Path prediction is an essential task for many real-world Cyber-Physical systems (CPS) applications, from autonomous driving and traffic monitoring/management to pedestrian/worker safety. These real-world CPS applicati...
详细信息
ISBN:
(纸本)9798400700361
Path prediction is an essential task for many real-world Cyber-Physical systems (CPS) applications, from autonomous driving and traffic monitoring/management to pedestrian/worker safety. These real-world CPS applications need a robust, lightweight path prediction that can provide a universal network architecture for multiple subjects (e.g., pedestrians and vehicles) from different perspectives. However, most existing algorithms are tailor-made for a unique subject with a specific camera perspective and scenario. This article presents Pishgu, a universal lightweight network architecture, as a robust and holistic solution for path prediction. Pishgu's architecture can adapt to multiple path prediction domains with different subjects (vehicles, pedestrians), perspectives ( bird's-eye, high-angle), and scenes (sidewalk, highway). Our proposed architecture captures the inter-dependencies within the subjects in each frame by taking advantage of Graph Isomorphism Networks and the attention module. We separately train and evaluate the efficacy of our architecture on three different CPS domains across multiple perspectives (vehicle bird's-eye view, pedestrian bird's-eye view, and human high-angle view). Pishgu outperforms state-of-the-art solutions in the vehicle bird's-eye view domain by 42% and 61% and pedestrian high-angle view domain by 23% and 22% in terms of ADE and FDE, respectively. Additionally, we analyze the domain-specific details for various datasets to understand their effect on path prediction and model interpretation. Finally, we report the latency and throughput for all three domains on multiple embedded platforms showcasing the robustness and adaptability of Pishgu for real-world integration into CPS applications.
Modern computing platforms for robotics applications comprise a set of heterogeneous elements, e.g., multi-core CPUs, embedded GPUs, and FPGAs. FPGAs are reprogrammable hardware devices that allow for fast and energy-...
详细信息
ISBN:
(纸本)9781665491907
Modern computing platforms for robotics applications comprise a set of heterogeneous elements, e.g., multi-core CPUs, embedded GPUs, and FPGAs. FPGAs are reprogrammable hardware devices that allow for fast and energy-efficient computation of many relevant tasks in robotics. ROS is the de-facto programming standard for robotics and decomposes an application into a set of communicating nodes. ReconROS is a previous approach that can map complete ROS nodes into hardware for acceleration. Since ReconROS relies on standard ROS communication layers, exchanging data between hardware-mapped nodes can lead to a performance bottleneck. This paper presents fpgaDDS, a lean data distribution service for hardware-mapped ROS 2 nodes. fpgaDDS relies on a customized and statically generated streaming-based communication architecture. We detail this communication architecture with its components and outline its benefits. We evaluate fpgaDDS on a test example and a larger autonomous vehicle case study. Compared to a ROS 2 application in software, we achieve speedups of up to 13.34 and reduce jitter by two orders of magnitude.
Runtime orchestration of cloud-native microservice systems remains a challenge with many technology options, such as Kubernetes for managing containers and OASIS TOSCA, a standard for orchestrating cloud services. Res...
详细信息
ISBN:
(纸本)9798350366266;9798350366259
Runtime orchestration of cloud-native microservice systems remains a challenge with many technology options, such as Kubernetes for managing containers and OASIS TOSCA, a standard for orchestrating cloud services. Researchers and practitioners have proposed different approaches on how the benefits of Kubernetes and TOSCA could be combined, but followed different design philosophies and did not reach consensus. An analysis of the different combinations is missing and existing TOSCA and Kubernetes combinations do not consider the integration of real-timeembedded controllers without container workloads, nor a safeguarding of configuration changes, which can be achieved using the GitOps paradigm. In this experience report, we describe and analyze different options for combining TOSCA and Kubernetes. Following one of the options, we have enhanced an existing TOSCA orchestrator to demonstrate software updates across heterogeneous software services as well as a GitOps extension for TOSCA service models. We found that TOSCA workflows are well suited for updates spanning different technologies and that a custom GitOps operator is needed in case not all components are orchestrated by Kubernetes.
