Environment perception is one of the major issues in autonomous driving systems. In particular, effective and robust drivable road region detection still remains a challenge to be addressed for autonomous vehicles in multi-lane roads, intersections and unstructured road environments. In this paper, a computer vision and neural networks-based drivable road region detection approach is proposed for fixed-route autonomous vehicles (e.g., shuttles, buses and other vehicles operating on fixed routes), using a vehicle-mounted camera, route map and real-time vehicle location. The key idea of the proposed approach is to fuse an image with its corresponding local route map to obtain the map-fusion image (MFI) where the information of the image and route map act as complementary to each other. The information of the image can be utilized in road regions with rich features, while local route map acts as critical heuristics that enable robust drivable road region detection in areas without clear lane marking or borders. A neural network model constructed upon the Convolutional Neural Networks (CNNs), namely FCN-VGG16, is utilized to extract the drivable road region from the fused MFI. The proposed approach is validated using real-world driving scenario videos captured by an industrial camera mounted on a testing vehicle. Experiments demonstrate that the proposed approach outperforms the conventional approach which uses non-fused images in terms of detection accuracy and robustness, and it achieves desirable robustness against undesirable illumination conditions and pavement appearance, as well as projection and map-fusion errors.
In modern civil aviation operations, the effective performance of pre-flight flight planning is the key of a safe flight, and the changing air traffic environment often requires modifying the pre-determined flight plan or even en route re-planning. This paper proposes an integrated system framework for the construction, re-planning, rehearsal and evaluation of computerized flight plans (CFP): the flight plan management and rehearsal system (FMRS). It provides interactive, graphic user interface - based ways of constructing flight routes using the navigation database and geographic information system (GIS), and the CFP parameters can be calculated automatically based on real performance data of various types of aircrafts. Simulation models of aircraft dynamics and airborne subsystems including the automatic flight control, navigation sensors and cockpit instruments are also integrated to support the rehearsal and evaluation of flight plans, and assist in analyzing en-route re-planning operations. All subsystems and components are integrated into an overall platform which is based on an inter-communication architecture and can be implemented on either centralized or distributed simulation platforms. Simulation and system evaluation results obtained from actual commercial flight routes demonstrate that the proposed system can effectively facilitate the preparation and evaluation of CFPs, and support the CFP re-planning decision-making process and operations.
This paper presents a SOA and cloud computing based architecture for the distributed simulation of advanced flight management system (FMS). The architecture is designed to facilitate the fast simulation, validation and evaluation of different FMS system designs and functionalities with customized system configurations and widely varying aircraft equipage levels under various operation conditions. It is also intended to accommodate the potential evolutionary extensions of new avionics concepts and functionalities such as the future CNS/ATM and 4-D trajectory based technologies. To address the requirements of flexibility, scalability and reusability, the design of the simulation architecture takes advantage of the cloud computing and service oriented architecture (SOA) and the key enabling technologies are developed: simulation unit service encapsulation, simulation agent technology and simulation orchestration. Based on the proposed architecture associated technologies, the simulation components are encapsulated as services or accessed through agents, and the configuration of different FMS system frameworks and simulation tasks can be achieved through simulation orchestration. A prototype avionic simulation system that implements the SOA/cloud computing architecture is developed and illustrated with application cases. The applications demonstrate that the proposed architecture enables fast and scalable simulation of both existing and new FMS design and technologies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.