Unlike traditional hierarchical controllers for robotic leg prostheses and exoskeletons, continuous systems could allow persons with mobility impairments to walk more naturally in real-world environments without requi...
详细信息
ISBN:
(纸本)9798350323658
Unlike traditional hierarchical controllers for robotic leg prostheses and exoskeletons, continuous systems could allow persons with mobility impairments to walk more naturally in real-world environments without requiring high-level switching between locomotion modes. To support these next-generation controllers, we developed a new system called KIFNet (Kinematics and Image Fusing Network) that uses lightweight and efficient deep learning models to continuously predict the leg kinematics during walking. We tested different sensor fusion methods to combine kinematics data from inertial sensors and computer vision data from smart glasses and found that adaptive instance normalization achieved the lowest RMSE predictions for knee and ankle joint kinematics. We also deployed our model on an embedded device. Without inference optimization, our model was 20 times faster than the previous state-of-the-art and achieved 20% higher prediction accuracies, and during some locomotor activities like stair descent, decreased RMSE up to 300%. With inference optimization, our best model achieved 125 FPS on an NVIDIA Jetson Nano. These results demonstrate the potential to build fast and accurate deep learning models for continuous prediction of leg kinematics during walking based on sensor fusion and embeddedcomputing, therein providing a foundation for real-time continuous controllers for robotic leg prostheses and exoskeletons.
The vehicle dynamics of off-road vehicles tend to be non-linear concerning suspension dynamics, tyre-terrain interactions, and subsystem kinematics. These non-linearities limit the performance of control due to the ne...
详细信息
AI on the edge as a paradigm promises unparalleled energy efficiency and data privacy among other benefits. This has resulted in a rising trend of approaches to bring AI computing near or embedded directly inside a se...
详细信息
embeddedsystems have become an integral part of our everyday lives. Devices are increasingly connected, especially in the Internet of Things (IoT) environment. The interfaces between the devices require high-quality ...
详细信息
ISBN:
(纸本)9798350363029;9798350363012
embeddedsystems have become an integral part of our everyday lives. Devices are increasingly connected, especially in the Internet of Things (IoT) environment. The interfaces between the devices require high-quality software and hardware to ensure reliable communication between them. This vital interconnection also leads to systems becoming increasingly complex, and therefore, the complexity of the tests increases. Therefore, such tests can usually only be done by means of automation, as manual testing is very time-consuming and cost-intensive. A System Under Test (SUT) has different requirements depending on the application area and the functionality, which is why different test automation approaches exist. This work reviews possible approaches for test automation of embedded devices and compares them with each other based on different criteria. Based on this comparison and in cooperation with Siemens Smart Infrastructure EA, a test automation system called Kubrotest was designed. To verify the test automation in a real usecase, Kubrotest is used to test a Siemens SICAM 8 series device.
We present a battery-powered wearable system that is able to identify the three basic types of speech disfluencies found in people who stutter: blocks, prolongations, and repetitions. Such a system could be used to ai...
详细信息
ISBN:
(纸本)9798350386394;9798350386400
We present a battery-powered wearable system that is able to identify the three basic types of speech disfluencies found in people who stutter: blocks, prolongations, and repetitions. Such a system could be used to aid speech pathology clinicians by performing automated diagnosis of stuttering or monitoring the progress of speech therapy, tasks that are currently time-consuming and produce potentially unreliable results. The system uses a deep learning model trained on the SEP-28k dataset and deployed on a microcontroller. It performs speech audio acquisition and model inference in realtime and stores the inference results to non-volatile memory. Once stored, the results can be further analyzed on a PC and presented to the clinician. Our deep learning model achieved a classification accuracy of 65%, 71%, and 64% for blocks, prolongations, and repetitions, respectively. We discuss the possible applications of this system in speech disorder diagnosis and therapy as well as potential improvements.
The role of technology is vital and can be observed through the 5th industrial revolution. As a matter of fact, the impact is so severe, it can be felt almost everywhere. As technology advances, one of the most promis...
详细信息
Patient aggression in older people with dementia is one of the most challenging problems of medical care in today's nursing homes. Existing wireless autography-based technologies help caregivers to collect data re...
详细信息
ISBN:
(纸本)9798350387186;9798350387179
Patient aggression in older people with dementia is one of the most challenging problems of medical care in today's nursing homes. Existing wireless autography-based technologies help caregivers to collect data related to behavioral and psychological symptoms of dementia. However, their inability to process the data in real-time reduces the efficiency of patient assessment and affects the quality of care. In this paper we present a computationally inexpensive technique that identifies aggressive behaviors on a sensor that measures the wrist acceleration of the dominant patient hand. Experiments show that the technique effectively detects aggressive behaviors in real-time and significantly reduces the wireless data transmissions.
The safe and secure implementation of increasingly complex features is a major challenge in the development of autonomous and distributed embeddedsystems. Automated design-time procedures that guarantee the fulfillme...
详细信息
ISBN:
(纸本)9798350348606;9783981926385
The safe and secure implementation of increasingly complex features is a major challenge in the development of autonomous and distributed embeddedsystems. Automated design-time procedures that guarantee the fulfillment of critical system properties are a promising approach to tackle this challenge. In the European project XANDAR, which took place from 2021 to 2023, eight partners developed an X-by-Construction (XbC) design framework to support developers in the creation of embedded software systems with certain safety, security, and real-time properties. The design framework combines a model-based toolchain with a hypervisor-based runtime architecture. It targets modern high-performance hardware, facilitates the integration of machine learning applications, and employs a library of trusted safety and security patterns to reduce the implementation and verification effort. This paper describes the concepts developed during the project, the prototypical implementation of the design framework, and its application in both an automotive and an avionics use case.
The paper outlines a methodology for crafting an embedded processor system to replicate image features computed within a mat lab software environment onto a hardware-based processor system. The proposed approach depen...
详细信息
The autonomous operations of unmanned aerial vehicles (UAV) necessitate the real-time analysis of information-rich signals, such as camera and LiDAR feeds, where the analysis algorithms often take the form of extremel...
详细信息
暂无评论