NOLO: Navigate Only Look Once
This addresses the challenge of adapting visual navigation policies to new scenes without retraining, offering a solution for robotics and autonomous systems, though it is incremental as it builds on existing in-context learning and offline RL methods.
The paper tackles the problem of learning an in-context navigation policy from offline videos without environment access, proposing NOLO, which uses pseudo action labeling and offline RL to achieve significant performance gains over baselines in simulation and real-world scenes.
The in-context learning ability of Transformer models has brought new possibilities to visual navigation. In this paper, we focus on the video navigation setting, where an in-context navigation policy needs to be learned purely from videos in an offline manner, without access to the actual environment. For this setting, we propose Navigate Only Look Once (NOLO), a method for learning a navigation policy that possesses the in-context ability and adapts to new scenes by taking corresponding context videos as input without finetuning or re-training. To enable learning from videos, we first propose a pseudo action labeling procedure using optical flow to recover the action label from egocentric videos. Then, offline reinforcement learning is applied to learn the navigation policy. Through extensive experiments on different scenes both in simulation and the real world, we show that our algorithm outperforms baselines by a large margin, which demonstrates the in-context learning ability of the learned policy. For videos and more information, visit https://sites.google.com/view/nol0.