\n \n \n
\n
\n\n \n \n \n \n \n \n Towards a Lifelong Mapping Approach Using Lanelet 2 for Autonomous Open-Pit Mine Operations.\n \n \n \n \n\n\n \n Eichenbaum, J.; Nikolovski, G.; Mülhens, L.; Reke, M.; Ferrein, A.; and Scholl, I.\n\n\n \n\n\n\n In
19th IEEE International Conference on Automation Science and Engineering (CASE), pages 1–8, Aug 2023. \n
\n\n
\n\n
\n\n
\n\n \n \n ieeexpl\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@InProceedings{Eichenbaum-etAl_CASE2023_Towards-Lifelong-Mapping,\n author = {Eichenbaum, Julian and Nikolovski, Gjorgji and M{\\"u}lhens, Leon\n and Reke, Michael and Ferrein, Alexander and Scholl, Ingrid},\n title = {Towards a Lifelong Mapping Approach Using Lanelet 2 for Autonomous Open-Pit Mine Operations}, \n booktitle = {19th IEEE International Conference on Automation Science and Engineering (CASE)}, \n year = {2023},\n month = {Aug},\n day = {26-30},\n location = {Auckland, New Zealand},\n pages = {1--8},\n doi = {10.1109/CASE56687.2023.10260526},\n url_ieeexpl = {https://ieeexplore.ieee.org/abstract/document/10260526},\n ISSN = {2161-8089},\n keywords = {Geometry;Shape;Navigation;Roads;Operating systems;Semantics;Object detection},\n abstract = {Autonomous agents require rich environment models\n for fulfilling their missions. High-definition maps\n are a well-established map format which allows for\n representing semantic information besides the usual\n geometric information of the environment. These are,\n for instance, road shapes, road markings, traffic\n signs or barriers. The geometric resolution of HD\n maps can be as precise as of centimetre level. In\n this paper, we report on our approach of using HD\n maps as a map representation for autonomous\n load-haul-dump vehicles in open-pit mining\n operations. As the mine undergoes constant change,\n we also need to constantly update the\n map. Therefore, we follow a lifelong mapping\n approach for updating the HD maps based on\n camera-based object detection and GPS data. We show\n our mapping algorithm based on the Lanelet 2 map\n format and show our integration with the navigation\n stack of the Robot Operating System. We present\n experimental results on our lifelong mapping\n approach from a real open-pit mine.},\n}\n
\n
\n\n\n
\n Autonomous agents require rich environment models for fulfilling their missions. High-definition maps are a well-established map format which allows for representing semantic information besides the usual geometric information of the environment. These are, for instance, road shapes, road markings, traffic signs or barriers. The geometric resolution of HD maps can be as precise as of centimetre level. In this paper, we report on our approach of using HD maps as a map representation for autonomous load-haul-dump vehicles in open-pit mining operations. As the mine undergoes constant change, we also need to constantly update the map. Therefore, we follow a lifelong mapping approach for updating the HD maps based on camera-based object detection and GPS data. We show our mapping algorithm based on the Lanelet 2 map format and show our integration with the navigation stack of the Robot Operating System. We present experimental results on our lifelong mapping approach from a real open-pit mine.\n
\n\n\n
\n\n\n \n\n\n
\n
\n\n \n \n \n \n \n \n Using V2X Communications for Smart ODD Management of Highly Automated Vehicles.\n \n \n \n \n\n\n \n Schulte-Tigges, J.; Rondinone, M.; Reke, M.; Wachenfeld, J.; and Kaszner, D.\n\n\n \n\n\n\n In
26th IEEE International Conference on Intelligent Transportation Systems (ITSC), pages 3317–3322, Sep. 2023. \n
\n\n
\n\n
\n\n
\n\n \n \n ieeexpl\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@InProceedings{ Schulte-Tigges-etAl_ITSC2023_Using-V2X-Comm,\n author = {Schulte-Tigges, Joschua and Rondinone, Michele and Reke, Michael and Wachenfeld, Jan and Kaszner, Daniel},\n booktitle = {26th IEEE International Conference on Intelligent Transportation Systems (ITSC)}, \n title = {Using {V2X} Communications for Smart {ODD} Management of Highly Automated Vehicles}, \n year = {2023},\n month = {Sep.},\n day = {24-28},\n location = {Bilbao, Spain},\n pages = {3317--3322},\n doi = {10.1109/ITSC57777.2023.10422043},\n url_ieeexpl = {https://ieeexplore.ieee.org/abstract/document/10422043},\n ISSN = {2153-0017},\n keywords = {Software architecture;Roads;Prototypes;Vehicle-to-everything;\n Standards;Intelligent transportation systems;Vehicles},\n abstract = {Hazardous events like stationary vehicles on the\n carriageway, being in most cases unforeseeable and\n not always easy to detect, pose serious challenges\n to automated vehicles (AVs). When such events occur,\n AVs have to determine within limited time and space\n if permanence in their Operational Design Domain\n (ODD) will be guaranteed or not, and how to react to\n ensure passengers' safety and comfort. To cope with\n such events more effectively and efficiently, in\n this paper we present a software architecture and\n logic for Connected AVs (CAVs) that takes into\n account hazard notification and road signage\n information from available standard V2X messages to\n manage ODD-related decisions and reactions in an\n anticipated way. Differently from earlier works,\n focusing more on automated compliance to traffic\n management suggestions by the connected road\n infrastructure, the presented solution emphasises\n the active role of the CAV logic in taking suitable\n decisions based on individual and local\n situations. We introduce a manoeuvre planner\n implementing distinct state machines to react to\n different types of received V2X information. In the\n resulting procedures, where the driver can be also\n involved, step goals for a motion planner and path\n controller are generated. By means of simulations,\n we demonstrate the benefits of the presented CAV\n solution against a baseline AV model only relying on\n on-board sensors. To prove its real-world\n feasibility, we also report the results of\n integrating the proposed logic into a CAV prototype\n and running real-world test-track experiments.},\n}\n
