Recently, unmanned aerial vehicles (UAVs) or drones have emerged as a ubiquitous and integral part of our society. They appear in great diversity in a multiplicity of applications for economic, commercial, leisure, military and academic purposes. The drone industry has seen a sharp uptake in the last decade as a model to manufacture and deliver convergence, offering synergy by incorporating multiple technologies. It is due to technological trends and rapid advancements in control, miniaturization, and computerization, which culminate in secure, lightweight, robust, more-accessible and cost-efficient UAVs. UAVs support implicit particularities including access to disaster-stricken zones, swift mobility, airborne missions and payload features. Despite these appealing benefits, UAVs face limitations in operability due to several critical concerns in terms of flight autonomy, path planning, battery endurance, flight time and limited payload carrying capability, as intuitively it is not recommended to load heavy objects such as batteries. As a result, the primary goal of this research is to provide insights into the potentials of UAVs, as well as their characteristics and functionality issues. This study provides a comprehensive review of UAVs, types, swarms, classifications, charging methods and regulations. Moreover, application scenarios, potential challenges and security issues are also examined. Finally, future research directions are identified to further hone the research work. We believe these insights will serve as guidelines and motivations for relevant researchers. 

/pdf/unmanned-aerial-vehicles-uavs-practical-aspects-applications-1daaaq4t.pdf

Unmanned aerial vehicles (UAVs): practical aspects, applications, open challenges, security issues, and future trends

• This paper proposes a SCA algorithm variant, called ARSCA. • ARSCA improves the convergence accuracy and avoids premature convergence. • This paper compares ARSCA with classical algorithms, variations of other algorithms. • ARSCA is applied to six engineering design problems and its results are satisfactory. The sine cosine algorithm (SCA) is a well-known meta-heuristic optimization algorithm. SCA has received much attention in various optimization fields due to its simple structure and excellent optimization capabilities. However, the dimension of objective function also increases with the increasing complexity of optimization tasks. This makes the original SCA appear to have insufficient optimization capability and likely to fall into premature convergence. A multi-mechanism acting variant of SCA, called ARSCA, is proposed to address the above deficiencies. ARSCA is an enhanced SCA algorithm based on the adaptive quadratic interpolation mechanism (AQIM) and Rounding mechanism (RM). RM enables a more balanced state between exploration and exploitation of the ARSCA. AQIM enhances local exploitation capabilities. To verify the performance of ARSCA, we compared ARSCA with some advanced traditional optimization algorithms and variants of algorithms for 30 consecutive benchmark functions of IEEE CEC2014. In addition, ARSCA was applied to 6 constrained engineering optimization problems. These six algorithms include the tension-compression spring design problem, the welded beam design problem, the pressure vessel design problem, the I-beam design problem, the speed reducer design problem, and the three-bar design problem. Experimental results show that ARSCA outperforms its competitors in both the solution quality and the ability to jump out of the local optimum. The relevant codes for the paper are publicly available at https://github.com/YangXiao9799/paper_ARSCA . 

An adaptive quadratic interpolation and rounding mechanism sine cosine algorithm with application to constrained engineering optimization problems

During the last two decades, managers have been applying Building Information Modeling (BIM) to improve the quality of management as well as operation. The effectiveness of applications within a BIM environment is restrained by the limited immersive experience in virtual environments. Defined as the immersive visualization of virtual scenes, Virtual Reality (VR) is an emerging technology that can be actively explored to expand BIM to more usage. This paper highlights the need for a structured methodology for the integration of BIM/VR and gives a generic review of BIM and VR in training platforms for management in infrastructures. The rationales for fire evacuation training were formed based on the review. Then, methods of configuring BIM + VR prototypes were formulated for emergency response in highway tunnels. Furthermore, a conceptual framework integrating BIM with VR was proposed to enable the visualization of the physical context in real-time during the training. The result indicated that, extended to the training system of highway management via the “hand” of BIM, the VR solution can benefit more areas, such as the cost of fire evacuation drills in highway tunnels and the tendency of accidents to occur in the emergency response.

/pdf/integrating-virtual-reality-and-building-information-1w40zr1l.pdf

Integrating Virtual Reality and Building Information Modeling for Improving Highway Tunnel Emergency Response Training

With the increasing frequency of autonomous driving, more and more attention is paid to personalized path planning. However, the path selection preferences of users will change with internal or external factors. Therefore, this paper proposes a personalized path recommendation strategy that can track and study user's path preference. First, we collect the data of the system, establish the relationship with the user preference factor, and get the user's initial preference weight vector by dichotomizing the K-means algorithm. The system then determines whether user preferences change based on a set threshold, and when the user's preference changes, the current preference weight vector can be obtained by redefining the preference factor or calling difference perception. Finally, the road network is quantized separately according to the user preference weight vector, and the optimal path is obtained by using Tabu search algorithm. The simulation results of two scenarios show that the proposed strategy can meet the requirements of autopilot even when user preferences change.

/pdf/a-personalized-navigation-route-recommendation-strategy-28b51gn2.pdf

Jiean Pei

Papers

A deep reinforcement learning based method for real-time path planning and dynamic obstacle avoidance