Sensors, Sensor Fusion, and Inter-connected Networked Autonomous Systems

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Networks".

Deadline for manuscript submissions: closed (31 December 2021) | Viewed by 7373

Special Issue Editors

Department of Engineering Sciences, University of Agder, Jon Lilletuns vei 9, 4879 Grimstad, Norway
Interests: sensors; sensor fusion; image/signal processing; ML; ADAS functionalities towards autonomous systems; IoT
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Autonomous and Cyber-Physical Systems Research Group, Department of Information and Communication Technology, University of Agder, Campus Grimstad, 4879 Grimstad, Norway
Interests: foundational and applied research to solve cutting-edge problems in these research areas; Internet of Things (IoT); cyber-physical systems; autonomous systems; robotics and automation involving advanced sensor systems; computer vision; thermal imaging; lidar imaging; radar imaging; wireless sensor networks; smart electronic systems; advanced machine learning techniques; connected autonomous systems
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The recent developments in sensors, sensor technologies, and increased computation with small form factor have helped develop complex systems incorporating a multitude of diverse sensors, processing heterogeneous data to retrieve the related information backed by statistical and probabilistic methods for robust decision-making and increased system performance. This has triggered the radical shift from the system with a centralized data processing pipeline, information retrieval and decision making to edge computing, where the above-mentioned processes take place near the data source, thus decreasing latency, increased efficiency, and robustness. Even though edge devices together with sensor and communication nodes have formed the basis of Internet of Things (IoT), Industrial IoT (IIoT), artificial intelligence-based (I)IoT (A(I)IoT), they are not sufficient for the present and future applications. Future applications, such as connected autonomous vehicles (CAVs), both UGVs and UAVs, harnessing energy from networked wind farm, weather forecasting, disaster management, automated load scheduling and forecasting employing renewable energy (solar, wind, tidal), smart cities, precision agriculture and intelligent transportation system require the interconnected networked system of systems.

For inter-connected networked autonomous systems, among various desirable functionalities, object recognition and tracking, navigation and collision avoidance, planning and control, robust real-time data processing and analysis, stochastic-based decision making, propagating information and control signal to constituent components, both inter and intra system, are of utmost importance, allowing them to make an independent decision based on the sensors data in a co-operative fashion. In this context, various algorithms and frameworks must be utilized, e.g. ML algorithms for object detection and 3D-point clouds; maximizing the efficiency of these algorithms in order to be able to process the large amount of heterogeneous data in real time from the various synchronized sensors, extracting the key useful information to take control decisions. Furthermore, converging humans and machine performance in a co-operative perspective, rather than a contrast and competing perspective, thus exploiting each other’s capabilities in an interactive way by mutual sharing of awareness in a way to benefit one other, would be one of the frontier requisites to harness inter-connected networked autonomous systems. This helps to create robust, reliable, and trustworthy ML with precise application in next generation inter-connected networked autonomous systems.

This, in turn, has put forward the demand for the evolution of “inter-connected networked autonomous systems” incorporating novel system architecture, constituent components, end-to-end robust sensing, perception, planning and control.  The deployment of these interconnected networked autonomous system of systems requires:

  • large amount of heterogeneous data from the various sensors, such as lidar, camera, radar, thermal camera, multi-spectral camera (MSI), hyper spectral camera (HSI) to be sensed;
  • robust, scalable and efficient data analysis pipeline using ML algorithms (incorporating boosting, Bayes’ inference, evolutionary algorithms) extending to real-time data analytics together with continual, federated and ensemble learning;
  • novel hardware—software architecture backed by algorithms development for co-operation and collaboration among different constituent components; both inter and intra system for low latency decision making and decision (control signal) propagation.

