Fakultät IuI
Refine
Document Type
- Conference Proceeding (16)
- Article (6)
- Part of Periodical (1)
- Working Paper (1)
Language
- English (24) (remove)
Has Fulltext
- no (24) (remove)
Is part of the Bibliography
- yes (24)
Keywords
- Power Consumption (2)
- time synchronization (2)
- 5G (1)
- 802.1AS (1)
- Computer-Human Interaction (1)
- DiffServ (1)
- Dynamic Adaptation (1)
- EDCA (1)
- Embedded Software Engineering (1)
- Embedded Systems (1)
Institute
- Fakultät IuI (24)
- Fakultät AuL (2)
- Institut für Duale Studiengänge (1)
The 3GPP release 16 integrates TSN functionality into 5G and standardizes various options for TSN time synchronization over 5G such as transparent mode and bridge mode. The time domains for the TSN network and the 5G network are kept separate with an option to synchronize either of the networks to the other. The TSN time synchronization over 5G is possible either by using the IEEE 1588 generalized Precision Time Protocol (gPTP) based on UDP/IP multicast or via IEEE 802.1AS based on Ethernet PDUs. The INET and Simu5G simulation frameworks, which are both based on the OMNeT++ discrete event simulator, are widely used for simulating TSN and 5G networks. The INET framework comprises the 802.1AS based time synchronization mechanism, and Simu5G provides the 5G user plane carrying IP PDUs. We modified the 802.1AS-based synchronization model of INET so that it works over UDP/IP. With that, it is possible to synchronize TSN slaves (connected to 5G UEs), across a 5G network, with a TSN master clock, present within a TSN network, that is connected to the 5G core network. Our simulation results show that 500 microseconds of synchronization accuracy can be achieved with the corrected asymmetric propagation delay of uplink and downlink between the gNodeB (gNB) and the User Equipment (UE). Furthermore, the synchronization accuracy can be improved if the delay difference between uplink and downlink is known.
Recent real-time networking developments have enabled ultra reliability, very low latency and high data rates in wired networks. Wireless networking developments have also shown that they can achieve very high data rates with consistency, but they still lack in providing ultra reliability and extremely low latency. Time Sensitive Networking (TSN) developments have brought these capabilities in Industry automation and Automotive industry too. Although TSN is standardized for wired networks for a long time, for wireless networks it will be standardized within the IEEE 802.11be standard for Wi-Fi and 3GPP Release 17 for 5G in the near future. This paper provides an overview of TSN in wired and wireless networks with the aim of comparing different simulators and presenting their offered functionality and shortcomings. These tools can be used to make oneself familiar with TSN algorithms, standards, and for the development and testing of time sensitive networks. Afterwards, the paper discusses open research questions for using TSN over wireless networks.
Artificial intelligence (AI) and human-machine interaction (HMI) are two keywords that usually do not fit embedded applications. Within the steps needed before applying AI to solve a specific task, HMI is usually missing during the AI architecture design and the training of an AI model. The human-in-the-loop concept is prevalent in all other steps of developing AI, from data analysis via data selection and cleaning to performance evaluation. During AI architecture design, HMI can immediately highlight unproductive layers of the architecture so that lightweight network architecture for embedded applications can be created easily. We show that by using this HMI, users can instantly distinguish which AI architecture should be trained and evaluated first since a high accuracy on the task could be expected. This approach reduces the resources needed for AI development by avoiding training and evaluating AI architectures with unproductive layers and leads to lightweight AI architectures. These resulting lightweight AI architectures will enable HMI while running the AI on an edge device. By enabling HMI during an AI uses inference, we will introduce the AI-in-the-loop concept that combines AI's and humans' strengths. In our AI-in-the-loop approach, the AI remains the working horse and primarily solves the task. If the AI is unsure whether its inference solves the task correctly, it asks the user to use an appropriate HMI. Consequently, AI will become available in many applications soon since HMI will make AI more reliable and explainable.
Knowledge of the maximum friction coefficient µmax between tire and road is necessary for implementing autonomous driving. As this coefficient cannot be measured via existing serial vehicle sensors, µmax estimation is a challenging field in modern automotive research. In particular, model-based approaches are applied, which are limited in the estimation accuracy by the physical vehicle model. Therefore, this paper presents a data-based µmax estimation using serial vehicle sensors. For this purpose, recurrent artificial neural networks are trained, validated, and tested based on driving maneuvers carried out with a test vehicle showing improved results compared to the model-based algorithm from previous works.
This paper investigates four different mobile robots with respect to their drivingcharacteristics and soil preservation properties in an agricultural environment.Thereby, robots of classical design from agriculture as well as systems from spacerobotics with advanced locomotion concepts are considered to determine theindividual advantages of each rover concept with respect to the application domain.Locomotion experiments were conducted to analyze the general driving behavior,tensile force, and obstacle‐surmounting capability and ground interaction of eachrobot. Various soil conditions typical for the area of application are taken intoaccount, which are varied in terms of moisture and density. The presented workcovers the specification of the conducted experiments, documentation of theimplementation as well as analysis and evaluation of the collected data. In theevaluation, particular attention is paid to the change in driving characteristics underdifferent soil conditions, as well as to the soil stress caused by driving, since soilquality is of critical importance for agricultural applications. The analysis shows thatthe advanced locomotion concepts, as used in space robotics, also have positiveimplications for certain requirements in agricultural applications, such as maneuver-ability in wet conditions and soil conservation. The results show potential for designinnovations in agricultural robotics that can be used, to open up new fields ofapplication for instance in the context of precision farming.
This paper presents a framework for OMNeT++ which includes time synchronization model for WLANs. Synchronization is based on the Generalized Precision Time Protocol (gPTP) standard, which aims to achieve an accuracy of less than 100 nanoseconds. The presented model is developed and implemented in OMNeT++, a discrete event network simulator, using its INET library. A new type of WLAN node is modeled which supports time synchronization at the Link layer. A clock module for WLAN nodes is also modeled which implements variable clock drift to simulate noise interference in clock frequency oscillators. Simulations with our WLAN nodes are done and the results show that using gPTP based time synchronization in wireless networks, accuracy of ±3ns can be achieved.