Peiqi Liu | 刘沛淇

I am a junior undergraduate student major in computer science at Peking University, advised by Prof. Hao Dong as a part of PKU-Agibot Lab.

Currently I am a visiting student in MIT CSAIL, where I was advised by Jiayuan Mao, Prof. Leslie Pack Kaelbling and Prof. Josh Tenenbaum.

Always excited to discussing cool ideas and potential collaborations. Feel free to book a meeting with me!

Email / Github / LinkedIn / Book a Meeting

Research

The goal of my research is to empower robots to assist humans in their daily lives, with a particular focus on enabling them to explore unfamiliar environments, execute long-horizon plans, and manipulate objects with precision. My research interests include planning, representation learning, navigation and imitation learning.

	Lifelong Experience Abstraction and Planning Peiqi Liu, Joshua B. Tenenbaum, Leslie Pack Kaelbling, Jiayuan Mao ICML 2025 Workshop PRAL (Oral) A framework for lifelong experience abstraction and planning that enables agents to learn and adapt continuously across different environments and tasks.
	MO-DDN: A Coarse-to-Fine Attribute-based Exploration Agent for Multi-object Demand-driven Navigation Hongcheng Wang, Peiqi Liu, Wenzhe Cai, Mingdong Wu, Changxi Zheng, Zhengyu Qian, Hao Dong NeurIPS 2024 project page / arXiv We propose a multi-object demand-driven navigation benchmark and train an coarse-to-fine attribute-based exploration agent to solve this task.

Experience

	Massachusetts Institute of Technology 2024.6 - Present Visiting Student at MIT CSAIL Advisor: Jiayuan Mao, Prof. Leslie Kaelbling, Prof. Josh Tenenbaum
	Peking University (PKU) 2022.09 - Present Undergraduate student Research Advisor: Prof. Hao Dong