Time-optimal Trajectory Optimization
Structured motion plans for dynamically feasible robot maneuvers in cluttered spaces.
I'm Yuwei, a final-year Ph.D. student in Electrical and Systems Engineering at the University of Pennsylvania and a member of the General Robotics, Automation, Sensing, and Perception (GRASP) Laboratory, advised by Prof. Vijay Kumar. Before my doctoral research, I worked with Prof. Fei Gao at Zhejiang Uiversity on trajectory optimization for quadrotors.
My work has published in IEEE RA-L, T-ITS, T-ASE, ICRA, IROS, MRS, WAFR and DARS, and has received recognition including selection as an IROS 2025 Best Paper Award Finalist, a Best Paper Award nomination at DARS 2024, and an Oral Highlight at the ICRA 2025 Doctoral Consortium. I also contribute to the robotics community as a Guest Editor for Autonomous Robots, student representative on the IEEE TC on Aerial Robotics and UAVs, and an organizer of workshops at RSS and IROS. I have reviewed more than 100 submissions across over 10 robotics journals and conferences.
A central question underlying my work is: How can we identify the right level of abstraction to reduce complexity while preserving the essential structure needed for robot motion planning and decision-making?
Guided by this perspective, I develop physical, geometric, and semantic abstractions that provide a common foundation for integrating optimization, control, data-driven methods, and foundation models toward reliable embodied AI.
Structured motion plans for dynamically feasible robot maneuvers in cluttered spaces.
Efficient representations of safe regions that keep planning light yet reliable.
Robust policies that keep teams resilient under uncertainty and hazards.
Launch the motion planning demos to experiment with trajectories in your browser.