Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metavers...
详细信息
Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach
A new teaching model of teaching-innovation-competition is presented and a wisdom course based on this model is developed for mechatronics engineering majors, mainly to deal with several existing problems such as limi...
详细信息
This study examines the application of big data clustering algorithms in the field of electrical engineering automation. Electrical engineering automation is a key area that covers power system management, smart grids...
详细信息
In response to the prevalent social issue of elderly individuals living alone who lack independent mobility and face difficulties in standing up and getting up, a multi-modal intelligent elderly assistance wheelchair ...
详细信息
The quality of welding is directly related to the performance and life of welded products. This paper proposes an automatic defect detection method using deep learning on a small weld X-ray image dataset. Combined wit...
详细信息
In practice, using vision measurement technology based on structured light to reconstruct the complex weld is a feasible way for providing the essential parameters for the welding polishing robot and guiding it to gri...
详细信息
Rule representation and a switchable pattern matching model for hot-rolled steel production (HRSP) scheduling system with rule engine are presented in this paper. Six features of scheduling rules for HRSP are describe...
详细信息
To improve the quality of self-pierce riveted joints, this paper uses a multi-objective optimisation method that incorporates a quadratic polynomial response surface model and the NSGA-II algorithm to optimise the par...
详细信息
The content and density of road traffic signs affect the driving behaviour of drivers and the smoothness of urban traffic. There is a lack of quantitative research methods on the current information threshold of traff...
详细信息
Magnesium alloys with excellent degradability and biocompatibility are promising materials for biomedical implants,saving patients the burden of second ***,their mechanical properties and corrosion resistance are sign...
详细信息
Magnesium alloys with excellent degradability and biocompatibility are promising materials for biomedical implants,saving patients the burden of second ***,their mechanical properties and corrosion resistance are significantly below the requirements for implant *** study aims to improve the mechanical and corrosion resistance properties of Mg-3Zn-0.2Ca alloy by pre-torsion treatment,and find out the optimal shear *** rod-shaped Mg-3Zn-0.2Ca alloy specimens were pre-torsion treated at different torsion *** effect of free-end torsion on Mg-3Zn-0.2Ca alloy was characterized through microstructure analysis,mechanical testing,and corrosion ***-torsion treatment can refine grain and induce twins and dislocations in Mg-3Zn-0.2Ca *** surface hardness increases with the increase in torsion *** yield strength and ultimate strength initially increase and then decrease with increasing torsion angle,while ductility decreases with increasing torsion *** with a shear strain of 30%exhibit the highest tensile strength,reaching 284.78±10.62 MPa,with an elongation of 19.37±1.66%.Furthermore,they show a significant improvement in fatigue lives both before and after *** the stress amplitude is 120 MPa,the fatigue lives for specimens without pre-torsion treatment are 54,275 cycles and 4324 cycles before and after pre-corrosion,while they increased significantly to 92,015 cycles and 5050 cycles with the 30%shear strain,***,the 30%shear strain specimens show a significant reduction in corrosion *** conclusion,pre-torsion treatment can effectively modify the microstructure of Mg-3Zn-0.2Ca alloy,enhancing both mechanical properties and corrosion *** optimal shear strain for this improvement is 30%.This study provides a practical method to enhance the mechanical properties and corrosion resistance of Mg-3Zn-0.2Ca alloy,making it more suitable for biomedical implan
暂无评论