Due to the high maneuverability and flexibility, unmanned aerial vehicles (UAVs) have been considered as a promising paradigm assist mobile edge computing (MEC) in many scenarios including disaster rescue field operation. Most existing research focuses on study of trajectory computation-offloading scheduling for UAV-assisted MEC stationary environments, could face challenges dynamic environments where locations UAVs devices (MDs) vary significantly. Some latest attempts develop policies by...

Mobile edge computing (MEC) has been considered as a promising paradigm to support the growing popularity of mobile devices (MDs) with similar capabilities cloud computing. Most existing research focuses on MEC enabled by terrestrial base stations (BSs), which is unable work in certain scenarios, e.g., disaster rescue and field operation. Some researchers have making efforts studying assisted unmanned-aerial-vehicles (UAVs) developed lots efficient scheduling algorithms. However, only UAVs...

Mobile devices (MDs) have undergone a booming development, yet are still capacity limited in computation and energy resources thus could face troubles when serving computation-intensive delay-sensitive applications. Mobile-edge computing (MEC) has been proposed to accommodate MDs with both satisfactory latency acceptable resources, by offloading MDs' tasks near-deployed edge servers (ESs). Whereas, solely ESs difficult meet distinct requirements of various applications, which leads the...

Mobile edge computing (MEC) has been envisioned as a promising paradigm that could effectively enhance the computational capacity of wireless user devices (WUDs) and quality experience mobile applications. One most crucial issues MEC is computation offloading, which decides how to offload WUDs’ tasks severs for further intensive computation. Conventional mathematical programming-based offloading approaches face troubles in dynamic environments due time-varying channel conditions (caused...

Space-air-ground integrated networks (SAGIN) provide seamless global coverage and cross-domain interconnection for the ubiquitous users in heterogeneous networks, which greatly promote rapid development of intelligent mobile devices applications. However, with limited computation capability energy budgets, it is still a serious challenge to meet stringent delay requirements computation-intensive Therefore, view significant success ground introduction edge computing (MEC) SAGIN has become...

Large-scale canals with cascaded pools are constructed wordwide to divert water from rich arid areas mitigate shortages. Efficient control of is essential improve water-diversion performance. Numerous model-based approaches have been proposed and made great progress for canal control. However, when the predictive model unavailable or unpromising long time step predictions, model-free could be considered as a possible way achieve efficient Since most existing focused on small reservoirs, this...

The surging popularity of adopting industrial robots in smart manufacturing has led to an increasing trend the simultaneous improvement energy costs and operational efficiency motion trajectory. Motivated by this, multi-objective trajectory planning subject kinematic dynamic constraints at multiple levels been considered as a promising paradigm achieve improvement. However, most existing model-based optimization algorithms tend come out with infeasible solutions, which results non-zero...

Data heterogeneity is one of the main challenges faced by federated learning (FL). Unlike traditional FL methods (e.g. FedAvg) which train a global model for all clients, personalized (PFL) can address above problem training each client. Current mainstream PFL researches first obtain through collaborative among clients and then fine-tune on client's local data to models. However, this two-staged approach has drawback: when different large, obtained final deviate from distributions therefore...

Quick Response (QR) code is one of the most worldwide used two-dimensional codes. Traditional QR codes appear as random collections black-and-white modules that lack visual semantics and aesthetic elements, which inspires recent works to beautify appearances However, these adopt fixed generation algorithms therefore can only generate with a pre-defined style. In this paper, combining Neural Style Transfer technique, we propose novel end-to-end method, named ArtCoder, stylized are...

Affordance detection is of great importance in robot operational tasks, due to its capability helping robots effectively interact with objects. Many affordance detectors have been proposed, primarily based on two-stage object detection, significantly suffering from the slow speed. Hence, recent years saw popularity one-stage encoder-decoder structures that adopt dilated convolutions extract high-resolution feature maps. However, high resolution features tend be computation and...

Recent years have witnessed the increasing popularity of mobile applications, e.g., virtual reality, unmanned driving, which are generally computation-intensive and latency-sensitive, posing a major challenge for resource-limited user equipment (UE). Mobile edge computing (MEC) has been proposed as promising approach to alleviate problem, by offloading tasks server (ES) deployed in close proximity UE. However, most existing task algorithms primarily based on centralized scheduling, could...

One of the key issues in mobile edge computing (MEC) is computation offloading, most policies which are developed based on mathematical programming (MP). Due to high computational complexity iterative MP-based policies, recent years have seen a popular trend develop offloading deep reinforcement learning (DRL). However, account poor generalization ability DRL models MEC environments with different network sizes and settings, it difficult directly apply DRL-based unseen environments....

Canals are constructed worldwidely to divert water from rich arid areas mitigate shortages. Since resource is fairly limited, it essential perform canal control efficiently improve water-delivery performance. A promising solution leverage model predictive (MPC), which calculates the desired action at each time step via reliable predictions of model. However, dependence degrades practicability and iterative calculation incurs intensive computations, especially for large-scale canals with...

Industrial robots are widely used in current production lines, and complex pipeline processes, especially those with different assembly requirements, designed for intelligent manufacturing the era of industry 4.0. During new crown epidemic, a large number car companies line to transform medical materials such as masks protective clothing, which provided strong guarantee fighting epidemic. In this scenario, is often assembled from robotic arms multiple suppliers. The traditional methods takes...