Zhuoqun Xu
I founded the PRS Organization and maintain its community, focusing on Embodied AI, Robotics, and generative agent. Prior to that, I earned my master's degree from the School of EECS at HNU. I completed my bachelor's degree at the School of Software Engineering at UPC.
Github
News
Recent Projects
With our collective expertise and diverse perspectives, we aim to facilitate the field by approaching AI and robotics from unique angles. Our goal is to make a meaningful impact on our community. Through our combined efforts, we strive to contribute in truly distinctive and transformative ways. Thank you for paying attention to this exciting venture, and I look forward to the innovative discoveries and collaborations that lie ahead.
PRS Challenge is a collaborative project with Apple, Peking University, Samsung Research.
Polar Research Station (PRS) Organization is an open-source organization dedicated to the research of general artificial intelligence and human-robot interaction, striving to create a better understanding of how AI can benefit society and improve the human experience.
Embodied robots are robots that can understand human language instructions and interact in scenarios to complete tasks. They are considered one of the most promising business scenarios in the near future, and many global companies are all competing to announce their progress in this field. We have invested years of effort in the field of embodied robots and have continuously achieved top results in international competitions, including human-robot interaction design, embodied navigation, and embodied instruction following.
At present, more and more work has begun to pay attention to the long-term housekeeping robot scene. Naturally, we wonder whether the robot can answer the questions raised by the owner according to the actual situation at home. These questions usually do not have a clear text context, are directly related to the actual scene, and it is difficult to find the answer from the general knowledge base. Therefore, the experience accumulated from the task seems to be a more natural choice.
Experience
Engaged in research on Embodied AI and Robotics. Responsible for developing new generation human-robot interaction and robotics technology. Participated in competitions, projects, and demo creation. Development of robot Systems in the Real World and simulation.
Research
I'm interested in Adaptive Learing, Embodied AI, Robotics, Human Simulation, AI Agent, LLM & MLLM, .etc.
- Human-centered In-building Embodied Delivery Benchmark
arXiv 2024 - Polar research station (PRS): A Virtual Human Society Environment for Generalist Embodied Agent Exploration
arXiv 2024 - PRS Challenge: Human Society Integration Exploration
2024 - Adaptive Projection Positioning Method for Fast Projector Robot Service in Indoor Scenee
2023 - Modular Method for Embodied Instruction Following with Environmental Context Adaptation
2023 - Defect Correction Method for Software Requirements Text Using Large Language Models
IJCNN 2023 - Modular-based Solution for Practical In-home Robot Routine Services with Fast Object Navigation and 6-DOF Grasping
CIRAC 2023 - Task-Driven and Experience-Based Question Answering Corpus for In-Home Robot Application in the House3D Virtual Environment
LREC 2022