Yifan Xu's Personal Website

Yifan Xu 徐一帆

I am an incoming Research Assistant Professor of Industry Engineering at the UT-Oak Ridge Innovation Institute (UT-ORII). I received my Ph.D. in Civil and Environmental Engineering from the University of Michigan, advised by Prof. Vineet R. Kamat and Prof. Carol C. Menassa, focusing on robotics, artificial intelligence, and the built environment.

My research lies at the intersection of construction robotics, assistive robotics, human-robot interaction, and multimodal AI in built and construction environments. I develop intelligent robotic systems that can perceive, reason, navigate, and collaborate with humans in complex real-world environments.

Email / CV / Linkedin

Research Interests

Physical AI and Robotics in Construction

Human-Robot Collaboration

Multimodal AI for Robotic Scene Understanding

Selected Publications

	KUKAloha: A General, Low-Cost, and Shared-Control based Teleoperation Framework for Construction Robot Arm Yifan Xu, Qizhang Shen, Vineet Kamat, Carol Menassa, under review, 2026 / arXiv A General, Low-Cost Teleoperation Framework for Construction Robot Arm
	Open-Vocabulary Semantic Segmentation with Uncertainty Alignment for Robotic Scene Understanding in Indoor Building Environments Yifan Xu, Vineet Kamat, Carol Menassa, JCCE(Journal of Computing in Civil Engineering), 2026 / Paper A 'Segment Detect Select' framework for open-vocabulary scene classification.
	UniPred: Unifying Deep Predicate Invention with Foundation Models Qianwei Wang, Bowen Li, Zhanpeng Luo, Yifan Xu, Alexander Gray, Tom Silver, Sebastian Scherer, Katia Sycara, Yaqi Xie, under review, 2026 / project page / arXiv Unifying deep predicate invention with foundation models for long horizon roboticplanning problems.
	OpenGuide: Assistive Object Retrieval in Indoor Spaces for Individuals with Visual Impairments Yifan Xu, Qianwei Wang, Vineet Kamat, Carol Menassa, Journal of Assistive Technologies (under review), 2025 / arXiv A model-based framework designed for robust object search in real world.
	Point2Graph: An End-to-end Point Cloud-based 3D Open-Vocabulary Scene Graph for Robot Navigation Yifan Xu, Ziming Luo, Qianwei Wang, Vineet Kamat, Carol Menassa, ICRA, 2025 project page / arXiv An end-to-end framework for generating the scene graph from point cloud directly.
	CoNav Chair: Development and Evaluation of a Shared Control-based Wheelchair for the Built Environment Yifan Xu, Qianwei Wang, Jordan Lillie Vineet Kamat, Carol Menassa, Clive D’Souza IEEE Transactions on Human-Machine Systems(under review), 2025 / arXiv The CoNav system demonstrated acceptable safety and performance laying the foundation for subsequent usability testing with people with disabilities.
	Socially-Aware Shared Control Navigation for Assistive Mobile Robots in the Built Environment" Yifan Xu, Qianwei Wang, Vineet Kamat, Carol Menassa, JCCE(Journal of Comupting in Civil Engineering), 2025 / arXiv A Socially-aware Shared Control-based Model Predictive Control with Dynamic Control Barrier Function (SS-MPC-DCBF) to adjust movements in real-time, integrating user preferences for safer, more autonomous navigation
	Solo t-dirl: Socially-aware dynamic local planner based on trajectory-ranked deep inverse reinforcement learning Yifan Xu, Theodor Chakhachiro, Tribhi Kathuria, Maani Ghaffari, ICRA, 2023 / Paper A new framework for a socially-aware dynamic local planner in crowded environments by building on the recently proposed Trajectory-ranked Maximum Entropy Deep Inverse Reinforcement Learning (T-MEDIRL)