Printer Friendly

Integration of autonomous vehicles and Industry 4.0.


Autonomous vehicles (AVs) and Mobility-as-a-Service (MaaS) can provide more efficient logistics and passenger transfer methods. Furthermore, smart sensors along with implementation of cognitive computing and the Internet of Things (IoT) represent an AV as a cyber-physical system (CPS), within which information from all related perspectives is closely monitored and synchronized between the physical devices and the cyber computational space. By utilizing advanced information analytics, AVs will be able to perform more efficiently, collaboratively and resiliently. Thus, it is possible to integrate AVs into Industry 4.0 systems. Competence and know-how about AVs as well as self-driving algorithms gained during ISEAUTO project presents a base for urban mobility studies. The paper presents ISEAUTO as a CPS that can be abstracted into sensing, computing, and actuation modules.

According to the report from McKinsey & Company, fully automated vehicles are unlikely to be commercially available before 2020 [1]. The implementation of AVs combing the application of MaaS or Transport-as-a-Service (TaaS) have become more realistic and meaningful. The readiness of these technologies empowers researchers to help industries to increase their productivity and create more benefits.

Since the term Industry 4.0 was first pushed by German government [2], it has been applied to a larger scope of technical elements and brought more connections between the virtual world and the physical one. Industry 4.0 describes a set of concepts that can drive the next industrial revolution. The potential of adopting the AVs into industrial area is promising for accommodating most technical concerns in the following areas:

* Cost-efficient: instead of traditional fuels, energy like electricity can reduce the cost and increase the effectiveness of manufacturing. Unmanned methods can also help to cut down expenses of employers' payments;

* Digitalization: using cloud computing to deal with big data captured by sensors from AVs help factories to keep control of all information and stay on track of the current status;

* Safety/Liability: real-time tracking and monitoring system ensure the safety during the vehicle operation. The avoidance of human intervention ensures better technology acceptance and a sustainable customer relationship;

* Flexibility/Scalability: involving more partners in this ecosystem brings more robustness and lowers the risk of dependency on a certain component, reaching continuously to different levels of investments and making the market more competitive;

* Environment-friendly: the reduction of the emissions of waste/pollution protects the living environment and adds satisfaction to surrounding residences. Clean energy also contributes to the whole production life circle thus completes the supply chain.


Self-driving vehicles are also foreseen to become a part of Industry 4.0. European technology platform ManuFuture (1) is developing a vision for 2030, where production logistics is integrated through self-driving mobile platforms both indoors and outdoors by artificial intelligence (AI), see Fig. 1.

Several initiatives are started in the world to integrate automated shuttles into industrial environment. However, most of the trials are still in early stages. Following use cases are reviewed in more details, a summary is presented in Table 1.

Foxconn (2). In 2017, Taiwanese firm Foxconn planned to build a $10 billion plant to the south of Milwaukee. They proposed that some lanes should be reserved only for AVs and the driverless-vehicle lanes could connect the Foxconn factory with Milwaukee's Mitchell International Airport. This plan would help Foxconn to automate its shipping of both goods and people. While accidents in US involving AVs have attracted attention in headlines, the advantage of such vehicles is safety, especially on dedicated routes with a constant ebb and flow of users.

Baidu (3). Under the agreement with SB Drive, ten Baidu Apolong mini buses will be exported to Japan from China in early 2019. Apolong buses are set to enter Japan's self-driving market as shuttle buses in practical use at the crippled Fukushima No. 1 nuclear power plant to transport workers within the facility. There is also a plan of using self-driving bus service for maintenance workers and tourists at Tokyo Haneda Airport.

Magride (4). Magride is a leading solution provider for short-range intelligent campus transportation in closed areas like airports, industrial plants, residential quarters and amusement parks. Its L4 shuttle bus G100 has already been used in Vanke Architecture Research Centerinstitute (Guangdong, China) for more than 1 year as a short-range transportation transferring employees. Its latest product G200 started pilot tests on open roads since August 2018.

