Indoor Navigation with Deep Reinforcement Learning

Bakale, Vijayalakshmi A; S, Yeshwanth Kumar V; Roodagi, Vivekanand C; Kulkarni, Yashaswini N; Patil, Mahesh S.; Chickerur, Satyadhyan

doi:10.1109/icict48043.2020.9112385

Cited by 8 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The calculation results were then presented in the form of an interior navigation system. Bakale et al (2020) suggested deep learning to identify objects in the provided indoor scene and then used reinforcement learning to find a path. The suggested solution has provided the navigation path for approximately 2 minutes and 10 seconds.…”

Section: Indoor Navigation Using Mixed Realitymentioning

confidence: 99%

A Review: Current Trend of Immersive Technologies for Indoor Navigation and the Algorithms

Sariman,

Othman,

Mat Akir

et al. 2024

JST

View full text Add to dashboard Cite

The term “indoor navigation system” pertains to a technological or practical approach that facilitates the navigation and orientation of individuals within indoor settings, such as museums, airports, shopping malls, or buildings. Over several years, significant advancements have been made in indoor navigation. Numerous studies have been conducted on the issue. However, a fair evaluation and comparison of indoor navigation algorithms have not been discussed further. This paper presents a comprehensive review of collective algorithms developed for indoor navigation. The in-depth analysis of these articles concentrates on both advantages and disadvantages, as well as the different types of algorithms used in each article. A systematic literature review (SLR) methodology guided our article-finding, vetting, and grading processes. Finally, we narrowed the pool down to 75 articles using SLR. We organized them into several groups according to their topics. In these quick analyses, we pull out the most important concepts, article types, rating criteria, and the positives and negatives of each piece. Based on the findings of this review, we can conclude that an efficient solution for indoor navigation that uses the capabilities of embedded data and technological advances in immersive technologies can be achieved by training the shortest path algorithm with a deep learning algorithm to enhance the indoor navigation system.

show abstract

Section: Indoor Navigation Using Mixed Realitymentioning

confidence: 99%

A Review: Current Trend of Immersive Technologies for Indoor Navigation and the Algorithms

Sariman,

Othman,

Mat Akir

et al. 2024

JST

View full text Add to dashboard Cite

show abstract

“…Reinforcement learning [ 35 ] is a promising ML algorithm that learns a set of behaviors toward a defined goal based on the current state and environment. It could be used in the indoor navigation system [ 36 , 37 , 38 , 39 ] to provide an available path from the current position to an expected one.…”

Section: Related Workmentioning

confidence: 99%

Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach

Lin

Gan

Jiang

et al. 2023

Sensors

View full text Add to dashboard Cite

Indoor localization and navigation have become an increasingly important problem in both industry and academia with the widespread use of mobile smart devices and the development of network techniques. The Wi-Fi-based technology shows great potential for applications due to the ubiquitous Wi-Fi infrastructure in public indoor environments. Most existing approaches use trilateration or machine learning methods to predict locations from a set of annotated Wi-Fi observations. However, annotated data are not always readily available. In this paper, we propose a robot-aided data collection strategy to obtain the limited but high-quality labeled data and a large amount of unlabeled data. Furthermore, we design two deep learning models based on a variational autoencoder for the localization and navigation tasks, respectively. To make full use of the collected data, a hybrid learning approach is developed to train the models by combining supervised, unsupervised and semi-supervised learning strategies. Extensive experiments suggest that our approach enables the models to learn effective knowledge from unlabeled data with incremental improvements, and it can achieve promising localization and navigation performance in a complex indoor environment with obstacles.

show abstract

“…Some maps oversimplify the environment representation: the map is divided into a grid with equally-sized smaller cells that store information about the environment [68,73,93]. Others oversimplify the environment's structure by simplifying objects representation or by using 1D/2D to represent the environment [34,36,39,41,47,55,65,67,74,86,87] . The UAV has to plan a safe and optimal path over the cells to avoid cells containing obstacles until it reaches its destination and has to plan its stopover at the charging stations based on the battery level and path length.…”

Section: Map-based Navigationmentioning

confidence: 99%

Autonomous Unmanned Aerial Vehicle navigation using Reinforcement Learning: A systematic review

AlMahamid

Grolinger

2022

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Indoor Navigation with Deep Reinforcement Learning

Cited by 8 publications

References 14 publications

A Review: Current Trend of Immersive Technologies for Indoor Navigation and the Algorithms

A Review: Current Trend of Immersive Technologies for Indoor Navigation and the Algorithms

Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach

Autonomous Unmanned Aerial Vehicle navigation using Reinforcement Learning: A systematic review

Contact Info

Product

Resources

About