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

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.

• 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