This defines the scope of this Special Issue (but not limited to)

  • Electro-optic and photonic sensors. Application of electro-optic and photonic sensors (laser, radar, etc.) for industrial applications, such as vibration measurement, imaging, distance, displacement, frequency and velocity measurement, object counting and scanning (e.g. for assembly and dis-assembly line)
  • Sensor performance. Recent developments in the sensor technologies enabling one to increase performance in terms of resolution, bandwidth, and other related sensor parameters
  • Signal processing and data analytics. Signal processing of data from—lidar, radar, vision systems such as—RGB camera, IR camera, hyperspectral imaging, multi-spectral imaging, (inverse) synthetic aperture radar (SAR, ISAR), and its application towards imaging, condition monitoring, predictive maintenance, prescriptive maintenance, asset monitoring
  • IoT, IIoT, AI-(I)IoT.
    • Recent and beyond state-of-the-art developments in these fields
    • Use of block chain in these areas for robust information and control flow
    • Novel wired, wireless or mixed network protocol and related architecture
    • Federated and ensemble together with ML for feature, data analytics and feature extraction
  • Perception in inter-connected networked autonomous systems.
    • Sensors, sensor fusion and signal processing heterogeneous data from various sensors
    • Novel ML-based algorithm incorporating evolutionary algorithm (e.g., CNN with genetic algorithm, etc.), Bayes’ inference, boosting algorithm
    • ML over network—federated learning; ensemble learning over networked edge nodes
    • Application in related fields, such as connected autonomous vehicles, both UAVs and UGVs for navigation, disaster management, inventory management, etc.
  • Autonomous navigation, decision, actuation, and control.
    • System architecture and description of connected UGV and UAVs
    • Use of RL for co-ordinate set of actions for unmanned aerial and ground vehicle in mixed-inventory transportation state
    • Deep reinforcement learning; multi-agent learning; multi-objective learning; converging simulated and real-world environment
    • Use of RL for control algorithm, e.g. precise movement of machinery in assembly/disassembly line or related industries for asset management and control algorithms.

Dr. Ajit Jha
Dr. Linga Reddy Cenkeramaddi
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Electro-optic and photonic sensors
  • Sensor performance
  • Signal processing and data analytics
  • Networked ML—federated, ensemble learning
  • IoT, IIoT, AI-(I)IoT
  • Autonomous navigation, decision, actuation, and control
  • Inter-connected networked autonomous systems
  • Connected autonomous vehicles, both UAVs and UGVs
  • Smart cities

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

17 pages, 4899 KiB  
Article
Localization of Multi-Class On-Road and Aerial Targets Using mmWave FMCW Radar
by Khushi Gupta, Soumya Joshi, M. B. Srinivas, Srinivas Boppu, M. Sabarimalai Manikandan and Linga Reddy Cenkeramaddi
Electronics 2021, 10(23), 2905; https://doi.org/10.3390/electronics10232905 - 24 Nov 2021
Cited by 3 | Viewed by 2407
Abstract
mmWave radars play a vital role in autonomous systems, such as unmanned aerial vehicles (UAVs), unmanned surface vehicles (USVs), ground station control and monitoring systems. The challenging task when using mmWave radars is to estimate the accurate angle of arrival (AoA) of the [...] Read more.
mmWave radars play a vital role in autonomous systems, such as unmanned aerial vehicles (UAVs), unmanned surface vehicles (USVs), ground station control and monitoring systems. The challenging task when using mmWave radars is to estimate the accurate angle of arrival (AoA) of the targets, due to the limited number of receivers. In this paper, we present a novel AoA estimation technique, using mmWave FMCW radars operating in the frequency range 77–81 GHz by utilizing the mechanical rotation. Rotating the radar also increases the field of view in both azimuth and elevation. The proposed method estimates the AoA of the targets, using only a single transmitter and receiver. The measurements are carried out in a variety of practical scenarios including pedestrians, a car, and an UAV, also known as a drone. With measured data, range-angle maps are created, and morphological operators are used to estimate the AoA of the targets. We also process radar range-angle images for improved visual representation. The proposed method will be extremely beneficial for practical ground stations, traffic control and monitoring frameworks for both on-ground and airborne vehicles. Full article
Show Figures

