Dartmouth Events

Abstract: Visual-inertial systems with camera and IMU sensors are increasingly vital for navigation and spatial perception in platforms like mobile robots, extended reality (XR), and autonomous systems. These systems support applications such as autonomous driving, robotics, and augmented reality, enabling robots to sense, reason, and interact with their environments.

At the core of these systems lies the state estimation algorithm, which is essential for accurately estimating the state (i.e., pose) of the sensing platform and understanding the environment. Despite significant progress in visual-inertial navigation systems (VINS) and VI-SLAM (Simultaneous Localization and Mapping) over the past decade, critical aspects of system design remain underexplored, limiting their practical deployment. This talk will present advancements in consistent estimation algorithms, which not only improve the efficiency and accuracy of current methods but also enhance the safety and robustness of next-generation edge devices. Additionally, I will discuss innovations in scene understanding and multi-sensor fusion, and both are crucial for achieving reliable autonomy in diverse applications.

Bio: Chuchu Chen is a Ph.D. candidate in Mechanical Engineering (ME) at the University of Delaware (UD). She earned her bachelor's degree in Mechanical Engineering from Harbin Engineering University. Chuchu aims to develop intelligent systems that can reason and interact in complex environments. Her expertise spans nonlinear estimation, spatial perception, probabilistic sensing, calibration, and navigation for ground, aerial, underwater vehicles, and mobile devices. Her work has earned several prestigious awards, including being a Best Paper Award Finalist at ICRA 2024 and a Best Student Paper Award Finalist at RSS 2023. She also receives the University of Delaware Doctoral Fellowship for Excellence (2024).