Tsintel Technology (5). Their pilot tests started from August 2017 in Tianjin Huaming High-Tech Industrial Park (CHINA) with an L4 autonomous shuttle bus, operating in semi-open environments. The shuttle bus can provide commuting services at a low speed on fixed and controllable routes. It can also be managed as a fleet for campus commuting, logistics, road cleaning or even excursion tours.


Nowadays the most effective autonomous approach relies on data fusion of information, coming from plenty of different sensors, some of these sensors are already available on commercial cars [3], others will be introduced step-by-step. The research and development activities have to enable high/full autonomous driving; and Industry 4.0 has to deal with a lot of new requirements (e.g., fail-operational systems, cyber security), technologies (connectivity over 5G, neural networks, future computing platforms), and topics (data analytics, AI) [4].

ISEAUTO [5] last mile bus is operating in the campus of Tallinn University of Technology (TalTech) close to parking lots and some pedestrian areas. That means that an obstacle should be detected in both short and long distances at the same time. It is difficult to have an accurate and fast prediction of the pedestrian behaviour in case of the car in order to react properly. In case of a stop or a recalibration of sensors, situations can occur when a pedestrian is not detected properly due to overlapping with another pedestrian. In case of a jaywalker the system must be able to react and remain in a safe state. This holds also for people lying on the ground or small animals. In all possible situations the system has to be able to stop before any injury occurs. Sensors shown in Table 2 are used in ISEAUTO last mile bus to observe the environment and for mapping, localization and navigation processes.

Similar sensors are often used in industrial systems. For example, machine vision is widely implemented in adaptive industrial robots [6] and LiDARs for safety curtains.

With many national/regional schemes implemented, the autonomous vehicle market is getting more and more crowded these years. Year 2017 and 2018 have witnessed many players increasing their involvement in this global competition; and huge investments from all over the world chasing the same goal and trying to get a share from the market. A successful application of using AV as a service in industry needs to take certain criteria into consideration (see Fig. 2).

The ISEAUTO navigation technology doesn't require much fixed installation of infrastructure. It can be tailored to specific requirements in a cost-effective method, even for industry applications, from individual steps in a process to complex material flows. The advanced technology of the self-driving platform creates significant competitive advantages, while guaranteeing a high flexibility in operational procedures at the same time. Safety systems and an integrated system are a prerequisite for a safe and efficient human-machine interaction (HMI).

The unmanned operation is feasible in many industrial fields, for either individual or defined fleet operations. The automated vehicles are not tied to shift patterns, thus substantially increasing cost-effectiveness, while bringing reductions in daily operational damage. Despite of highly autonomous functions, the whole range of models can also be easily operated using conventional manual controlling mode and can well cope with potential technical issues like power cut-off, network failure etc.

Autonomous multi-agent systems, which optimize the planning and scheduling of industrial processes using the example of courier and express services is presented in [7], where the multi-agent-based approach is used for the optimization and synchronization of logistic and production processes in Industry 4.0 applications. Another research approach that nowadays receives attention in the industry is cellular transport systems. The idea of cellular transport systems [8] is embodied by dedicated (cellular) material handling entities. Cellular transport systems can be represented by autonomous conveying modules or transport vehicles. They are built upon a controlling architecture consisting of several small, self-organizing, intelligent units, which act and decide autonomously [8].


The proposed concept is integrating autonomous shuttle vehicles with multi-agent based workflow. The AI supported smart planning and scheduling of production involves self-driving vehicles into the process to serve intelligent resource transportation. In industry, performance indicators and energy efficiency are the most important factors to automate production [9]. These factors can be improved by smart production planning and scheduling service, which has all information from the production. It is important that all the equipment is connected to the cloud and provides real-time information about energy consumption, productivity and capacity. In case of the lack of this functionality, a monitoring system can be added also for older equipment as discussed in detail in [10]. By extending the production planning and scheduling with self-driving vehicle, much higher flexibility and efficiency can be achieved. Figure 3 is presenting the integration concept where production cells are physical units located all over the industrial area of the factory. One or more autonomous vehicles (AV 1, AV n) are serving the production units based on resource requests and guided commands from a cloud-based planning and scheduling system.

