Zero-shot object goal visual navigation

TL;DR

This paper introduces a zero-shot object goal visual navigation framework that enables robots to find novel objects without prior training, leveraging semantic similarity and detection results to generalize across unseen classes.

Contribution

The paper proposes SSNet, a novel zero-shot navigation framework using semantic similarity, improving generalization to unseen object classes in visual navigation tasks.

Findings

Outperforms baseline models in zero-shot navigation tasks

Demonstrates strong generalization to novel object classes

Validated on the AI2-THOR platform

Abstract

Object goal visual navigation is a challenging task that aims to guide a robot to find the target object based on its visual observation, and the target is limited to the classes pre-defined in the training stage. However, in real households, there may exist numerous target classes that the robot needs to deal with, and it is hard for all of these classes to be contained in the training stage. To address this challenge, we study the zero-shot object goal visual navigation task, which aims at guiding robots to find targets belonging to novel classes without any training samples. To this end, we also propose a novel zero-shot object navigation framework called semantic similarity network (SSNet). Our framework use the detection results and the cosine similarity between semantic word embeddings as input. Such type of input data has a weak correlation with classes and thus our framework has the ability to generalize the policy to novel classes. Extensive experiments on the AI2-THOR platform show that our model outperforms the baseline models in the zero-shot object navigation task, which proves the generalization ability of our model. Our code is available at: https://github.com/pioneer-innovation/Zero-Shot-Object-Navigation.