Figure 1

13 pages, 3464 KiB  
Article
A Velocity Estimation Technique for a Monocular Camera Using mmWave FMCW Radars
by Aarav Pandya, Ajit Jha and Linga Reddy Cenkeramaddi
Electronics 2021, 10(19), 2397; https://doi.org/10.3390/electronics10192397 - 30 Sep 2021
Cited by 4 | Viewed by 2547
Abstract
Perception in terms of object detection, classification, and dynamic estimation (position and velocity) are fundamental functionalities that autonomous agents (unmanned ground vehicles, unmanned aerial vehicles, or robots) have to navigate safely and autonomously. To date, various sensors have been used individually or in [...] Read more.
Perception in terms of object detection, classification, and dynamic estimation (position and velocity) are fundamental functionalities that autonomous agents (unmanned ground vehicles, unmanned aerial vehicles, or robots) have to navigate safely and autonomously. To date, various sensors have been used individually or in combination to achieve this goal. In this paper, we present a novel method for leveraging millimeter wave radar’s (mmW radar’s) ability to accurately measure position and velocity in order to improve and optimize velocity estimation using a monocular camera (using optical flow) and machine learning techniques. The proposed method eliminates ambiguity in optical flow velocity estimation when the object of interest is at the edge of the frame or far away from the camera without requiring camera–radar calibration. Moreover, algorithms of various complexity were implemented using custom dataset, and each of them successfully detected the object and estimated its velocity accurately and independently of the object’s distance and location in frame. Here, we present a complete implementation of camera–mmW radar late feature fusion to improve the camera’s velocity estimation performance. It includes setup design, data acquisition, dataset development, and finally, implementing a lightweight ML model that successfully maps the mmW radar features to the camera, allowing it to perceive and estimate the dynamics of a target object without any calibration. Full article
Show Figures

Figure 1

16 pages, 582 KiB  
Article
Multi-Objective GRASP for Maximizing Diversity
by Pedro Casas-Martínez, Alejandra Casado-Ceballos, Jesús Sánchez-Oro and Eduardo G. Pardo
Electronics 2021, 10(11), 1232; https://doi.org/10.3390/electronics10111232 - 22 May 2021
Cited by 5 | Viewed by 1523
Abstract
This work presents a novel greedy randomized adaptive search procedure approach for dealing with the maximum diversity problem from a multi-objective perspective. In particular, five of the most extended diversity metrics were considered, with the aim of maximizing all of them simultaneously. The [...] Read more.
This work presents a novel greedy randomized adaptive search procedure approach for dealing with the maximum diversity problem from a multi-objective perspective. In particular, five of the most extended diversity metrics were considered, with the aim of maximizing all of them simultaneously. The metrics considered have been proven to be in conflict, i.e., it is not possible to optimize one metric without deteriorating another one. Therefore, this results in a multi-objective optimization problem where a set of efficient solutions that are diverse with respect to all the metrics at the same time must be obtained. A novel adaptation of the well-known greedy randomized adaptive search procedure, which has been traditionally used for single-objective optimization, was proposed. Two new constructive procedures are presented to generate a set of efficient solutions. Then, the improvement phase of the proposed algorithm consists of a new efficient local search procedure based on an exchange neighborhood structure that follows a first improvement approach. An effective exploration of the exchange neighborhood structure is also presented, to firstly explore the most promising ones. This feature allowed the local search proposed to limit the size of the neighborhood explored, resulting in an efficient exploration of the solution space. The computational experiments showed the merit of the proposed algorithm, when comparing the obtained results with the best previous method in the literature. Additionally, new multi-objective evolutionary algorithms derived from the state-of-the-art were also included in the comparison, to prove the quality of the proposal. Furthermore, the differences found were supported by non-parametric statistical tests. Full article
Show Figures

Figure 1

Back to TopTop