\n
\n\n\n
\n Hazardous events like stationary vehicles on the carriageway, being in most cases unforeseeable and not always easy to detect, pose serious challenges to automated vehicles (AVs). When such events occur, AVs have to determine within limited time and space if permanence in their Operational Design Domain (ODD) will be guaranteed or not, and how to react to ensure passengers' safety and comfort. To cope with such events more effectively and efficiently, in this paper we present a software architecture and logic for Connected AVs (CAVs) that takes into account hazard notification and road signage information from available standard V2X messages to manage ODD-related decisions and reactions in an anticipated way. Differently from earlier works, focusing more on automated compliance to traffic management suggestions by the connected road infrastructure, the presented solution emphasises the active role of the CAV logic in taking suitable decisions based on individual and local situations. We introduce a manoeuvre planner implementing distinct state machines to react to different types of received V2X information. In the resulting procedures, where the driver can be also involved, step goals for a motion planner and path controller are generated. By means of simulations, we demonstrate the benefits of the presented CAV solution against a baseline AV model only relying on on-board sensors. To prove its real-world feasibility, we also report the results of integrating the proposed logic into a CAV prototype and running real-world test-track experiments.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Demonstrating a V2X Enabled System for Transition of Control and Minimum Risk Manoeuvre When Leaving the Operational Design Domain.\n \n \n \n \n\n\n \n Schulte-Tigges, J.; Matheis, D.; Reke, M.; Walter, T.; and Kaszner, D.\n\n\n \n\n\n\n In Krömker, H., editor(s),
HCI in Mobility, Transport, and Automotive Systems (HCII 2023), volume 14048, of
Lecture Notes in Computer Science, pages 200–210, Cham, 2023. Springer Nature Switzerland\n
\n\n
\n\n
\n\n
\n\n \n \n springer\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@InProceedings{ Schulte-Tigges-etAl_HCII2023_Demonstrating-V2X,\n author = "Schulte-Tigges, Joschua and Matheis, Dominik and Reke, Michael and Walter, Thomas and Kaszner, Daniel",\n editor = "Kr{\\"o}mker, Heidi",\n title = "Demonstrating a {V2X} Enabled System for Transition of Control and\n Minimum Risk Manoeuvre When Leaving the Operational Design Domain",\n booktitle = "HCI in Mobility, Transport, and Automotive Systems (HCII 2023)",\n year = "2023",\n publisher = "Springer Nature Switzerland",\n address = "Cham",\n pages = "200--210",\n series = {Lecture Notes in Computer Science},\n volume = {14048},\n url_springer = {https://link.springer.com/chapter/10.1007/978-3-031-35678-0_12},\n doi = {10.1007/978-3-031-35678-0_12},\n abstract = "Modern implementations of driver assistance systems\n are evolving from a pure driver assistance to a\n independently acting automation system. Still these\n systems are not covering the full vehicle usage\n range, also called operational design domain, which\n require the human driver as fall-back\n mechanism. Transition of control and potential\n minimum risk manoeuvres are currently research\n topics and will bridge the gap until full autonomous\n vehicles are available. The authors showed in a\n demonstration that the transition of control\n mechanisms can be further improved by usage of\n communication technology. Receiving the incident\n type and position information by usage of\n standardised vehicle to everything (V2X) messages\n can improve the driver safety and comfort level. The\n connected and automated vehicle's software framework\n can take this information to plan areas where the\n driver should take back control by initiating a\n transition of control which can be followed by a\n minimum risk manoeuvre in case of an unresponsive\n driver. This transition of control has been\n implemented in a test vehicle and was presented to\n the public during the IEEE IV2022 (IEEE Intelligent\n Vehicle Symposium) in Aachen, Germany.",\n isbn = "978-3-031-35678-0"\n}\n\n
\n
\n\n\n
\n Modern implementations of driver assistance systems are evolving from a pure driver assistance to a independently acting automation system. Still these systems are not covering the full vehicle usage range, also called operational design domain, which require the human driver as fall-back mechanism. Transition of control and potential minimum risk manoeuvres are currently research topics and will bridge the gap until full autonomous vehicles are available. The authors showed in a demonstration that the transition of control mechanisms can be further improved by usage of communication technology. Receiving the incident type and position information by usage of standardised vehicle to everything (V2X) messages can improve the driver safety and comfort level. The connected and automated vehicle's software framework can take this information to plan areas where the driver should take back control by initiating a transition of control which can be followed by a minimum risk manoeuvre in case of an unresponsive driver. This transition of control has been implemented in a test vehicle and was presented to the public during the IEEE IV2022 (IEEE Intelligent Vehicle Symposium) in Aachen, Germany.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Controlling a Fleet of Autonomous LHD Vehicles in Mining Operation.\n \n \n \n \n\n\n \n Ferrein, A.; Nikolovski, G.; Limpert, N.; Reke, M.; Schiffer, S.; and Scholl, I.\n\n\n \n\n\n\n In Küçük, S., editor(s),
