120 Minutes and a Laptop: Minimalist Image-goal Navigation via Unsupervised Exploration and Offline RL

Read full text Summarise with VIRAT
Authors: Xiaoming Liu, Borong Zhang, Qingbiao Li, Steven Morad
Cited by: 0
References: 17

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The prevailing paradigm for image-goal visual navigation often assumes access to large-scale datasets, substantial pretraining, and significant computational resources. In this work, we challenge this assumption. We show that we can collect a dataset, train an in-domain policy, and deploy it to the real world (1) in less than 120 minutes, (2) on a consumer laptop, (3) without any human intervention. Our method, MINav, formulates image-goal navigation as an offline goal-conditioned reinforcement learning problem, combining unsupervised data collection with hindsight goal relabeling and offline policy learning. Experiments in simulation and the real world show that MINav improves exploration efficiency, outperforms zero-shot navigation baselines in target environments, and scales favorably with dataset size. These results suggest that effective real-world robotic learning can be achieved with high computational efficiency, lowering the barrier to rapid policy prototyping and deployment.

Fields of Study & Subjects

Reinforcement Learning in Robotics Robot Manipulation and Learning Robotics and Sensor-Based Localization

Publication details

Journal / source
arXiv (Cornell University)
Publication date
27 March 2026
Language
EN
Document type
Preprint