In the concept, several types of AVs can be applied for different purposes. Last mile shuttle buses like ISEAUTO are for transporting humans; universal mobile robot like [11] is for transporting goods and materials. The latter is also applied for different purposes in addition to transportation. For example, road cleaning or snow blowing during the idle time or securing the factory area in the night time.


In the near future, self-driving vehicles will take its place in everyday life and industry. Requirements from the Industry 4.0 are specified and the very first attempts of integration self-driving vehicles are reviewed in the paper.

ISEAUTO is the first research and educational project in Estonia targeted on the design and development of a self-driving vehicle. The potential of adopting ISEAUTO self-driving platform into Industry 4.0 is proposed in the paper. The long-term objective of the ISEAUTO project is to establish a smart city testbed where different types of rescarches regarding future urban mobility can be studied. The smart city testbed is a real-life environment where self-driving cars, delivery robots and smart infrastructure objects are placed. ISEAUTO last mile bus can be a base for Vehicle-to-everything (V2X) platform, a vehicular communication system that incorporates other more specific types of communication as Vehicle-to-infrastructure (V2I), Vehicle-to-vehicle (V2V) and Vehicle-to-pedestrian (V2P); V2D (Vehicle-to-device), V2G (Vehicle-to-grid), or any other entity that may affect the vehicle.


The project is supported by the TalTech and SilberAuto joint grant SS419. The publication costs of this article were covered by the Estonian Academy of Sciences.


[1.] Gao, P., Kaas, H. W., Mohr, D., and Wee, D. Disruptive trends that will transform the auto industry. McKinsey & Company.

[2.] Kagermann, H., Lukas, W.-D., and Wahlster, W. Industrie 4.0: Mit dem Internet der Dinge auf dem Weg zur 4. industriellen Revolution. VDI nachrichten, 2011, 13(11), 2.

[3.] Russo, G., Baccaglini, E., Boulard, L., Brevi, D., and Scopigno, R. Video processing for V2V communications: A case study with traffic lights and plate recognition. In Proceedings of 2015 IEEE 1st International Forum on Research and Technologies for Society and Industry Leveraging a better tomorrow (RTSI), Turin, Italy, September 16-18, 2015. IEEE, 2015, 144-148.

[4.] Traub, M., Vogel, H.-J., Sax, E., Streichert, T., and Harri, J. Digitalization in automotive and industrial systems. In Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition (DATE), Dresden, Germany, March 19-23, 2018. IEEE, 2018, 1203-1204.

[5.] Rassolkin, A., Sell, R., and Leier. M. Development Case Study of the First Estonian Self-Driving Car, ISEAUTO. Electr. Control Commun. Eng., 2018, 14(1), 81-88.

[6.] Kuts, V., Otto, T., Tahemaa, T., Bukhari, K., and Pataraia, T. Adaptive Industrial Robots Using Machine Vision. In Proceedings of the ASME 2018 International Mechanical Engineering Congress and Exposition (IMECE2018), Pittsburgh, PA, USA, November 9-15, 2018. ASME, 2019.

[7.] Gath, M., Herzog, O., and Edelkamp, S. Autonomous and flexible multiagent systems enhance transport logistics. In Proceedings of the 2014 11th International Conference and Expo on Emerging Technologies for a Smarter World (CEWIT), Melville, NY, USA, October 29-30 2014. IEEE 2014, 0-5.

[8.] Schieweck, S., Kern-Isberner, G., and Ten Hompel, M. Using answer set programming in an order-picking system with cellular transport vehicles. In Proceedings of the 2016 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Bali, Indonesia, December 4-7, 2016. IEEE 2016, 1600-1604.