Multi-Robot Systems - New Advances, 4. IntechOpen, Rijeka, 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n \n intech\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@incollection{Ferrein:etAl_INTECH2023_Controlling-a-Fleet,\n author = {Alexander Ferrein and Gjorgji Nikolovski and Nicolas Limpert\n and Michael Reke and Stefan Schiffer and Ingrid Scholl},\n title = {{Controlling a Fleet of Autonomous LHD Vehicles in Mining Operation}},\n booktitle = {Multi-Robot Systems - New Advances},\n publisher = {IntechOpen},\n address = {Rijeka},\n year = {2023},\n editor = {Serdar K{\\"u}{\\c{c}}{\\"u}k},\n chapter = {4},\n doi = {10.5772/intechopen.113044},\n url = {https://doi.org/10.5772/intechopen.113044},\n url_intech = {https://www.intechopen.com/chapters/88580},\n abstract = {In this chapter, we report on our activities to\n create and maintain a fleet of autonomous load haul\n dump (LHD) vehicles for mining operations. The ever\n increasing demand for sustainable solutions and\n economic pressure causes innovation in the mining\n industry just like in any other branch. In this\n chapter, we present our approach to create a fleet\n of autonomous special purpose vehicles and to\n control these vehicles in mining operations. After\n an initial exploration of the site we deploy the\n fleet. Every vehicle is running an instance of our\n ROS 2-based architecture. The fleet is then\n controlled with a dedicated planning module. We also\n use continuous environment monitoring to implement a\n life-long mapping approach. In our experiments, we\n show that a combination of synthetic, augmented and\n real training data improves our classifier based on\n the deep learning network Yolo v5 to detect our\n vehicles, persons and navigation beacons. The\n classifier was successfully installed on the NVidia\n AGX-Drive platform, so that the abovementioned\n objects can be recognised during the dumper\n drive. The 3D poses of the detected beacons are\n assigned to lanelets and transferred to an existing\n map.},\n}\n
\n
\n\n\n
\n 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.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Model-predictive Control with Parallelised Optimisation for the Navigation of Autonomous Mining Vehicles.\n \n \n \n \n\n\n \n Nikolovski, G.; Limpert, N.; Nessau, H.; Reke, M.; and Ferrein, A.\n\n\n \n\n\n\n In
2023 IEEE Intelligent Vehicles Symposium (IV), pages 1–6, June 2023. IEEE\n
\n\n
\n\n
\n\n
\n\n \n \n ieeexpl\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@InProceedings{Nikolovski-etAl_IV2023_MPC-Nav-Mining,\n author = {Nikolovski, Gjorgji and Limpert, Nicolas and Nessau, Hendrik and Reke, Michael and Ferrein, Alexander},\n booktitle = {2023 IEEE Intelligent Vehicles Symposium (IV)}, \n title = {Model-predictive Control with Parallelised Optimisation for the Navigation of Autonomous Mining Vehicles}, \n year = {2023},\n month = {June},\n day = {04-07},\n pages = {1--6},\n location = {Anchorage, AK, USA},\n doi = {10.1109/IV55152.2023.10186806},\n url_ieeexpl = {https://ieeexplore.ieee.org/abstract/document/10186806},\n publisher = {IEEE},\n ISSN = {2642-7214},\n keywords = {Navigation;Intelligent vehicles;Hydraulic\n drives;Steering systems;Transportation;Hydraulic\n systems;Minimization;mpc;control;path-following;navigation;automation},\n abstract = {The work in modern open-pit and underground mines\n requires the transportation of large amounts of\n resources between fixed points. The navigation to\n these fixed points is a repetitive task that can be\n automated. The challenge in automating the\n navigation of vehicles commonly used in mines is the\n systemic properties of such vehicles. Many mining\n vehicles, such as the one we have used in the\n research for this paper, use steering systems with\n an articulated joint bending the vehicle’s drive\n axis to change its course and a hydraulic drive\n system to actuate axial drive components or the\n movements of tippers if available. To address the\n difficulties of controlling such a vehicle, we\n present a model-predictive approach for controlling\n the vehicle. While the control optimisation based on\n a parallel error minimisation of the predicted state\n has already been established in the past, we provide\n insight into the design and implementation of an MPC\n for an articulated mining vehicle and show the\n results of real-world experiments in an open-pit\n mine environment.},\n}\n
\n
\n\n\n