The interoperability of more devices onto the IoT and the addition of the low-power applications like sensors and other embeddedsystems have posed severe security challenges. Many cryptographic protocols are ineffect...
详细信息
Anomaly detection is a very important component in weather forecasting, disaster preparedness and climate modeling in meteorology. We use Density Based Spatial Clustering of applications with Noise, Isolation Forest, ...
详细信息
The demand for enhanced flexibility in automation systems, dictated by initiatives as the Industry 4.0 in Europe or the Industrial Internet Consortium in the United States, can be satisfied inheriting solutions of the...
详细信息
ISBN:
(纸本)9781665464321
The demand for enhanced flexibility in automation systems, dictated by initiatives as the Industry 4.0 in Europe or the Industrial Internet Consortium in the United States, can be satisfied inheriting solutions of the information technology (the so called IT-OT convergence). Other than communication and cloud technologies, virtualization will play a relevant role in the next future. The use of lightweight virtualization, e.g., in the form of containers for implementing the edge computing paradigm, is a promising tool to dynamically provide services depending on the actual production needs. However, requirements of industrial automation applications are different from those of office-like counterparts. For this reason, methodologies for evaluating obtainable performance are needed. In this work, an industrial-grade framework, the Siemens Industrial Edge, is considered. A reference testbed is setup to evaluate latencies when information is exchanged between two user applications. Experiments demonstrate that round trip time in the order of 10 ms is feasible, compatible with the requirements of both process control systems and supervision applications.
Manipulating deformable objects arises in daily life and numerous applications. Despite phenomenal advances in industrial robotics, manipulation of deformable objects remains mostly a manual task. This is because of t...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Manipulating deformable objects arises in daily life and numerous applications. Despite phenomenal advances in industrial robotics, manipulation of deformable objects remains mostly a manual task. This is because of the high number of internal degrees of freedom and the complexity of predicting its motion. In this paper, we apply the computationally efficient position-based dynamics method to predict object motion and distance to obstacles. This distance is incorporated in a control barrier function for the resolved motion kinematic control for one or more robots to adjust their motion to avoid colliding with the obstacles. The controller has been applied in simulations to 1D and 2D deformable objects with varying numbers of assistant agents, demonstrating its versatility across different object types and multi-agent systems. Results indicate the feasibility of real-time collision avoidance through deformable object simulation, minimizing path tracking error while maintaining a predefined minimum distance from obstacles and preventing overstretching of the deformable object. The implementation is performed in ROS, allowing ready portability to different applications.
real-time Ethernet protocols are currently undergoing specification updates to include security features. These features generally take the form of a public key infrastructure and associated network node and message a...
详细信息
For portability, embeddedsystems software follows a layered design to reduce dependence on particular hardware behavior. We consider the problem of identifying layering violations: instances where the embedded applic...
详细信息
ISBN:
(纸本)9798400701740
For portability, embeddedsystems software follows a layered design to reduce dependence on particular hardware behavior. We consider the problem of identifying layering violations: instances where the embedded application accesses non-adjacent layers. This paper presents our preliminary work to detect a class of layering violations called Non Conventional MMIO Accesses (NCMAs). We find them by searching for direct Memory Mapped Input Output (MMIO) accesses made outside of the Hardware Abstraction Layer (HAL). For evaluation, we curated a list of 988 applications spanning 5 realtime Operating systems (RTOSes) - the first large dataset of compilable embeddedapplications. Our system identified 369 NCMAs. We reported these issues to the corresponding developers and found interesting reasons for committing layering violations. We have open-sourced our tool and the collected dataset to foster future research.
The overarching goal of this research is to improve Smartphone user identification in practical settings by using multi-model biometric systems. A dataset was retrieved from the Kaggle library for this specific resear...
详细信息
暂无评论