Title:

Optimizing Intelligence: Building Resilient and Efficient Robot Autonomy

Abstract:

Motion planning is a fundamental challenge in robot autonomy, particularly for enabling real-time and resilient operation in complex environments, where trajectory generation and environment representation are key components. However, existing approaches often struggle to balance efficiency with adaptability under dynamic and uncertain conditions, offering only sub-optimal performance. This motivates the development of planning algorithms that approach theoretical optimality while remaining computationally efficient and robust to environmental variability.

In this talk, I will present recent work that integrates learning-based methods with optimization frameworks to address these challenges. Specifically, I will discuss techniques for generating high-quality dynamically feasible trajectories and constructing environment representations such as safe flight corridors. I will further illustrate how these methods contribute to advancing the theoretical foundations and practical capabilities of the next generation of autonomous robotic systems. Finally, I will discuss several extensions of this roadmap, including formulations for dynamic obstacle avoidance and multi-robot coordination.

Bio:

Yuwei Wu is a fourth-year Ph.D. student in the GRASP Laboratory at the University of Pennsylvania, advised by Prof. Vijay Kumar. Her research focuses on motion planning and trajectory optimization for mobile robots, with an emphasis on operation in dynamic, uncertain, and complex real-world environments. She received her B.Eng. degree in Transportation Engineering from Beijing Jiaotong University in 2019 and her M.S.E. degree in Systems Engineering from the University of Pennsylvania in 2022. Prior to her Ph.D., she worked with Prof. Fei Gao at Zhejiang University on trajectory optimization for quadrotors.