Yufei Ding | 丁昱菲

I am a junior in Zhi Class at the School of Electronic Engineering and Computer Science(EECS) of Peking University, where I lead the Academic Committee of Intelligence Science and Technology (ACIST). I major in Artificial Intelligence, with GPA ranking 1^st. I am currently advised by Prof. He Wang at Embodied Perception and InteraCtion (EPIC) Lab, and was previously an intern at Shanghai Artificial Intelligence Laboratory. My research interest lies in robotics and 3D vision, with the goal of enabling embodied agents to tackle complex tasks in 3D environments.

Email  /  Github /  WeChat Official Account /  quote of the day

@misc{geng2025roboverse,
title={RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning},
author={Haoran Geng and Feishi Wang and Songlin Wei and Yuyang Li and Bangjun Wang and Boshi An and Charlie Tianyue Cheng and Haozhe Lou and Peihao Li and Yen-Jen Wang and Yutong Liang and Dylan Goetting and Chaoyi Xu and Haozhe Chen and Yuxi Qian and Yiran Geng and Jiageng Mao and Weikang Wan and Mingtong Zhang and Jiangran Lyu and Siheng Zhao and Jiazhao Zhang and Jialiang Zhang and Chengyang Zhao and Haoran Lu and Yufei Ding and Ran Gong and Yuran Wang and Yuxuan Kuang and Ruihai Wu and Baoxiong Jia and Carlo Sferrazza and Hao Dong and Siyuan Huang and Koushil Sreenath and Yue Wang and Jitendra Malik and Pieter Abbeel}, year={2025},
primaryClass={cs.RO},
url={https://roboverse.wiki},
}

We propose RoboVerse, a comprehensive framework for advancing robotics through a simulation platform, synthetic dataset, and unified benchmarks. Its MetaSim infrastructure abstracts diverse simulators into a universal interface, ensuring interoperability and extensibility. RoboVerse improves sim-to-real transfer and enables consistent evaluation for imitation and reinforcement learning, addressing key challenges in scaling robotic data and benchmarking.

We introduce the concept of semantic orientation and propose a generalizable model for language-grounded spatial reasoning and robot manipulation.

@INPROCEEDINGS{10802733,
author={Ding, Yufei and Geng, Haoran and Xu, Chaoyi and Fang, Xiaomeng and Zhang, Jiazhao and Wei, Songlin and Dai, Qiyu and Zhang, Zhizheng and Wang, He},
booktitle={2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
title={Open6DOR: Benchmarking Open-instruction 6-DoF Object Rearrangement and A VLM-based Approach},
year={2024},
volume={},
number={},
pages={7359-7366},
keywords={Three-dimensional displays;Benchmark testing;Propulsion;6-DOF;Real-time systems;Artificial intelligence;Intelligent robots;Synthetic data},
doi={10.1109/IROS58592.2024.10802733}
}

We present Open6DOR, a challenging and comprehensive benchmark for open-instruction 6-DoF object rearrangement tasks. Following this, we propose a zero-shot method, Open6DORGPT, which achieves SOTA performance and proves effective in demanding simulation environments and real-world scenarios.

We synthesized a large-scale dexterous grasping dataset in cluttered scenes and designed a generative framework to learn grasping in the real world.

Simulately is a project where we gather useful information of robotics & physics simulators for cutting-edge robot learning research.