PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning

Abstract

State-of-the-art approaches to ObjectGoal navigation (ObjectNav) rely on reinforcement learning and typically require significant computational resources and time for learning. We propose Potential functions for ObjectGoal Navigation with Interaction-free learning (PONI), a modular approach that disentangles the skills of 'where to look?’ for an object and 'how to navigate to <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(x,\ y)$</tex> ?’. Our key insight is that 'where to look?’ can be treated purely as a perception problem, and learned without environment interactions. To address this, we propose a network that predicts two complementary potential functions conditioned on a semantic map and uses them to decide where to look for an unseen object. We train the potential function network using supervised learning on a passive dataset of top-down semantic maps, and integrate it into a modular framework to perform ObjectNav. Experiments on Gibson and Matterport3D demonstrate that our method achieves the stateof-the-art for ObjectNav while incurring up to <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$1,600\times less$</tex> computational cost for training. Code and pre-trained models are available. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> Website: https://vision.cs.utexas.edu/projects/poni/