RESEARCH

My research interests lie in the design of autonomous systems that advance the deployability of service robots operating in open-world environments. My research and project experience span planning, human–robot interaction, and service robot system design. I particularly aim to bridge the gap between robotics research and real-world deployment in socially aware scenarios.

I define open-world problems as misalignment among human intent, a rational robot’s internal representations, and the underlying knowledge of the operating environment. Specifically, they are characterized by (1) natural and unconstrained human instruction to robots, (2) incomplete environmental knowledge at both the semantic and geometric levels, and (3) humans’ implicit models of tasks and expectations.

I adopt a system design grounded in compositionality and modularity, and advocate the principle of Rationally Engineering Rational Robots. I view human-centric rationality as emerging from structured representations that link semantic concepts to their grounding in the physical world, while retaining unstructured flexibility to handle open-world uncertainty and human intent. At the low level, I develop robust navigation and manipulation systems that passively tolerate unforeseen objects and environments. At the high level, I design systems and algorithms that proactively expand the robot's representations and models.

Open-world Interaction

GSON

GSON: A Group-based Social Navigation Framework with Large Multimodal Model

IEEE Robotics and Automation Letters (RA-L) 2025.

Shangyi Luo, Peng Sun, Ji Zhu, Yuhong Deng, Cunjun Yu, Anxing Xiao (Mentor), Xueqian Wang

TL;DR: Group-aware social navigation using large multimodal models for socially-aware robot motion.

Robi Butler

Robi Butler: Multimodal Remote Interactions with a Household Robot Assistant

IEEE International Conference on Robotics and Automation (ICRA) 2025.

Anxing Xiao, Nuwan Janaka, Tianrun Hu, Anshul Gupta, Kaixin Li, Cunjun Yu, David Hsu

TL;DR: Remote multimodal (language + gesture) interactions with household robots.

Quadruped Guidance Robot

Quadruped Guidance Robot for the Visually Impaired: A Comfort-Based Approach

IEEE International Conference on Robotics and Automation (ICRA) 2023.

Yanbo Chen, Zhengzhe Xu, Zhuozhu Jian, Gengpan Tang, Yunong Yangli, Anxing Xiao (Mentor), Xueqian Wang, Bin Liang

TL;DR: Comfort-based guidance that safely leads visually impaired users through complex environments.

Robotic Guide Dog

Robotic Guide Dog: Leading a Human with Leash-Guided Hybrid Physical Interactions

IEEE International Conference on Robotics and Automation (ICRA) 2021.

Anxing Xiao*, Wenzhe Tong*, Lizhi Yang*, Jun Zeng, Zhongyu Li, Koushil Sreenath

ICRA Best Paper Award Finalist for Service Robotics.

TL;DR: The world's first robotic guide dog that can lead visually impaired to safely travel in a confined space.

Open-world Reasoning

ApBot

Robot Operation of Home Appliances by Reading User Manuals

Conference on Robot Learning (CoRL) 2025.

Jian Zhang, Hanbo Zhang, Anxing Xiao, David Hsu

TL;DR: Read and follow user manuals to operate home appliances autonomously.

Octopi

Octopi: Object Property Reasoning with Large Tactile-Language Models

Robotics: Science and Systems (RSS) 2024.

Samson Yu, Kelvin Lin, Anxing Xiao, Jiafei Duan, and Harold Soh

TL;DR: Combine tactile sensing with language to infer physical properties via interaction.

LLM-State

LLM-State: Expandable State Representation for Long-horizon Task Planning in the Open World

Preprint 2024.

Siwei Chen, Anxing Xiao, David Hsu

TL;DR: Maintain and expand object attributes for long-horizon planning in open worlds.

Open-world Capability

MimicFunc

MimicFunc: Imitating Tool Manipulation from a Single Human Video via Functional Correspondence

Conference on Robot Learning (CoRL) 2025.

Chao Tang, Anxing Xiao, Yuhong Deng, Tianrun Hu, Wenlong Dong, Hanbo Zhang, David Hsu, Hong Zhang

TL;DR: Learn tool-use from a single human video via functional correspondence.

CHD

CHD: Coupled Hierarchical Diffusion for Long-Horizon Tasks

Conference on Robot Learning (CoRL) 2025.

Ce Hao, Anxing Xiao, Zhiwei Xue, Harold Soh

TL;DR: Hierarchical diffusion for planning and executing long-horizon robotic tasks.

Trolley Collection

Robotic Autonomous Trolley Collection with Progressive Perception and Nonlinear Model Predictive Control

IEEE International Conference on Robotics and Automation (ICRA) 2022.

Anxing Xiao*, Hao Luan*, Ziqi Zhao*, Yue Hong, Jieting Zhao, Jiankun Wang, Max Q-H Meng

TL;DR: Compact robot collects unmarked trolleys in dynamic, complex environments.

Collaborative Trolley Transportation

Collaborative Trolley Transportation System with Autonomous Nonholonomic Robots

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023.

Bingyi Xia, Hao Luan, Ziqi Zhao, Xuheng Gao, Peijia Xie, Anxing Xiao (Mentor), Jiankun Wang, Max Q-H Meng

TL;DR: Multi-robot system for collaborative trolley transportation in crowded spaces.

PUTN

PUTN: A Plane-fitting based Uneven Terrain Navigation Framework

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022.

Zhuozhu Jian, Zihong Lu, Xiao Zhou, Bin Lan, Anxing Xiao (Mentor), Xueqian Wang, Bin Liang

TL;DR: Plane-fitting based navigation for effective traversal on uneven terrain.

Jumping Quadruped

Autonomous Navigation with Optimized Jumping through Constrained Obstacles on Quadrupeds

IEEE Conference on Automation Science and Engineering (CASE) 2021.

Scott Gilroy, Derek Lau, Lizhi Yang, Ed Izaguirre, Kristen Biermayer, Anxing Xiao, Mengti Sun, Ayush Agrawal, Jun Zeng, Zhongyu Li, Koushil Sreenath

TL;DR: Enable quadrupeds to jump through window-shaped obstacles during navigation.