\n The work in modern open-pit and underground mines requires the transportation of large amounts of resources between fixed points. The navigation to these fixed points is a repetitive task that can be automated. The challenge in automating the navigation of vehicles commonly used in mines is the systemic properties of such vehicles. Many mining vehicles, such as the one we have used in the research for this paper, use steering systems with an articulated joint bending the vehicle’s drive axis to change its course and a hydraulic drive system to actuate axial drive components or the movements of tippers if available. To address the difficulties of controlling such a vehicle, we present a model-predictive approach for controlling the vehicle. While the control optimisation based on a parallel error minimisation of the predicted state has already been established in the past, we provide insight into the design and implementation of an MPC for an articulated mining vehicle and show the results of real-world experiments in an open-pit mine environment.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Demonstrativ-aktiv-iterativ: Arbeitssysteme mit Künstlicher Intelligenz an Demonstratoren im Reallabor vermitteln, erproben und weiterentwickeln.\n \n \n \n \n\n\n \n Altepost, A.; Berlin, F.; Ferrein, A.; and Harlacher, M.\n\n\n \n\n\n\n In
GfA (Hrsg) Nachhaltig Arbeiten und Lernen - Analyse und Gestaltung lern- förderlicher und nachhaltiger Arbeitssysteme und Arbeits- und Lernprozesse. Bericht zum 69. Arbeitswissenschaftlichen Kongress vom 01. – 03. März 2023, pages 1–6, Sankt Augustin, 2023. GfA Press\n
\n\n
\n\n
\n\n
\n\n \n \n rwth\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@inproceedings{ Altepost-etAl_GfA2023_Demonstrativ-aktiv-iterativ,\n author = {Altepost, Andrea and Berlin, Florian and Ferrein, Alexander and Harlacher, Markus},\n title = {{Demonstrativ-aktiv-iterativ: Arbeitssysteme mit K{\\"u}nstlicher Intelligenz\n an Demonstratoren im Reallabor vermitteln, erproben und weiterentwickeln}},\n booktitle = {GfA (Hrsg) Nachhaltig Arbeiten und Lernen - Analyse und Gestaltung lern-\n f{\\"o}rderlicher und nachhaltiger Arbeitssysteme und Arbeits- und Lernprozesse.\n\t Bericht zum 69. Arbeitswissenschaftlichen Kongress vom 01. – 03. März 2023},\n pages = {1--6},\n OPTdoi = {},\n number = {C.6.2},\n year = {2023},\n location = {Gottfried Wilhelm Leibniz Universität Hannover},\n publisher = {GfA Press},\n address = {Sankt Augustin},\n url_RWTH = {https://publications.rwth-aachen.de/record/972487},\n keywords = {WIRKsam, Arbeitsgestaltung, Künstliche Intelligenz, Demonstratoren, Reallabor},\n abstract = {Das Kompetenzzentrum WIRKsam gestaltet innovative\n Arbeits- und Prozessabläufe mit Künstlicher\n Intelligenz für und mit Unternehmen im Rheinischen\n Braunkohlerevier. Neun unterschiedliche\n Problemstellungen regionaler Unternehmen werden mit\n maßgeschneiderten KI-Lösungen und Arbeitsgestaltung\n basierend auf dem MTO-Ansatz (Strohm & Ulich 1997;\n Ulich 2013) adressiert. Für das derzeit im Aufbau\n befindliche WIRKsam-Reallabor sollen Demonstratoren,\n die Erfahrungen aus den Anwendungsfällen aufgreifen,\n erleb- und erprobbar machen. Darüber hinaus sollen\n sie interessierte Unternehmen dazu anregen, sich an\n der Weiterentwicklung gezeigter Lösungen und der\n Findung neuer Ansätze aktiv zu beteiligen, mit dem\n Ziel, den Transfer in das eigene Unternehmen\n vorzubereiten. In Workshops wurden von verschiedenen\n Teilnehmendengruppen Anforderungen und\n Gestaltungshinweise für die Entwicklung der\n Demonstratoren erarbeitet.},\n}\n
\n
\n\n\n
\n Das Kompetenzzentrum WIRKsam gestaltet innovative Arbeits- und Prozessabläufe mit Künstlicher Intelligenz für und mit Unternehmen im Rheinischen Braunkohlerevier. Neun unterschiedliche Problemstellungen regionaler Unternehmen werden mit maßgeschneiderten KI-Lösungen und Arbeitsgestaltung basierend auf dem MTO-Ansatz (Strohm & Ulich 1997; Ulich 2013) adressiert. Für das derzeit im Aufbau befindliche WIRKsam-Reallabor sollen Demonstratoren, die Erfahrungen aus den Anwendungsfällen aufgreifen, erleb- und erprobbar machen. Darüber hinaus sollen sie interessierte Unternehmen dazu anregen, sich an der Weiterentwicklung gezeigter Lösungen und der Findung neuer Ansätze aktiv zu beteiligen, mit dem Ziel, den Transfer in das eigene Unternehmen vorzubereiten. In Workshops wurden von verschiedenen Teilnehmendengruppen Anforderungen und Gestaltungshinweise für die Entwicklung der Demonstratoren erarbeitet.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Anomaly Detection in the Metal-Textile Industry for the Reduction of the Cognitive Load of Quality Control Workers.\n \n \n \n \n\n\n \n Arndt, T.; Conzen, M.; Elsen, I.; Ferrein, A.; Galla, O.; Köse, H.; Schiffer, S.; and Tschesche, M.\n\n\n \n\n\n\n In
Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments, of
PETRA '23, pages 535–542, New York, NY, USA, 2023. Association for Computing Machinery\n
Best Workshop Paper - Runner Up\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n \n acm dl\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@inproceedings{Arndt:etAl_PETRA2023_AnomalyDetection,\n author = {Arndt, Tobias and Conzen, Max and Elsen, Ingo and\n Ferrein, Alexander and Galla, Oskar and K{\\"o}se,\n Hakan and Schiffer, Stefan and Tschesche, Matteo},\n title = {{Anomaly Detection in the Metal-Textile Industry for the\n Reduction of the Cognitive Load of Quality Control Workers}},\n booktitle = {Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments},\n pages = {535--542},\n numpages = {8},\n year = {2023},\n isbn = {9798400700699},\n publisher = {Association for Computing Machinery},\n address = {New York, NY, USA},\n location = {Corfu, Greece},\n series = {PETRA '23},\n url = {https://doi.org/10.1145/3594806.3596558},\n url_ACM_DL = {https://dl.acm.org/doi/abs/10.1145/3594806.3596558},\n doi = {10.1145/3594806.3596558},\n keywords = {WIRKsam, Artificial Intelligence, anomaly detection, datasets, neural networks, process optimization, quality control},\n abstract = {This paper presents an approach for reducing the\n cognitive load for humans working in quality control\n (QC) for production processes that adhere to the 6σ\n -methodology. While 100\\% QC requires every part to\n be inspected, this task can be reduced when a\n human-in-the-loop QC process gets supported by an\n anomaly detection system that only presents those\n parts for manual inspection that have a significant\n likelihood of being defective. This approach shows\n good results when applied to image-based QC for\n metal textile products.