MASKOR Institut für Mobile Autonome Systeme und Kognitive Robotik
Refine
Year of publication
Institute
- MASKOR Institut für Mobile Autonome Systeme und Kognitive Robotik (81)
- Fachbereich Elektrotechnik und Informationstechnik (60)
- Fachbereich Maschinenbau und Mechatronik (23)
- IaAM - Institut für angewandte Automation und Mechatronik (17)
- ECSM European Center for Sustainable Mobility (3)
- Digitalisierung in Studium & Lehre (1)
- Fachbereich Luft- und Raumfahrttechnik (1)
- Fachbereich Wirtschaftswissenschaften (1)
- Rektoratskommission für Forschung und Entwicklung (1)
Document Type
- Conference Proceeding (52)
- Article (18)
- Part of a Book (9)
- Conference Poster (1)
- Contribution to a Periodical (1)
Keywords
- Industry 4.0 (4)
- Gamification (3)
- Automation (2)
- Autonomous mobile robots (2)
- Digital Twin (2)
- Field device (2)
- IO-Link (2)
- Multi-robot systems (2)
- Robotics (2)
- Smart factory (2)
Traditionally, agent architectures based on the Belief- Desire-Intention (BDI) model make use of precompiled plans, or if they do generate plans, the plans do not involve stochastic actions nor probabilistic observations. Plans that do involve these kinds of actions and observations are generated by partially observable Markov decision process (POMDP) planners. In particular for POMDP planning, we make use of a POMDP planner which is implemented in the robot programming and plan language Golog. Golog is very suitable for integrating beliefs, as it is based on the situation calculus and we can draw upon previous research on this. However, a POMDP planner on its own cannot cope well with dynamically changing environments and complicated goals. This is exactly a strength of the BDI model; the model is for reasoning over goals dynamically. Therefore, in this paper, we propose an architecture that will lay the groundwork for architectures that combine the advantages of a POMDP planner written in the situation calculus, and the BDI model of agency. We show preliminary results which can be seen as a proof of concept for integrating a POMDP into a BDI architecture.
Looking back on 20 years of RoboCup : Interview with Hans-Arthur Marsiske, writer and journalist
(2016)
We present golog++, a high-level agent programming and interfacing framework that offers a temporal constraint language to explicitly model layer-penetrating contingencies in low-level platform behavior. It can be used to maintain a clear separation between an agent's domain model and certain quirks of its execution platform that affect problem solving behavior. Our system reasons about the execution of an abstract (i.e. exclusively domain-bound) plan on a particular execution platform. This way, we avoid compounding the complexity of the planning problem while improving the modularity of both golog++ and the user code. On a run-through example from the well-known blocksworld domain, we demonstrate the entire process from domain modeling and platform modeling to plan transformation and platform-specific plan execution. © 2021 by SCITEPRESS - Science and Technology Publications, Lda.
This paper explores the basic concepts of Operational Design Domains (ODDs) in the field of autonomous driving. We address the intricacies of different scenario descriptions and promote the communication of system requirements and operational constraints in the context of Automated Driving Systems (ADSs).
Development of an Industry 4.0 ontology to enable semantic interoperability at the field level
(2025)
Industrial communication at the field level is highly dependent on the standards and their implementation on industrial PCs and Programmable Logic Controllers. The integration of industrial sensors and actuators requires manual configuration by plant operators and automation engineers. Nowadays interoperability plays an important role in Industry 4.0. For this the OPC UA Foundation and Platform Industrie 4.0 organization have published the Field Device eXchange and Asset Administration Shell standards, respectively, to define interoperable metadata models. However, there is no single way to define a field device metadata model and reuse it with other systems. This leads to heterogeneous data models and a lack of agreement on a generic semantic model for field devices. In this paper, we propose the Industry 4.0 Field Device Ontology to enable an interoperable semantic definition of field devices. The goal of this ontology is to reuse existing information from field devices, such as device description files, device profiles, and their application data. This paper covers the design of the ontology to enable semantic interoperability of field devices, the generalization of application data, and its implementation with the OWL 2 Web Ontology Language. The main contribution of our work is to provide the basic building blocks to enable the development of interoperable field device applications and integration with Industry 4.0 information model standards.
Ziel des Projektes Fluoreszenz ID von Altholz (FrIDAH) ist die Entwicklung eines Demonstrators gewesen, welcher die automatisierte Sortierung von Altholzproben gemäß der Altholzverordnung unter Verwendung der Messung von Fluoreszenzabklingzeiten ermöglicht. In diesem Beitrag werden der entwickelte Messaufbau, die Software, das Automatisierungssystem, sowie der Klassifikator vorgestellt. Die Ergebnisse zeigen, dass die verwendete Technologie zur zuverlässigen Klassifikation von Altholz geeignet ist und für die automatisierte Sortierung angewendet werden kann.
The use of industrial robots allows the precise manipulation of all components necessary for setting up a large-scale particle image velocimetry (PIV) system. The known internal calibration matrix of the cameras in combination with the actual pose of the industrial robots and the calculated transform from the fiducial markers to camera coordinates allow the precise positioning of the individual PIV components according to the measurement demands. In addition, the complete calibration procedure for generating the external camera matrix and the mapping functions for e.g. dewarping the stereo images can be automatically determined without further user interaction and thus the degree of automation can be extended to nearly 100%. This increased degree of automation expands the applications range of PIV systems, in particular for measurement tasks with severe time constraints.
In this chapter, we report on our activities to create and maintain a fleet of autonomous load haul dump (LHD) vehicles for mining operations. The ever increasing demand for sustainable solutions and economic pressure causes innovation in the mining industry just like in any other branch. In this chapter, we present our approach to create a fleet of autonomous special purpose vehicles and to control these vehicles in mining operations. After an initial exploration of the site we deploy the fleet. Every vehicle is running an instance of our ROS 2-based architecture. The fleet is then controlled with a dedicated planning module. We also use continuous environment monitoring to implement a life-long mapping approach. In our experiments, we show that a combination of synthetic, augmented and real training data improves our classifier based on the deep learning network Yolo v5 to detect our vehicles, persons and navigation beacons. The classifier was successfully installed on the NVidia AGX-Drive platform, so that the abovementioned objects can be recognised during the dumper drive. The 3D poses of the detected beacons are assigned to lanelets and transferred to an existing map.
To successfully develop and introduce concrete artificial intelligence (AI) solutions in operational practice, a comprehensive process model is being tested in the WIRKsam joint project. It is based on a methodical approach that integrates human, technical and organisational aspects and involves employees in the process. The chapter focuses on the procedure for identifying requirements for a work system that is implementing AI in problem-driven projects and for selecting appropriate AI methods. This means that the use case has already been narrowed down at the beginning of the project and must be completely defined in the following. Initially, the existing preliminary work is presented. Based on this, an overview of all procedural steps and methods is given. All methods are presented in detail and good practice approaches are shown. Finally, a reflection of the developed procedure based on the application in nine companies is given.