Student First Author: yes
Keywords: instruction following, language models, vision-based navigation
TL;DR: We can utilize pre-trained models of images and language to provide a textual interface to visual navigation models, enabling zero-shot instruction following robots in the real world!
Abstract: Goal-conditioned policies for robotic navigation can be trained on large, unannotated datasets, providing for good generalization to real-world settings. However, particularly in vision-based settings where specifying goals requires an image, this makes for an unnatural interface. Language provides a more convenient modality for communication with robots, but contemporary methods typically require expensive supervision, in the form of trajectories annotated with language descriptions. We present a system, LM-Nav, for robotic navigation that enjoys the benefits of training on unannotated large datasets of trajectories, while still providing a high-level interface to the user. Instead of utilizing a labeled instruction following dataset, we show that such a system can be constructed entirely out of pre-trained models for navigation (ViNG), image-language association (CLIP), and language modeling (GPT-3), without requiring any fine-tuning or language-annotated robot data. LM-Nav extracts landmarks names from an instruction, grounds them in the world via the image-language model, and then reaches them via the (vision-only) navigation model. We instantiate LM-Nav on a real-world mobile robot and demonstrate long-horizon navigation through complex, outdoor environments from natural language instructions.
Supplementary Material: zip