[9.] Kaganski, S., Majak, J., Karjust, K., and Toompalu, S. (2017). Implementation of Key Performance Indicators Selection Model as Part of the Enterprise Analysis Model. Procedia CIRP, 2017, 63, 283-288.

[10.] Eiskop, T., Snatkin, A., and Karjust, K. Production monitoring system with predictive functionality. J. Eng. Sci. Technol., 2017, 12 (9), 2410-2425.

[11.] Sell, R. and Otto, T. Remotely controlled multi robot environment. In Proceedings of the 19th EAEEIE Annual Conference, Tallinn, Estonia, June 29-July 2, 2008. IEEE 2008, 20-25.

Isejuhtivate soidukite ja Toostus 4.0 integratsioon

Raivo Sell, Anton Rassolkin, Ruxin Wang ja Tauno Otto

Toostuse automatiseerimise ja digitaliseerimise jargmist sammu nimetatakse toostusrevolutsiooniks Toostus 4.0. Digitaliseerimine ei tahenda selles kontekstis mitte ainult tootmisprotsesside taiustamist, vaid ka tootmislogistika ja transpordi uusi integreeritud lahendusi. Autotoostuse ja eriti isejuhtivate soidukite ning autonoomsete susteemide kiire areng voimaldab luua taiesti uusi Toostus 4.0 lahendusi. Artiklis on uuritud erinevaid lahendusi, mida maailmas on puutud rakendada, ja valja pakutud TalTechi ning SilberAuto koostoos valminud isejuhtiva platformi ISEAUTO kontseptsioon Toostus 4.0 integreerimiseks, samuti analuusitud selle tootmislogistikasse rakendamise voimalusi.

Raivo Sell (a*), Anton Rassolkin (b), Ruxin Wang (a), and Tauno Otto (a)

(a) Department of Mechanical and Industrial Engineering, Tallinn University of Technology, Ehitajate tee 5, 19086 Tallinn, Estonia

(b) Department of Electrical Power Engineering and Mechatronics, Tallinn University of Technology, Ehitajate tee 5, 19086 Tallinn, Estonia

Received 12 April 2019, accepted 16 May 2019, available online 12 November 2019

(*) Corresponding author,





Table 1. Comparison of shuttle buses developed worldwide

    Case study          Location            State-of-art features

Foxconn Factory     Milwaukee, US     Reserved lanes on normal highways
                                      only for autonomous vehicles.
Baidu               Fukushima, Japan  Transport workers within the
                                      nuclear power plant facility.
Tsintel Technology  Tianjin, China    Provide commuting services at a
                                      low speed in semi-open
Magride             Guangdong, China  Serve as a short-range
                                      transportation transferring

    Case study      Status

Foxconn Factory     Plan

Baidu               Plan

Tsintel Technology  Pilot

Magride             Operate

Table 2. Sensors used in ISEAUTO last mile shuttle bus

       Sensor              Type         Quantity
LiDAR                 Velodyne VLP-16      2            Placement

LiDAR                 15[degrees] VFoD     1      Roof
Ultrasonic            PGA450-Q1            8      Front
Radar                 IWR1443              1      4 x front, 4 x back
Camera                Basler               5      Front
                                                  2 x front, 2 x sides,
Satellite navigation  RTK-GNSS+IMU         1      back
COPYRIGHT 2019 Estonian Academy Publishers
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2019 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Author:Sell, Raivo; Rassolkin, Anton; Wang, Ruxin; Otto, Tauno
Publication:Proceedings of the Estonian Academy of Sciences
Geographic Code:4EXES
Date:Dec 1, 2019
Previous Article:Suitability analysis of using industrial robots in manufacturing.
Next Article:Modular smart control system architecture for the mobile robot platform.

Terms of use | Privacy policy | Copyright © 2020 Farlex, Inc. | Feedback | For webmasters