A Review on IoT Deep Learning UAV Systems for Autonomous Obstacle Detection and Collision Avoidance

Fraga‐Lamas, Paula; Ramos, Lucía; Mondéjar-Guerra, Víctor Manuel; Fernández‐Caramés, Tiago M.

doi:10.3390/rs11182144

Cited by 110 publications

(69 citation statements)

References 140 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Photogrammetric recording of the real urban site II with small unmanned aerial vehicles (UAV) was performed for better presentation of the results using the GPR-TPS model of the certain UUI. In remote-sensing applications UAV are mostly used for photogrammetric purposes, the production of 3D-models of objects, digital surface models, digital terrain models (DTM) and orthophotos [39,40]. The Mikrokopter Hexa XL UAV system with six rotors, three of which rotate in a clockwise direction and three in a counterclockwise direction, was used.…”

Section: Methods and Instrumentationmentioning

confidence: 99%

Application of Kinematic GPR-TPS Model with High 3D Georeference Accuracy for Underground Utility Infrastructure Mapping: A Case Study from Urban Sites in Celje, Slovenia

et al. 2020

View full text Add to dashboard Cite

This paper describes in detail the applicability of the developed ground-penetrating radar (GPR) model with a kinematic GPR and self-tracking (robotic) terrestrial positioning system (TPS) surveying setup (GPR-TPS model) for the acquisition, processing and visualisation of underground utility infrastructure (UUI) in a real urban environment. The integration of GPR with TPS can significantly improve the accuracy of UUI positioning in a real urban environment by means of efficient control of GPR trajectories. Two areas in the urban part of Celje in Slovenia were chosen. The accuracy of the kinematic GPR-TPS model was analysed by comparing the three-dimensional (3D) position of UUI given as reference values (true 3D position) from the officially consolidated cadastre of utility infrastructure in the Republic of Slovenia and those obtained by the GPR-TPS method. To determine the reference 3D position of the GPR antenna and UUI, the same positional and height geodetic network was used. Small unmanned aerial vehicles (UAV) were used for recording to provide a better spatial display of the results of UUI obtained with the GPR-TPS method. As demonstrated by the results, the kinematic GPR-TPS model for data acquisition can achieve an accuracy of fewer than 15 centimetres in a real urban environment.

show abstract

Section: Methods and Instrumentationmentioning

confidence: 99%

Application of Kinematic GPR-TPS Model with High 3D Georeference Accuracy for Underground Utility Infrastructure Mapping: A Case Study from Urban Sites in Celje, Slovenia

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The quantity and quality of data is still a problem for good generalization capability [86]. In addition, the development of more realistic virtual datasets is an open problem, which can be solved by recording real cases [87][88][89].…”

Section: Future Directionsmentioning

confidence: 99%

A Survey on Theories and Applications for Self-Driving Cars Based on Deep Learning Methods

Chen

et al. 2020

Applied Sciences

110

View full text Add to dashboard Cite

Self-driving cars are a hot research topic in science and technology, which has a great influence on social and economic development. Deep learning is one of the current key areas in the field of artificial intelligence research. It has been widely applied in image processing, natural language understanding, and so on. In recent years, more and more deep learning-based solutions have been presented in the field of self-driving cars and have achieved outstanding results. This paper presents a review of recent research on theories and applications of deep learning for self-driving cars. This survey provides a detailed explanation of the developments of self-driving cars and summarizes the applications of deep learning methods in the field of self-driving cars. Then the main problems in self-driving cars and their solutions based on deep learning methods are analyzed, such as obstacle detection, scene recognition, lane detection, navigation and path planning. In addition, the details of some representative approaches for self-driving cars using deep learning methods are summarized. Finally, the future challenges in the applications of deep learning for self-driving cars are given out.

show abstract

“…Searching for the best location of UAVs with model-based approaches is a difficult problem, since many restriction and assumption should be considered. Such a task can indeed be solved by resorting to RL approaches [38,71]. Agents in RL are UAVs, and their flying parameters are the system state; in a certain time period, the numbers of satisfied users are measured as reward function; the action consists of lowering or increasing the speed of the UAVs.…”

Section: Design Of Collectors and Relaysmentioning

confidence: 99%

On the Application of Machine Learning to the Design of UAV-Based 5G Radio Access Networks

et al. 2020

View full text Add to dashboard Cite

A groundbreaking design of radio access networks (RANs) is needed to fulfill 5G traffic requirements. To this aim, a cost-effective and flexible strategy consists of complementing terrestrial RANs with unmanned aerial vehicles (UAVs). However, several problems must be solved in order to effectively deploy such UAV-based RANs (U-RANs). Indeed, due to the high complexity and heterogeneity of these networks, model-based design approaches, often relying on restrictive assumptions and constraints, exhibit severe limitation in real-world scenarios. Moreover, design of a set of appropriate protocols for such U-RANs is a highly sophisticated task. In this context, machine learning (ML) emerges as a useful tool to obtain practical and effective solutions. In this paper, we discuss why, how, and which types of ML methods are useful for designing U-RANs, by focusing in particular on supervised and reinforcement learning strategies.

show abstract

A Review on IoT Deep Learning UAV Systems for Autonomous Obstacle Detection and Collision Avoidance

Cited by 110 publications

References 140 publications

Application of Kinematic GPR-TPS Model with High 3D Georeference Accuracy for Underground Utility Infrastructure Mapping: A Case Study from Urban Sites in Celje, Slovenia

Application of Kinematic GPR-TPS Model with High 3D Georeference Accuracy for Underground Utility Infrastructure Mapping: A Case Study from Urban Sites in Celje, Slovenia

A Survey on Theories and Applications for Self-Driving Cars Based on Deep Learning Methods

On the Application of Machine Learning to the Design of UAV-Based 5G Radio Access Networks

Contact Info

Product

Resources

About