},\n note = {Best Workshop Paper - Runner Up},\n}\n%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n%% Leistung und Entgelt Magazine issue on WIRKsam w/ my co-authorship\n%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n\n
\n
\n\n\n
\n This paper presents an approach for reducing the cognitive load for humans working in quality control (QC) for production processes that adhere to the 6σ -methodology. While 100% QC requires every part to be inspected, this task can be reduced when a human-in-the-loop QC process gets supported by an anomaly detection system that only presents those parts for manual inspection that have a significant likelihood of being defective. This approach shows good results when applied to image-based QC for metal textile products.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Kompetenzzentrum WIRKsam - Wirtschaftlicher Wandel in der rheinischen Textil- und Kohleregion mit Künstlicher Intelligenz gemeinsam gestalten.\n \n \n \n \n\n\n \n Jeske, T.; Harlacher, M.; Altepost, A. A.; Schmenk, B.; Ferrein, A.; and Schiffer, S.,\n editors.\n \n\n\n \n\n\n\n Volume 2023 Joh. Heider Verlag GmbH, Bergisch Gladbach, 6 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n rwth\n \n \n \n ifaa\n \n \n \n pdf ifaa\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@BOOK{ Leistung-und-Entgelt_2024_WIRKsam,\n editor = {Jeske, Tim and Harlacher, Markus and Altepost, Andrea Anna\n and Schmenk, Bernhard and Ferrein, Alexander and Schiffer, Stefan},\n title = {{K}ompetenzzentrum {WIRK}sam - {W}irtschaftlicher {W}andel in der rheinischen\n {T}extil- und {K}ohleregion mit {K}{\\"u}nstlicher {I}ntelligenz gemeinsam gestalten},\n journal = {Leistung \\& Entgelt},\n volume = {2023},\n number = {2},\n issn = {2510-0424},\n address = {Bergisch Gladbach},\n publisher = {Joh. Heider Verlag GmbH},\n pages = {46 Seiten : Illustrationen},\n year = {2023},\n month = {6},\n subtyp = {Brochure},\n key_RWTH = {962619},\n url_RWTH = {https://publications.rwth-aachen.de/record/962619},\n url_ifaa = {https://www.arbeitswissenschaft.net/angebote-produkte/broschueren/leistung-und-entgelt-kompetenzzentrum-wirksam},\n url_PDF_ifaa = {https://www.arbeitswissenschaft.net/fileadmin/user_upload/Klein_Ende_24211_LundE_2_2023_finale_Version_fuer_Druckerei.pdf},\n keywords = {WIRKsam},\n abstract = {Das Kompetenzzentrum WIRKsam ist eines von acht\n regionalen Kompetenzzentren der Arbeitsforschung mit\n Fokus auf der Gestaltung neuer Arbeitsformen durch\n Künstliche Intelligenz. Es hat seine regionale\n Verankerung im Rheinischen Revier, das aufgrund des\n Kohleausstiegs von einem starken Strukturwandel\n betroffen ist. Gleichzeitig ist es Teil der\n Rheinischen Textilregion, die sich in den letzten 50\n Jahren stark verändert hat. Künstliche Intelligenz\n bietet umfassende Möglichkeiten, die Arbeitswelt mit\n innovativen Arbeits- und Prozessabläufen zu\n gestalten und Produkte zu verbessern. Sie hilft\n Unter- nehmen dabei, im globalen Wettbewerb zu\n bestehen und Wohlstand und Arbeitsplätze zu\n sichern. Die Arbeiten im Kompetenzzentrum WIRKsam\n zielen darauf ab, die Potenziale von KI für die\n Unternehmen im Rheinischen Revier zu\n erschließen. Der Kern der For- schungsaktivitäten\n liegt in der prototypischen Entwicklung und\n Einführung von KI-gestützten Systemen zur\n Unterstützung von Arbeit in bislang neun\n Anwendungsunternehmen. So entstehen Beispiele\n guter Praxis, die anderen Unternehmen Orientierung\n bieten sollen. In dieser Ausgabe der "Leistung \\&\n Entgelt" werden das vom Bundesministerium für Bil-\n dung und Forschung geförderte Projekt vorgestellt\n und seine bisher neun Anwendungs- fälle\n beschrieben.},\n}\n\n\n%%\n%article{ Harlacher:Niehus_LuE2023WIRKsam_SystematisierungAWFs\n% pages = {1--6},\n%% AP 3\n% 3-1_FEG\n% 3-2_Essedea\n% 3-3_Heusch\n%% AP 4\n% 4-1_AUNDE\n% 4-2_R+F\n% 4-3_neusser-fb\n%% AP 5\n% 5-1_GKD\n% 5-2_Heimbach\n% 5-3_Viethen\n%%\n\n\n
\n
\n\n\n
\n Das Kompetenzzentrum WIRKsam ist eines von acht regionalen Kompetenzzentren der Arbeitsforschung mit Fokus auf der Gestaltung neuer Arbeitsformen durch Künstliche Intelligenz. Es hat seine regionale Verankerung im Rheinischen Revier, das aufgrund des Kohleausstiegs von einem starken Strukturwandel betroffen ist. Gleichzeitig ist es Teil der Rheinischen Textilregion, die sich in den letzten 50 Jahren stark verändert hat. Künstliche Intelligenz bietet umfassende Möglichkeiten, die Arbeitswelt mit innovativen Arbeits- und Prozessabläufen zu gestalten und Produkte zu verbessern. Sie hilft Unter- nehmen dabei, im globalen Wettbewerb zu bestehen und Wohlstand und Arbeitsplätze zu sichern. Die Arbeiten im Kompetenzzentrum WIRKsam zielen darauf ab, die Potenziale von KI für die Unternehmen im Rheinischen Revier zu erschließen. Der Kern der For- schungsaktivitäten liegt in der prototypischen Entwicklung und Einführung von KI-gestützten Systemen zur Unterstützung von Arbeit in bislang neun Anwendungsunternehmen. So entstehen Beispiele guter Praxis, die anderen Unternehmen Orientierung bieten sollen. In dieser Ausgabe der \"Leistung & Entgelt\" werden das vom Bundesministerium für Bil- dung und Forschung geförderte Projekt vorgestellt und seine bisher neun Anwendungs- fälle beschrieben.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n WIRKsam : Projektvorstellung.\n \n \n \n \n\n\n \n Jeske, T.; Harlacher, M.; Altepost, A. A.; Schmenk, B.; Ferrein, A.; and Schiffer, S.\n\n\n \n\n\n\n
