’m a fan of Albert Camus and Victor Hugo.
News
Nov, 2023: Our work Low computational-cost detection and tracking of dynamic obstacles for mobile robots with RGB-D cameras is accepted by RA-L!
Jun, 2023: Our recent work A vision-based autonomous UAV inspection framework for unknown tunnel construction sites with dynamic obstacles is accepted by RA-L!
March, 2023: Our work Compositional Neural Certificates for Networked Dynamical Systems is accepted by L4DC 2023!
Jan, 2023: Our work Vision-aided UAV Navigation and Dynamic Obstacle Avoidance using Gradient-based B-spline Trajectory Optimization is accepted by ICRA 2023!
Jan, 2023: Our work A real-time dynamic obstacle tracking and mapping system for UAV navigation and collision avoidance with an RGB-D camera is accepted by ICRA 2023!