PEANUT: Predicting and Navigating to Unseen Targets
This addresses the problem of navigating to unseen objects in unfamiliar settings for robotics and AI systems, offering a lightweight and data-efficient incremental improvement over existing methods.
The paper tackles efficient ObjectGoal navigation in novel environments by predicting unseen target locations from incomplete semantic maps, achieving state-of-the-art results on HM3D and MP3D datasets without additional training data.
Efficient ObjectGoal navigation (ObjectNav) in novel environments requires an understanding of the spatial and semantic regularities in environment layouts. In this work, we present a straightforward method for learning these regularities by predicting the locations of unobserved objects from incomplete semantic maps. Our method differs from previous prediction-based navigation methods, such as frontier potential prediction or egocentric map completion, by directly predicting unseen targets while leveraging the global context from all previously explored areas. Our prediction model is lightweight and can be trained in a supervised manner using a relatively small amount of passively collected data. Once trained, the model can be incorporated into a modular pipeline for ObjectNav without the need for any reinforcement learning. We validate the effectiveness of our method on the HM3D and MP3D ObjectNav datasets. We find that it achieves the state-of-the-art on both datasets, despite not using any additional data for training.