Leistung & Entgelt, 2023(2): 7–12. 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n rwth\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@ARTICLE{ Jeske:etAl_LuE2023WIRKsam_Projektvorstellung,\n author = {Jeske, Tim and Harlacher, Markus and Altepost, Andrea Anna\n and Schmenk, Bernhard and Ferrein, Alexander and Schiffer,\n Stefan},\n title = {{WIRK}sam : {P}rojektvorstellung},\n journal = {Leistung \\& Entgelt},\n volume = {2023},\n number = {2},\n issn = {2510-0424},\n address = {Bergisch-Gladbach},\n publisher = {Joh. Heider Verlag GmbH},\n reportid = {RWTH-2023-07490},\n pages = {7--12},\n year = {2023},\n url_RWTH = {https://publications.rwth-aachen.de/record/962599},\n keywords = {WIRKsam},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Multikriterielle KI-basierte Prozesssteuerung und Qualifizierung für Medizinprodukte.\n \n \n \n \n\n\n \n Harlacher, M.; Neihues, S.; Hansen-Ampah, A. T.; Köse, H.; Schiffer, S.; Ferrein, A.; Rezaey, A.; and Dievernich, A.\n\n\n \n\n\n\n
Leistung & Entgelt, 2023(2): 16–18. 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n rwth\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@ARTICLE{ Harlacher:etAl_LuE2023WIRKsam_3-1_FEG,\n author = {Harlacher, Markus and Neihues, Sina and Hansen-Ampah, Adjan\n Troy and K{\\"o}se, Hakan and Schiffer, Stefan and Ferrein,\n Alexander and Rezaey, Arash and Dievernich, Axel},\n title = {{M}ultikriterielle {KI}-basierte {P}rozesssteuerung und\n {Q}ualifizierung f{\\"u}r {M}edizinprodukte},\n journal = {Leistung \\& Entgelt},\n volume = {2023},\n number = {2},\n issn = {2510-0424},\n address = {Bergisch-Gladbach},\n publisher = {Joh. Heider Verlag GmbH},\n reportid = {RWTH-2023-07491},\n pages = {16--18},\n year = {2023},\n url_RWTH = {https://publications.rwth-aachen.de/record/962600},\n keywords = {WIRKsam},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n KI-Expertensystem für lernförderliche Empfehlungen zur maßgetreuen Produktion von 3D-Textilien mit digital unterstützter Eingangswerterfassung.\n \n \n \n \n\n\n \n Harlacher, M.; Niehues, S.; Merx, W.; Roder, S.; Schiffer, S.; Ferrein, A.; Zohren, M.; and Rezaey, A.\n\n\n \n\n\n\n
Leistung & Entgelt, 2023(2): 19-21. 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n rwth\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@ARTICLE{Harlacher:etAl_LuE2023WIRKsam_3-2_Essedea,\n author = {Harlacher, Markus and Niehues, Sina and Merx, Wolfgang and\n Roder, Simon and Schiffer, Stefan and Ferrein, Alexander and\n Zohren, Marc and Rezaey, Arash},\n title = {{KI}-{E}xpertensystem f{\\"u}r lernf{\\"o}rderliche {E}mpfehlungen\n zur ma{\\ss}getreuen {P}roduktion von 3{D}-{T}extilien mit\n digital unterst{\\"u}tzter {E}ingangswerterfassung},\n journal = {Leistung \\& Entgelt},\n volume = {2023},\n number = {2},\n issn = {2510-0424},\n address = {Bergisch-Gladbach},\n publisher = {Joh. Heider Verlag GmbH},\n reportid = {RWTH-2023-07492},\n pages = {19-21},\n year = {2023},\n url_RWTH = {https://publications.rwth-aachen.de/record/962601},\n keywords = {WIRKsam},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Lernförderliches KI-Varianzmanagement für die Produktion von Geweben mit kundenspezifisch veränderlich ausgeprägten Prüfmerkmalen.\n \n \n \n \n\n\n \n Köse, H.; Schiffer, S.; Ferrein, A.; Ramm, G. M.; Harlacher, M.; Merx, W.; Zohren, M.; Rezaey, A.; Ernst, L.; and Ntzemos, E.\n\n\n \n\n\n\n
Leistung & Entgelt, 2023(2): 25-27. 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n rwth\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@ARTICLE{Koese:etAl_LuE2023WIRKsam_4-1_AUNDE,\n author = {K{\\"o}se, Hakan and Schiffer, Stefan and Ferrein, Alexander\n and Ramm, Gerda Maria and Harlacher, Markus and Merx,\n Wolfgang and Zohren, Marc and Rezaey, Arash and Ernst, Leon\n and Ntzemos, Emmanuil},\n title = {{L}ernf{\\"o}rderliches {KI}-{V}arianzmanagement f{\\"u}r die\n {P}roduktion von {G}eweben mit kundenspezifisch\n ver{\\"a}nderlich ausgepr{\\"a}gten {P}r{\\"u}fmerkmalen},\n journal = {Leistung \\& Entgelt},\n volume = {2023},\n number = {2},\n issn = {2510-0424},\n address = {Bergisch-Gladbach},\n publisher = {Joh. Heider Verlag GmbH},\n reportid = {RWTH-2023-07495},\n pages = {25-27},\n year = {2023},\n url_RWTH = {https://publications.rwth-aachen.de/record/962605},\n keywords = {WIRKsam},\n}\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n KI-Nachfrageprognose zur Verringerung von Lagerbeständen, Produktionsschwankungen und damit verbundener Beschäftigungsbelastung.\n \n \n \n \n\n\n \n Tschesche, M.; Hennig, M.; Schiffer, S.; Ferrein, A.; Ramm, G. M.; Harlacher, M.; Merx, W.; Zohren, M.; Rezaey, A.; Kot, A.; and Smekal, J.\n\n\n \n\n\n\n
