The Neural Compass: Probabilistic Relative Feature Fields for Robotic Search

TL;DR

This paper introduces ProReFF, a probabilistic feature field model trained on unlabeled data to predict relative feature distributions for robotic object search, significantly improving efficiency over baselines.

Contribution

ProReFF is a novel model that learns implicit object priors from unlabeled observations and a learning strategy for aligning inconsistent data, enhancing robotic search capabilities.

Findings

ProReFF captures meaningful feature relations in natural scenes.

The search agent using ProReFF is 20% more efficient than baselines.

The agent achieves up to 80% of human performance in simulated tasks.

Abstract

Object co-occurrences provide a key cue for finding objects successfully and efficiently in unfamiliar environments. Typically, one looks for cups in kitchens and views fridges as evidence of being in a kitchen. Such priors have also been exploited in artificial agents, but they are typically learned from explicitly labeled data or queried from language models. It is still unclear whether these relations can be learned implicitly from unlabeled observations alone. In this work, we address this problem and propose ProReFF, a feature field model trained to predict relative distributions of features obtained from pre-trained vision language models. In addition, we introduce a learning-based strategy that enables training from unlabeled and potentially contradictory data by aligning inconsistent observations into a coherent relative distribution. For the downstream object search task, we propose an agent that leverages predicted feature distributions as a semantic prior to guide exploration toward regions with a high likelihood of containing the object. We present extensive evaluations demonstrating that ProReFF captures meaningful relative feature distributions in natural scenes and provides insight into the impact of our proposed alignment step. We further evaluate the performance of our search agent in 100 challenges in the Matterport3D simulator, comparing with feature-based baselines and human participants. The proposed agent is 20% more efficient than the strongest baseline and achieves up to 80% of human performance.