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

TL;DR

PONI introduces a modular, interaction-free learning approach for ObjectGoal navigation that predicts potential functions from semantic maps, achieving state-of-the-art results with significantly reduced training costs.

Contribution

The paper presents a novel perception-based potential function network trained without environment interactions, enabling efficient and effective ObjectGoal navigation.

Findings

Achieves state-of-the-art performance on Gibson and Matterport3D datasets.

Reduces training computational cost by up to 1,600 times.

Demonstrates the effectiveness of interaction-free, perception-based learning for navigation.

Abstract

State-of-the-art approaches to ObjectGoal navigation 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 (x, y)?'. 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 ObjectGoal navigation. Experiments on Gibson and Matterport3D demonstrate that our method achieves the state-of-the-art for ObjectGoal navigation while incurring up to 1,600x less computational cost for training. Code and pre-trained models are available: https://vision.cs.utexas.edu/projects/poni/