Embedded systems have been widely used in various fields, such as smart cities, automotive electronics, and 5G chips, etc. In order to solve the modeling problem of embedded systems, a solution is obtained using an ex...
详细信息
ISBN:
(纸本)9789819756742;9789819756759
Embedded systems have been widely used in various fields, such as smart cities, automotive electronics, and 5G chips, etc. In order to solve the modeling problem of embedded systems, a solution is obtained using an extended Petri net synthesis operation. For the object-oriented Petri net based representation for embedded systems (OOPRES+), a kind of shared object subnet synthesis operation method is proposed. The preservation of liveness and boundedness of the synthesis net system has been investigated to alleviate the problem of state space explosion of OOPRES+. The modeling and analysis of an intelligent transportation system illustrates the effectiveness of the synthesis method. Results obtained provide a favorable means for the modeling of the large-scale complex embedded systems.
This paper describes a comprehensive system for real-time pedestrian detection and tracking, which is intended to suit the needs of intelligent video surveillance in dynamic metropolitan areas. The main detection comp...
详细信息
When large-scale photovoltaic power generation is put into use, it is necessary to consider how to keep photovoltaic panels as high as possible. However, the efficiency of photovoltaic panels is not static, its effici...
详细信息
This paper introduces a modular IoT-based framework for the monitoring and control of critical infrastructure, addressing challenges such as system resilience, adaptability, and low-energy operation. The proposed modu...
详细信息
In this paper, we propose a radar odometry structure that directly utilizes radar velocity measurements for dead reckoning while maintaining its ability to update estimations within the Kalman filter framework. Specif...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
In this paper, we propose a radar odometry structure that directly utilizes radar velocity measurements for dead reckoning while maintaining its ability to update estimations within the Kalman filter framework. Specifically, we employ the Doppler velocity obtained by a 4D Frequency Modulated Continuous Wave (FMCW) radar in conjunction with gyroscope data to calculate poses. This approach helps mitigate high drift resulting from accelerometer biases and double integration. Instead, tilt angles measured by gravitational force are utilized alongside relative distance measurements from radar scan matching for the filter's measurement update. Additionally, to further enhance the system's accuracy, we estimate and compensate for the radar velocity scale factor. The performance of the proposed method is verified through five real-world open-source datasets. The results demonstrate that our approach reduces position error by 62% and rotation error by 66% on average compared to the state-of-the-art radar-inertial fusion method in terms of absolute trajectory error.
Cloud computing is the practice of offering services like servers, storage, analytics, and databases to networks or computer systems worldwide. With enhanced technical infrastructure, Internet users can now use comput...
详细信息
This paper explores the utilization of machine learning techniques to develop an approximate input-output linearizable neural network model aimed at improving disturbance attenuation. The incorporation of a learning m...
详细信息
ISBN:
(纸本)9798350364309;9798350364293
This paper explores the utilization of machine learning techniques to develop an approximate input-output linearizable neural network model aimed at improving disturbance attenuation. The incorporation of a learning mechanism allows for the synthesis of control laws that effectively address disturbance attenuation by imposing a specific parameterization and an L-2 gain constraint during the learning process. The constraint is subsequently relaxed into a set of diagonally dominant (DD) matrix constraints. This relaxation leads to a series of linear constraints that can be seamlessly incorporated into the loss criterion. Therefore, a log-sum-exp (LSE) function-a smoothed version of the max function- of these linearized constraints is added to the loss criterion which results in an unconstrained problem amenable to training via back-propagation. The proposed methodology is applied to two variants of nonlinear perturbed pendulum systems. The results emphasize the effectiveness of the model, both on its own and as a framework for developing control laws for disturbance attenuation.
This paper proposes a novel passenger- oriented intelligent intersection-level control named "Integrated Signal and Bus Lane control" (ISBLC), which aims to balance between the optimization of passenger thro...
详细信息
ISBN:
(纸本)9798350399462
This paper proposes a novel passenger- oriented intelligent intersection-level control named "Integrated Signal and Bus Lane control" (ISBLC), which aims to balance between the optimization of passenger throughput and the reliability of public transport operations by dynamically adjusting traffic signals and assigning dedicated bus lanes to upstream lanes of the intersection, based on the observed traffic conditions, as well as the Vehicle-to- Infrastructure (V2I) communication. The method utilizes reinforcement learning, which allows the system to learn and adapt to continuously changing traffic conditions in real-time, while enabling the proposed scheme to continuously improve its decisions based on the consequences of previous actions, leading to more efficient traffic management. Findings suggest that ISBLC, when compared to traditional traffic signal and bus prioritization approaches, shows excellent results both in terms of transit reliability and level of service of adjacent road traffic, in a wide range of demand profiles.
This article is concerned with data-driven analysis and controller design for continuous-time sampled-data systems. The linear system considered in this paper is controlled under the periodic event-triggering transmis...
详细信息
This article is concerned with data-driven analysis and controller design for continuous-time sampled-data systems. The linear system considered in this paper is controlled under the periodic event-triggering transmission mechanism. Firstly, the periodic event-triggered control (PETC) systems are modeled and analyzed by the time-delay approach. And model-based stability conditions are presented by invoking the Lyapunov stability approach. Secondly, based on the model-based conditions and a popular data-based representation, data-based stability criteria are deduced by using only noisy data. The stability criteria guarantee the stability properties robustly for all unknown systems consistent with the measured data. The data-driven estimation of the maximum detecting interval (MDI) is also obtained directly without model knowledge. Beyond that, the data-based method for the controller design as well as computing a possibly large MDI under various triggering parameters is put forth. Finally, the effectiveness of the proposed methods is demonstrated by the numerical simulation and the hardware-in-the-loop (HIL) experiment.
Technological advancement transforms construction jobsites into more intelligentsystems. Among the technologies, robotics relies on environmental perception, such as the motion and dynamics of interacting objects;a d...
详细信息
ISBN:
(数字)9780784485224
ISBN:
(纸本)9780784485224
Technological advancement transforms construction jobsites into more intelligentsystems. Among the technologies, robotics relies on environmental perception, such as the motion and dynamics of interacting objects;a digital twin expands its capabilities by collecting real-time data of the physical twin, including spatial and physical properties. Given booming attention and efforts in such technologies, there lacks a non-invasive approach to collect jobsite objects' 3D location and orientation, which is a required step for physically based modeling. As an initial effort, this paper proposes a vision-based approach to estimate the 6-DoF object pose of construction jobsite objects from a single image while leveraging deep learning. Tests are performed on a brick and a concrete block of cuboid shape. The evaluation against ground truth data, collected by an RGB-D camera, presents a certain potential for utilizing a non-invasive perception approach to collect jobsite objects' advanced kinematic data for extended capabilities of intelligentsystems.
暂无评论