This paper describes a simple low cost embedded vision system which has been developed and can satiate the requirement of a small vision system in various surveillance and control systems and in applications which req...
详细信息
ISBN:
(纸本)9781424423675
This paper describes a simple low cost embedded vision system which has been developed and can satiate the requirement of a small vision system in various surveillance and control systems and in applications which require an artificial vision to be embedded in them. This system utilizes a low cost CMOS camera module and all image data is processed by a high speed, low cost AVR microcontroller. The embedded vision system implements simple image processing algorithms and taps the processing power of the AVR microcontrollers with the firmware which in turn also helps to reduce the hardware cost. This system being simple and portable can be used in applications where on board image processing is a fundamental requirement and use of a traditional vision system is not possible.
As the complexity of the missions to be performed by mechatronicsystems grows, so does the amount of embedded software to be produced and the number of involved specialists. System complexity management and software ...
详细信息
ISBN:
(纸本)0780390466
As the complexity of the missions to be performed by mechatronicsystems grows, so does the amount of embedded software to be produced and the number of involved specialists. System complexity management and software integration become more important. In this paper, we present an initial implementation of a real-time capable software framework for complex mechatronicsystems that facilitates embedded software development and integration. The framework also promotes software components reuse across applications, architecture reuse and software portability across hardware platforms. To illustrate the proposed solution, we present two applications of the framework: an autonomous indoor navigation system for mobile robots and a driver assistance system for smart cars.
Ambient assisted living and intelligent transportation systems are becoming strongly coupled. There is the necessity of improving the quality of life by developing inclusive mobility solutions for impaired people. In ...
详细信息
Ambient assisted living and intelligent transportation systems are becoming strongly coupled. There is the necessity of improving the quality of life by developing inclusive mobility solutions for impaired people. In this paper, we focus on a monocular vision-based system to assist people during walking, jogging, and running in outdoor environments. The impaired user is guided along a path represented by a lane or line on a dedicated runway. We developed a set of image processing algorithms to extract lines/lanes to follow. The embedded system is based on a small camera and a board that is responsible for processing the images and communicating with the developed haptic device. The haptic device is formed by a set of two gloves equipped with vibration motors that drive the user to the right direction. The vibration sequences are generated according to a robotic-like controller, considering the user as a two wheel steering robot, where the rotational and translation velocity can be controlled. The results obtained show that the overall system is able to detect the right path and to provide the right stimuli to the user, by means of the gloves, up to a speed over 10 km/h.
Development of mechatronic products, and their controllers, carries a series of difficulties related mainly to product complexity. This paper discusses such difficulties and introduces a proposal of a framework of pro...
详细信息
ISBN:
(纸本)9781424423675
Development of mechatronic products, and their controllers, carries a series of difficulties related mainly to product complexity. This paper discusses such difficulties and introduces a proposal of a framework of prototype tools that aim to support controller design for mechatronicsystems by providing control software generation. This work emphasizes the high level system description embedded in such framework and the model integration aspects.
作者:
Xu, JiaYork Univ
Dept Comp Sci & Engn Toronto ON M3J 2R7 Canada
A software architecture that makes it much easier to verify the system timing properties is presented. The software architecture is based on a pre-run-time scheduling approach and is suitable for many complex real-tim...
详细信息
ISBN:
(纸本)9780780397200
A software architecture that makes it much easier to verify the system timing properties is presented. The software architecture is based on a pre-run-time scheduling approach and is suitable for many complex real-time embeddedsystems. A comparison of the software architecture based on pre-run-time scheduling with software architectures based on priority scheduling is also presented.
This paper discusses problems in complex mechatronic system design observed in an industrial setting. In the process of adding functionality to mechatronicsystems it is important to manage complexity. It is observed ...
详细信息
ISBN:
(纸本)9781424423675
This paper discusses problems in complex mechatronic system design observed in an industrial setting. In the process of adding functionality to mechatronicsystems it is important to manage complexity. It is observed that an important aspect in managing complexity is keeping a system wide overview and understanding among system architects and engineers. A function modeling approach is proposed to connect different design aspect views (e.g. functional view, workflow view, requirements view) on different levels of abstraction to support the architects in the conceptual design process. The overview will improve system understanding.
This paper introduces a kernel-based method for learning feedforward controllers within an Iterative Learning Control (ILC) framework tailored for nonlinear processes. Unlike traditional ILC algorithm that relies on t...
详细信息
ISBN:
(纸本)9798331516246;9798331516239
This paper introduces a kernel-based method for learning feedforward controllers within an Iterative Learning Control (ILC) framework tailored for nonlinear processes. Unlike traditional ILC algorithm that relies on the knowledge of first principle-based models, this approach leverages a data-driven methodology to develop an iterative control update rule using kernel-based training. We compared this method against a traditional ILC scheme and a baseline neural networkbased approach. The effectiveness of the proposed method is demonstrated through a unicycle path-following control problem, evaluated across various simulated test scenarios. Performance metrics include vehicle tracking error and ILC convergence speed, confirming the effectiveness of the proposed data-driven approach.
Model-based development tools are one possible solution to handle the increasing complexity of mechatronicsystems. While traditional approaches often separate design of hardware and software, especially in mechatroni...
详细信息
ISBN:
(纸本)9781424423675
Model-based development tools are one possible solution to handle the increasing complexity of mechatronicsystems. While traditional approaches often separate design of hardware and software, especially in mechatronicsystems hardware/software interaction is the most critical component. Hence, both aspects must be considered in this context. The goal is a model-based development tool for software/hardware co-design including the generation of efficient code for the respective target platforms. EasyLab is a modular and easily expandable development tool especially suitable for such applications. Its objectives are to facilitate reusability and to accelerate the development process. It raises the level of abstraction and thus simplifies the development of mechatronicsystems even for unexperienced users. A graphical user interface provides various modeling languages that are easy to use. By employing platform optimized generation of the code, efficiency of the resulting programs can be guaranteed, which we demonstrate on a set of experimental mechatronicsystems.
In this concept paper the notion of the configurations and configurability is interpreted in the context of robotic and automation systems. A review is given on related methods and techniques, and how configurations r...
详细信息
ISBN:
(纸本)9781509061907
In this concept paper the notion of the configurations and configurability is interpreted in the context of robotic and automation systems. A review is given on related methods and techniques, and how configurations relate to system and software life cycles. The modeling principles for configuration based design are outlined and a proposal is made for the design process based on systems and software product line principles, including a completely new way to reuse system model data by storing them as semantic descriptions in SW delivery packages, to be queried by system designers. A tentative design example is presented.
The objective of this study is to identify the optimal object detection architecture for training on a specific type of defect detection, namely incorrectly polished surfaces on aluminium elements. In order to facilit...
详细信息
ISBN:
(纸本)9798331516246;9798331516239
The objective of this study is to identify the optimal object detection architecture for training on a specific type of defect detection, namely incorrectly polished surfaces on aluminium elements. In order to facilitate a meaningful comparison of the various architectures, a maximum training time of approximately one hour was established for each architecture. Using the Darknet framework and a specific dataset, five architectures were compared (for the time being). The parameters of the various architectures, including network size, number of batches, and so forth, were modified according to a well-defined and systematic procedure. The preliminary findings indicate that the YOLOv4-tiny network exhibits superior training performance on this dataset, rendering it an optimal choice for industrial applications. This research provides support to small and mediumsized enterprises (SMEs) by identifying effective object detection architectures for quality control and highlighting avenues for advancing AI-driven defect detection in manufacturing.
暂无评论