KAnIS Cooperative Autonomous Intralogistic Systems

Improving the efficiency of intralogistic processes via cooperative autonomous industrial trucks.

Intelligent networking and automation of internal industrial trucks
Project Management: Prof. Dr. Hans-Georg Stark
University: TH Aschaffenburg (UAS), Germany
Research Area: Intelligent Systems
Project duration: 03.2020–05.2023

IntelligentSystems   ArtificialIntelligenceDataSciences   ElectronicsElectricDrives   RoboticsAutomation   IntelligentMobility   IntelligentSensorsSignals   Prof.Dr.Stark


The automation of intralogistic processes is an important factor in sustainably securing the competitiveness of companies in a market characterised by globalisation and increased competition. Given the great importance of this topic, Aschaffenburg UAS has been cooperating with strong partners from the logistics industry in the field of applied research and development, for many years. These include, for example, Linde Material Handling GmbH, one of the world's leading manufacturers of industrial trucks and an industrial partner in the "Cooperative Autonomous Intralogistics Systems" (KAnIS) project funded by the Free State of Bavaria.


The purpose of the project is to develop new methods for the intelligent networking and automation of internal industrial trucks. Such an interconnected fleet should achieve a significant increase in the operational flow of goods and materials through cooperative behaviour in autonomous driving, order planning and order processing, as well as through the evaluation of an as comprehensive as possible database, and thus make a significant contribution in optimising the profitability and efficiency of intralogistic processes. The latest methods of artificial intelligence and machine learning are used for this purpose. Thematically, the project is divided into the sub-work packages "CoopLogistics" and "CoopAutonomy", which are described under Methods.


  • CoopLogistics: Optimization of task planning/ logistics
  • CoopAutonomy: Improved performance of autonomous trucks through enhanced cooperation



In this sub-project, a novel cooperative approach to automating internal industrial truck fleets is being researched. In this approach, methods for automatic track guidance of individual industrial trucks make the data from their environmental sensors, their position information and other important vehicle data available to a central unit, the cloud, via a communication platform and thus ensure a highy accurate following of the predefined path (see the following sketch). Conversely, to complement the data from the on-board sensors, each member of the fleet is also provided with important sensor information and vehicle data from the other individual industrial trucks, as well as the information from other sensors stationarily mounted on the premises, via radio transmission from the central unit. By means of a suitable sensor data fusion, all vehicles, regardless of their individual sensor equipment, have almost the same information about the vehicle environment (cooperative perception) and their own position (cooperative localisation) at their disposal.

Industrial trucks send information to the cloud

Another focus of the CoopAutonomy research project is the development of methods for automatic lane guidance of individual industrial trucks. Innovative control algorithms are being researched which, on the basis of the data provided by the cooperative perception and localisation, enable targeted control of the steering, drive and brake and thus ensure a highly accurate target path sequence (see the following sketch) and adherence to the specified target speed.

Sketch of the innovative control algorithms for an industrial truck


Particular attention is paid here to the strongly varying steering behaviour of the individual fleet members caused by the different individual industrial truck variants and variable vehicle parameters (e.g. variable vehicle mass and centre of gravity position due to load pick-up). The latter must be taken into account in the controll design in order to ensure stable control loop behaviour and thus safe vehicle guidance. The aim of the research is to develop a control and regulation concept that can be used universally for all individual industrial truck variants and which adapts itself to the variable individual industrial truck variants and vehicle parameters by using the latest machine learning methods.


The sub-project CoopLogistics is dedicated to the central question of what kind of new possibilities are opened up for optimising intralogistic processes through the targeted networking and cooperation of the individual fleet members. New strategies for order planning and order processing, predictive maintenance as well as energy and battery management of industrial trucks are being researched. The common feature of these strategies is the targeted evaluation of a data set that is as extensive as possible, provided cooperatively and fused in the cloud. Artificial intelligence methods, the latest network theory approaches (e.g. from graph theory) and discrete-event simulation methods are used here.

Important objectives of the optimisation of intralogistic processes are:

  • The increase of the internal flow of goods and materials and shortening goods and material throughput times
  • The acquisition of the maintenance and wear condition of the individual fleet members
  • Based on this, the realisation of intelligent order planning and predictive maintenance of the individual industrial truck members to prevent unnecessary downtimes
  • Reducing energy costs by integrating innovative energy management systems into autonomous and learning logistics systems
  • Maximising the operating times of the fleet members by implementing an intelligent battery/charging management system as well as an innovative inductive battery charging process for electrically driven individual industrial trucks.

Project Members

Consortium of Scientists

Prof. Dr.-Ing. Bochtler, Circuit & Measurement Technology, Radio Technology
Prof. Dr.-Ing. Doll, Automated Traffic Systems
Prof. Dr. Eley, Logistics, Optimization
Prof. Dr.-Ing. Krini, Signal Processing and Sensors
Prof.-Dr. Möckel, Mathematics, Machine Learning, Predictive Maintenance
Prof.Dr.-Ing. Mußenbrock, Energy Management and Efficiency
Prof. Dr. Stark, Mathematics, Signal Processing, Project Coordination
Prof. Dr.-Ing. Teigelkötter, Electrical Drive Technology, Battery Management
Prof. Dr.-Ing. Thielemann, Micro-System Technology & Sensors, Biological Neuronal Networks
Prof. Dr.-Ing. Zindler, Automation and Control Technology, Vehicle Control


R&D Programme "Information- and Communication Technology" Free State of Bavaria


Do you want to join our research team? Are you researching on a similar topic as professor, postgraduate or student? Are you looking for participation possibilities in a research project on this topic?

We will be happy to identify our cooperation potential. Please feel free to contact Prof. Dr. Stark.


Stefan Prokosch | Linde Material Handling GmbH

"For Linde Material Handling, automation is one of the future fields in which we are systematically investing. With the KAnIS research project, we are addressing the field of applications both for indoor- and outdoor-use, and with the counterbalance truck, also one of the most complex products for automation.

The broad scope of the project, the multitude of different topics, the great commitment of the professors, scientific staff, master's- and bachelor's students motivates us to make this research project a success every day. This strengthens Aschaffenburg as a science and business location and will hopefully lead to many more joint projects and innovations in the future.

For me, the regular exchange with all those involved is a welcome incubator for new solutions, innovative ideas and approaches. On this basis we can continue to develop first-class products and holistic solutions for our customers in the future."

Stefan Prokosch
SVP Productmanagement Industrial Trucks Counterbalance
Linde Material Handling GmbH, Deutschland

more on research activities on Intelligent Systems