SIAI Seminar Series: Open Questions in Open-World Navigation: Representation, Data, and Evaluation

ABSTRACT

As foundation models push AI toward generalization, open-world navigation offers a concrete testbed for understanding how representation, data, and evaluation must evolve together. Building robust open-world navigation systems requires bridging high-level semantic reasoning with reliable low-level control. In this seminar, I will discuss three central challenges. First, representation: while metric maps remain essential for local safety, graph-based abstractions enable flexible long-horizon planning under uncertainty, serving as a lightweight cognitive layer for scalable spatial reasoning. Second, data: I will present a framework that learns human-like urban navigation behaviors from uncurated web videos, avoiding costly on-robot data collection. Third, evaluation: I will introduce a high-fidelity real-to-sim approach that closes the visual and geometric sim-to-real gap and enables reproducible benchmarking. I will conclude with a vision for unifying classical robotics and foundation models into a navigation stack that is both reliable and scalable in open-world environments.

BIOGRAPHY

Chen Feng is an Institute Associate Professor at New York University, Director of the AI4CE Lab, and Founding Co-Director of the NYU Center for Robotics and Embodied Intelligence. He has also been an Amazon Scholar with its Frontier AI & Robotics team since 2026. His research focuses on active and collaborative robot perception and robot learning to address multidisciplinary, use-inspired challenges in construction, manufacturing, and transportation. He is dedicated to developing novel algorithms and systems that enable intelligent agents to understand and interact with dynamic, unstructured environments. Before NYU, he worked as a research scientist in the Computer Vision Group at Mitsubishi Electric Research Laboratories (MERL) in Cambridge, Massachusetts, where he developed patented algorithms for localization, mapping, and 3D deep learning in autonomous vehicles and robotics. Chen Feng earned his doctoral and master's degrees from the University of Michigan between 2010 and 2015, and his bachelor's degree in 2010 from Wuhan University. Chen is an active contributor to the AI and robotics communities, such as CVPR, IEEE RA-L, and ICRA, and he has served as an area chair and associate editor. In 2023, he was awarded the NSF CAREER Award. More information about his research can be found at ai4ce.github.io.