Qamcom Research and Technology (Sweden)

This article presents the European 6G Flagship project Hexa-X-II's view on 6G AI-driven air interface. It outlines motivations for AI in the physical layer, selected applications of AI for communication and sensing, their achieved performance, and the challenges to be addressed. The article also provides an overview of the relevant standardization activities.

As 6G emerges, cellular systems are envisioned to integrate sensing with communication capabilities, leading to multi-faceted communication and sensing (JCAS). This paper presents a comprehensive cross-layer overview of the Hexa-X-II project's endeavors in JCAS, aligning 6G use cases with service requirements and pinpointing distinct scenarios that bridge communication and sensing. This work relates to these scenarios through the lens of the cross-layer physical and networking domains, covering models, deployments, resource allocation, storage challenges, computational constraints, interfaces, and innovative functions.

As the research community focuses on improving the reliability of deep learning, identifying out-of-distribution (OOD) data has become crucial. Detecting OOD inputs during test/prediction allows the model to account for discriminative features unknown to the model. This capability increases the model’s reliability since this model provides a class prediction solely at incoming data similar to the training one. Although OOD detection is well-established in computer vision, it is relatively unexplored in other areas, like time series-based human activity recognition (HAR). Since uncertainty has been a critical driver for OOD in vision-based models, the same component has proven effective in time-series applications. In this work, we propose an ensemble-based temporal learning framework to address the OOD detection problem in HAR with time-series data. First, we define different types of OOD for HAR that arise from realistic scenarios. Then we apply our ensemble-based temporal learning framework incorporating uncertainty to detect OODs for the defined HAR workloads. This particular formulation also allows a novel approach to fall detection. We train our model on non-fall activities and detect falls as OOD. Our method shows state-of-the-art performance in a fall detection task using much lesser data. Furthermore, the ensemble framework outperformed the traditional deep-learning method (our baseline) on the OOD detection task across all the other chosen datasets.

During the last decade, there has been significant increase in research focused on automated vehicles (AVs) and ensuring safe operation of these vehicles. However, challenges still remain, some involving the cooperation and collaboration of multiple AVs, including when and how to perform a minimal risk manoeuvre (MRM), leading to a minimal risk condition (MRC) when an AV within one of these systems is unable to complete its original goal. As most literature is focused on individual AVs, there is a need to adapt and extend the knowledge and techniques to these new contexts. Based on existing knowledge of individual AVs, this paper explores MRM strategies involving cooperative and collaborative AV systems with different capabilities. Specifically, collaborative systems have the potential to enact local MRCs, allowing continued productivity despite having one (or several) of its constituents encounter a fault. Definitions are provided for local and global MRCs, alongside discussions of their implications for MRMs. Illustrative examples are also presented for each type of system.

Emerging use-cases like smart manufacturing and smart cities pose challenges in terms of latency, which cannot be satisfied by traditional centralized infrastructure. Edge networks, which bring computational capacity closer to the users/clients, are a promising solution for supporting these critical low latency services. Different from traditional centralized networks, the edge is distributed by nature and is usually equipped with limited compute capacity. This creates a complex network to handle, subject to failures of different natures, that requires novel solutions to work in practice. To reduce complexity, edge application technology enablers, advanced infrastructure and application orchestration techniques need to be in place where AI and ML are key players.

With the growing interest of the research community in making deep learning (DL) robust and reliable, detecting out-of-distribution (OOD) data has become critical. Detecting OOD inputs during test/prediction allows the model to account for discriminative features unknown to the model. This capability increases the model's reliability since this model provides a class prediction solely at incoming data similar to the training one. OOD detection is well-established in computer vision problems. However, it remains relatively under-explored in other domains such as time series (i.e., Human Activity Recognition (HAR)).<br> Since uncertainty has been a critical driver for OOD in vision-based models, the same component has proven effective in time-series applications. We plan to address the OOD detection problem in HAR with time-series data in this work. To test the capability of the proposed method, we define different types of OOD for HAR that arise from realistic scenarios. We apply an ensemble-based temporal learning framework that incorporates uncertainty and detects OOD for the defined HAR workloads. In particular, we extract OODs from popular benchmark HAR datasets and use the framework to separate those OODs from the in-distribution (ID) data.<br> Across all the datasets, the ensemble framework outperformed the traditional deep-learning method (our baseline) on the OOD detection task.

&lt;div class="section abstract"&gt;&lt;div class="htmlview paragraph"&gt;One major challenge in designing SAE level 3-5 Automated Driving Systems (ADS) is to define requirements for the perception system that would enable argumentation for safe operation. The safety requirements on the perception system can only be fulfilled through redundancy in the sensor hardware. It is, however, a challenge to specify the redundancy that is required in the sensor system. Safe operation for an ADS is significantly more difficult compared to advanced driver assistance systems (ADAS). The safety argumentation for ADAS typically argues that in case of a failure in the sensor array a fail-silent behavior is acceptable because the human driver can take control of the vehicle back. This argumentation however is not possible when developing level 4 or higher automation. This paper investigates prerequisites for applying a systematic methodology for analyzing redundancy in a multi-sensor system and the relation to a conceptual ADS functional architecture. This analysis must address the complexity that comes with partially overlapping sensor data from different sensors and considers variations in performance and characteristics due to changes in the environmental conditions. The paper introduces the term incomplete redundancy and presents a systematic methodology for analyzing redundancy. The aim is to provide arguments for how several sensors in a system, when appropriately combined, meet an assigned safety requirement on a higher level. Each sensor will then be assigned a certain responsibility and contributes with a sub-set of information. A set of questions of importance to address as a foundation for such a methodology are defined and discussed. The definitions of redundancy and independence between sensors are discussed as well as contract-based functional safety to adapt to different environmental and operating conditions.&lt;/div&gt;&lt;/div&gt;

This letter provides a description of how hierarchical dependencies between inequalities can be exploited in order to efficiently calculate polyhedral approximations of maximal robust positive invariant sets using geometrically motivated methods. Due to the hierarchical dependencies, the calculations of preimage sets and minimal representations can be alleviated. It is also shown that as a byproduct from the calculations of minimal representations, a stopping criterion is obtained, which means that the commonly used subset test is superfluous.

Every new generation of mobile systems should provide higher capacity, serve more users, be more energy efficient, and have lower cost. Radio-access hardware constitutes a major bottleneck for reaching these goals, which is a particularly noticeable issue now that 5G communication systems are being developed. A combination of breakthroughs in communication theory-as in massive multiple input/multiple output (MIMO) [1], highly integrated semiconductor and packaging technologies, and extended spectrum allocations- has enabled a paradigm shift in the way radio hardware will be realized. Today's high-power, fewantenna, sectorized systems will soon be replaced with highly integrated active antenna systems having up to hundreds of individually driven low-power radios operating with very wideband signals.

We study a combinatorial optimization problem that is motivated by the scenario of autonomous cars driving on a multi-lane highway: some cars need to change lanes before the next intersection, and if there is congestion, cars need to slow down to make space for those who are changing lanes. There are two natural objective functions to minimize: (1) how long does it take for all traffic to clear the road, and (2) the total number of maneuvers. In this work, we present an approximation algorithm for solving these problems in the two-lane case and a hardness result for the multi-lane case.