Zero-shot object goal visual navigation

06/15/2022
by   Qianfan Zhao, et al.
18

Object goal visual navigation is a challenging task that aims to guide a robot to find the target object only based on its visual observation, and the target is limited to the classes specified in the training stage. However, in real households, there may exist numerous object 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 propose a zero-shot object navigation task by combining zero-shot learning with object goal visual navigation, which aims at guiding robots to find objects belonging to novel classes without any training samples. This task gives rise to the need to generalize the learned policy to novel classes, which is a less addressed issue of object navigation using deep reinforcement learning. To address this issue, we utilize "class-unrelated" data as input to alleviate the overfitting of the classes specified in the training stage. The class-unrelated input consists of detection results and cosine similarity of word embeddings, and does not contain any class-related visual features or knowledge graphs. Extensive experiments on the AI2-THOR platform show that our model outperforms the baseline models in both seen and unseen classes, which proves that our model is less class-sensitive and generalizes better. Our code is available at https://github.com/pioneer-innovation/Zero-Shot-Object-Navigation

READ FULL TEXT

page 2

page 13

page 14

research
07/19/2020

Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning

Zero-shot learning (ZSL) addresses the unseen class recognition problem ...
research
12/16/2018

Classifier and Exemplar Synthesis for Zero-Shot Learning

Zero-shot learning (ZSL) enables solving a task without the need to see ...
research
09/19/2023

Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill

Zero-shot object navigation is a challenging task for home-assistance ro...
research
02/05/2022

Zero Experience Required: Plug Play Modular Transfer Learning for Semantic Visual Navigation

In reinforcement learning for visual navigation, it is common to develop...
research
06/08/2021

RobustNav: Towards Benchmarking Robustness in Embodied Navigation

As an attempt towards assessing the robustness of embodied navigation ag...
research
08/18/2023

Taken by Surprise: Contrast effect for Similarity Scores

Accurately evaluating the similarity of object vector embeddings is of c...
research
02/03/2023

Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation

We propose a meta-ability decoupling (MAD) paradigm, which brings togeth...

Please sign up or login with your details

Forgot password? Click here to reset