publications

Or browse publications by tag.

2025

1. 

   EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents

   llm multi-agent embodied-ai

   Junting Chen, Checheng Yu, Xunzhe Zhou, and 7 more authors

   In The Thirteenth International Conference on Learning Representations (ICLR), 2025

   Abs Website

   We present EMOS, an embodiment-aware heterogeneous multi-robot operating system powered by large language model (LLM) agents.

2. 

   OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis

   mobile-manipulation embodied-ai vlm

   Junting Chen, Haotian Liang, Lingxiao Du, and 8 more authors

   In Advances in Neural Information Processing Systems (NeurIPS), 2025

   Abs Website

   We present OWMM-Agent, a framework for open world mobile manipulation with multi-modal agentic data synthesis.

3. 

   LISN: Language-Instructed Social Navigation with VLM-based Controller Modulating

   navigation embodied-ai vlm

   Junting Chen, Yunchuan Li, Panfeng Jiang, and 5 more authors

   2025

   Abs Website

   We present the first simulation benchmark LISN-Bench for language instructed socially navigation benchmark with human-robot coexistence and high environment dynamic, and the fast-slow hierarchical system Social-Nav-Modulator to tackle the introduced social navigation tasks.

4. Manual2skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models

   manipulation vlm embodied-ai

   Chenrui Tie, Shengxiang Sun, Jinxuan Zhu, and 7 more authors

   In Robotics: Science and Systems (RSS), 2025

   Website
5. ArtGS: 3D Gaussian Splatting for Interactive Visual-Physical Modeling and Manipulation of Articulated Objects

   Gaussian Splatting 3DV embodied-ai

   Qiaojun Yu, Xibin Yuan, Yu Jiang, and 8 more authors

   In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025

   Website

2024

1. 

   RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation

   embodied-ai LLM manipulation

   Junting Chen, Yao Mu, Qiaojun Yu, and 11 more authors

   2024

   Abs arXiv

   We present RoboScript, a code generation framework for free-form manipulation tasks across both real and simulated environments.

2. 

   RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis

   embodied-ai llm manipulation

   Yao Mu, \textbfChen, Junting, Qing-Long Zhang, and 8 more authors

   In International Conference on Machine Learning(ICML), 2024

   Abs arXiv

   We present RoboCodeX, a multimodal code generation framework for table-top manipulation with physical preference priors.

3. Camon: Cooperative agents for multi-object navigation with llm-based conversations

   embodied-ai llm multi-agent

   Pengying Wu, Yao Mu, Kangjie Zhou, and 3 more authors

   arXiv preprint arXiv:2407.00632, 2024

   arXiv

2023

1. 

   How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers

   embodied-ai navigation

   Junting Chen, Guohao Li, Suryansh Kumar, and 2 more authors

   In Proceedings of Robotics: Science and Systems (RSS), 2023

   Abs DOI arXiv Video Website

   Object goal navigation is an important problem in Embodied AI that involves guiding the agent to navigate to an instance of the object category in an unknown environment—typically an indoor scene. We present a modular and training-free solution, which embraces more classic approaches, to tackle the object goal navigation problem. Our method builds a structured scene representation based on classic visual simultaneous localization and mapping (V-SLAM) framework and reasons about promising areas to search goal object by injecting semantics to geometric-based frontier exploration.