Leistung & Entgelt, 2023(2): 28-30. 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n rwth\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@ARTICLE{Tschesche:etAl_LuE2023WIRKsam_4-2_R+F,\n author = {Tschesche, Matteo and Hennig, Mike and Schiffer, Stefan and\n Ferrein, Alexander and Ramm, Gerda Maria and Harlacher,\n Markus and Merx, Wolfgang and Zohren, Marc and Rezaey, Arash\n and Kot, Aylin and Smekal, J{\\"u}rgen},\n title = {{KI}-{N}achfrageprognose zur {V}erringerung von\n {L}agerbest{\\"a}nden, {P}roduktionsschwankungen und damit\n verbundener {B}esch{\\"a}ftigungsbelastung},\n journal = {Leistung \\& Entgelt},\n volume = {2023},\n number = {2},\n issn = {2510-0424},\n address = {Bergisch-Gladbach},\n publisher = {Joh. Heider Verlag GmbH},\n reportid = {RWTH-2023-07500},\n pages = {28-30},\n year = {2023},\n url_RWTH = {https://publications.rwth-aachen.de/record/962613},\n keywords = {WIRKsam},\n}\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Situative KI-Entscheidungsunterstützung zur Abschätzung arbeitsorganisatorischer Folgen im Rahmen des Shopfloor Managements.\n \n \n \n \n\n\n \n Tschesche, M.; Henning, M.; Schiffer, S.; Ferrein, A.; Ramm, G. M.; Harlacher, M.; Merx, W.; and Sahm, J.\n\n\n \n\n\n\n
Leistung & Entgelt, 2023(2): 31-33. 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n rwth\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@ARTICLE{Tschesche:etAl_LuE2023WIRKsam_4-3_neusser-fb,\n author = {Tschesche, Matteo and Henning, Mike and Schiffer, Stefan\n and Ferrein, Alexander and Ramm, Gerda Maria and Harlacher,\n Markus and Merx, Wolfgang and Sahm, Joachim},\n title = {{S}ituative {KI}-{E}ntscheidungsunterst{\\"u}tzung zur\n {A}bsch{\\"a}tzung arbeitsorganisatorischer {F}olgen im {R}ahmen\n des {S}hopfloor {M}anagements},\n journal = {Leistung \\& Entgelt},\n volume = {2023},\n number = {2},\n issn = {2510-0424},\n address = {Bergisch-Gladbach},\n publisher = {Joh. Heider Verlag GmbH},\n reportid = {RWTH-2023-07501},\n pages = {31-33},\n year = {2023},\n url_RWTH = {https://publications.rwth-aachen.de/record/962614},\n keywords = {WIRKsam},\n}\n\n\n
\n
\n\n\n\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Unterstützung von Produktentwicklung und Qualitätssicherung durch KI-basierte Vergleiche von Produktkennwerten vor und nach dem Einsatz an Papiermaschinen.\n \n \n \n \n\n\n \n Hansen-Ampah, A. T.; Arndt, T.; Schiffer, S.; Ferrein, A.; Shahinfar, F. N.; Ramm, G. M.; and Klopp, K.\n\n\n \n\n\n\n
Leistung & Entgelt, 2023(2): 37-39. 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n rwth\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@ARTICLE{HansenAmpah:etAl_LuE2023WIRKsam_5-1_Heimbach,\n author = {Hansen-Ampah, Adjan Troy and Arndt, Tobias and Schiffer,\n Stefan and Ferrein, Alexander and Shahinfar, Fatemeh N. and\n Ramm, Gerda Maria and Klopp, Kai},\n title = {{U}nterst{\\"u}tzung von {P}roduktentwicklung und\n {Q}ualit{\\"a}tssicherung durch {KI}-basierte {V}ergleiche von\n {P}roduktkennwerten vor und nach dem {E}insatz an\n {P}apiermaschinen},\n journal = {Leistung \\& Entgelt},\n volume = {2023},\n number = {2},\n issn = {2510-0424},\n address = {Bergisch-Gladbach},\n publisher = {Joh. Heider Verlag GmbH},\n reportid = {RWTH-2023-07504},\n pages = {37-39},\n year = {2023},\n url_RWTH = {https://publications.rwth-aachen.de/record/962617},\n keywords = {WIRKsam},\n}\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Nutzung einer Mensch-Roboter-Kollaboration zum Erlernen komplexer motorischer Fertigkeiten für Tätigkeiten in der Faserverbundherstellung.\n \n \n \n \n\n\n \n Hansen-Ampah, A. T.; Backes, S. C.; Arndt, T.; Schiffer, S.; Ferrein, A.; Shahinfar, F. N.; Ramm, G. M.; and Viethen, H.\n\n\n \n\n\n\n
Leistung & Entgelt, 2023(2): 40-42. 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n rwth\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n\n\n\n
\n
@ARTICLE{HansenAmpah:etAl_LuE2023WIRKsam_5-1_Viethen,\n author = {Hansen-Ampah, Adjan Troy and Backes, Sebastian Christoph\n and Arndt, Tobias and Schiffer, Stefan and Ferrein,\n Alexander and Shahinfar, Fatemeh N. and Ramm, Gerda Maria\n and Viethen, Heinrich},\n title = {{N}utzung einer {M}ensch-{R}oboter-{K}ollaboration zum\n {E}rlernen komplexer motorischer {F}ertigkeiten f{\\"u}r\n {T}{\\"a}tigkeiten in der {F}aserverbundherstellung},\n journal = {Leistung \\& Entgelt},\n volume = {2023},\n number = {2},\n issn = {2510-0424},\n address = {Bergisch-Gladbach},\n publisher = {Joh. Heider Verlag GmbH},\n reportid = {RWTH-2023-07505},\n pages = {40-42},\n year = {2023},\n url_RWTH = {https://publications.rwth-aachen.de/record/962618},\n keywords = {WIRKsam},\n}\n\n\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Towards a Fleet of Autonomous Haul-Dump Vehicles in Hybrid Mines.\n \n \n \n \n\n\n \n Ferrein, A.; Reke, M.; Scholl, I.; Decker, B.; Limpert, N.; Nikolovski, G.; and Schiffer, S.\n\n\n \n\n\n\n In
Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, pages 278–288, 2023. INSTICC, SciTePress\n
\n\n
\n\n
\n\n
\n\n \n \n sciteprs\n \n \n \n pdf\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@InProceedings{ Ferrein-etAl_ICAART2023_Towards-a-Fleet,\n author = {Alexander Ferrein and Michael Reke and Ingrid Scholl and Benjamin Decker\n and Nicolas Limpert and Gjorgji Nikolovski and Stefan Schiffer},\n title = {Towards a Fleet of Autonomous Haul-Dump Vehicles in Hybrid Mines},\n booktitle = {Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART},\n year = {2023},\n pages = {278--288},\n publisher = {SciTePress},\n organization = {INSTICC},\n doi = {10.5220/0011693600003393},\n url_sciteprs = {https://www.scitepress.org/Papers/2023/116936/},\n url_PDF = {https://www.scitepress.org/Papers/2023/116936/116936.pdf},\n isbn = {978-989-758-623-1},\n abstract = {Like many industries, the mining industry is facing\n major transformations towards more sustainable and\n decarbonised operations with smaller environmental\n footprints. Even though the mining industry, in\n general, is quite conservative, key drivers for\n future developments are digitalisation and\n automation. Another direction forward is to mine\n deeper and reduce the mine footprint at the\n surface. This leads to so-called hybrid mines, where\n part of the operation is open pit, and part of the\n mining takes place underground. In this paper, we\n present our approach to running a fleet of\n autonomous hauling vehicles suitable for hybrid\n mining operations. We present a ROS 2-based\n architecture for running the vehicles. The fleet of\n currently three vehicles is controlled by a\n SHOP3-based planner which dispatches missions to the\n vehicles. The basic actions of the vehicles are\n realised as behaviour trees in ROS 2. We used a deep\n learning network for detection and classification of\n mining objects trained with a mixing of synthetic\n and real world training images. In a life-long\n mapping approach, we define lanelets and show their\n integration into HD maps. We demonstrate a\n proof-of-concept of the vehicles in operation in\n simulation and in real-world experiments in a gravel\n pit.},\n}\n% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n% 2022\n% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n\n
\n
\n\n\n
\n Like many industries, the mining industry is facing major transformations towards more sustainable and decarbonised operations with smaller environmental footprints. Even though the mining industry, in general, is quite conservative, key drivers for future developments are digitalisation and automation. Another direction forward is to mine deeper and reduce the mine footprint at the surface. This leads to so-called hybrid mines, where part of the operation is open pit, and part of the mining takes place underground. In this paper, we present our approach to running a fleet of autonomous hauling vehicles suitable for hybrid mining operations. We present a ROS 2-based architecture for running the vehicles. The fleet of currently three vehicles is controlled by a SHOP3-based planner which dispatches missions to the vehicles. The basic actions of the vehicles are realised as behaviour trees in ROS 2. We used a deep learning network for detection and classification of mining objects trained with a mixing of synthetic and real world training images. In a life-long mapping approach, we define lanelets and show their integration into HD maps. We demonstrate a proof-of-concept of the vehicles in operation in simulation and in real-world experiments in a gravel pit.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Winning the RoboCup Logistics League with Visual Servoing and Centralized Goal Reasoning.\n \n \n \n \n\n\n \n Viehmann, T.; Limpert, N.; Hofmann, T.; Henning, M.; Ferrein, A.; and Lakemeyer, G.\n\n\n \n\n\n\n In Eguchi, A.; Lau, N.; Paetzel-Prüsmann, M.; and Wanichanon, T., editor(s),
RoboCup 2022: Robot World Cup XXV, volume 13561, of
Lecture Notes in Computer Science, pages 300–312, Cham, 2023. Springer International Publishing\n
\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@InProceedings{Viehmann-etAl_RoboCup2022_Winning-the-RoboCup-Logistics-League,\n author = "Viehmann, Tarik and Limpert, Nicolas and Hofmann, Till and Henning, Mike and Ferrein, Alexander and Lakemeyer, Gerhard",\n editor = "Eguchi, Amy and Lau, Nuno and Paetzel-Pr{\\"u}smann, Maike and Wanichanon, Thanapat",\n title = "{Winning the RoboCup Logistics League with Visual Servoing and Centralized Goal Reasoning}",\n booktitle = "RoboCup 2022: Robot World Cup XXV",\n year = "2023",\n pages = "300--312",\n series = {Lecture Notes in Computer Science},\n volume = {13561},\n publisher = "Springer International Publishing",\n address = "Cham",\n isbn = "978-3-031-28469-4",\n doi = {10.1007/978-3-031-28469-4_25},\n url = {https://link.springer.com/chapter/10.1007/978-3-031-28469-4_25},\n keywords = {RoboCup, Logistics League, RCLL},\n abstract = "The RoboCup Logistics League (RCLL) is a robotics\n competition in a production logistics scenario in\n the context of a Smart Factory. In the competition,\n a team of three robots needs to assemble products to\n fulfill various orders that are requested online\n during the game. This year, the Carologistics team\n was able to win the competition with a new approach\n to multi-agent coordination as well as significant\n changes to the robot's perception unit and a\n pragmatic network setup using the cellular network\n instead of WiFi. In this paper, we describe the\n major components of our approach with a focus on the\n changes compared to the last physical competition in\n 2019.",\n}\n\n% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n% 2021\n% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n\n
\n
\n\n\n
\n The RoboCup Logistics League (RCLL) is a robotics competition in a production logistics scenario in the context of a Smart Factory. In the competition, a team of three robots needs to assemble products to fulfill various orders that are requested online during the game. This year, the Carologistics team was able to win the competition with a new approach to multi-agent coordination as well as significant changes to the robot's perception unit and a pragmatic network setup using the cellular network instead of WiFi. In this paper, we describe the major components of our approach with a focus on the changes compared to the last physical competition in 2019.\n
\n\n\n
\n\n\n\n\n\n