An automated driving systems data acquisition and analytics platform

Xia, Xin; Meng, Zonglin; Han, Xu; Li, Hanzhao; Tsukiji, Takahiro; Xu, Runsheng; Zheng, Zhaoliang; Ma, Jiaqi

doi:10.1016/j.trc.2023.104120

Cited by 129 publications

(96 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks are also rising to cope with the sensor fusion problem, in which the processed data of each sensor are provided in input to another neural network for data fusion [127]. However, CAVs also offer the possibility of cooperative sensor fusion, exploiting data from different vehicles with a proper processing pipeline as described in [128].…”

Section: Data Processingmentioning

confidence: 99%

Architecture and Potential of Connected and Autonomous Vehicles

Pipicelli,

Gimelli,

Sessa

et al. 2024

Vehicles

View full text Add to dashboard Cite

The transport sector is under an intensive renovation process. Innovative concepts such as shared and intermodal mobility, mobility as a service, and connected and autonomous vehicles (CAVs) will contribute to the transition toward carbon neutrality and are foreseen as crucial parts of future mobility systems, as demonstrated by worldwide efforts in research and industry communities. The main driver of CAVs development is road safety, but other benefits, such as comfort and energy saving, are not to be neglected. CAVs analysis and development usually focus on Information and Communication Technology (ICT) research themes and less on the entire vehicle system. Many studies on specific aspects of CAVs are available in the literature, including advanced powertrain control strategies and their effects on vehicle efficiency. However, most studies neglect the additional power consumption due to the autonomous driving system. This work aims to assess uncertain CAVs’ efficiency improvements and offers an overview of their architecture. In particular, a combination of the literature survey and proper statistical methods are proposed to provide a comprehensive overview of CAVs. The CAV layout, data processing, and management to be used in energy management strategies are discussed. The data gathered are used to define statistical distribution relative to the efficiency improvement, number of sensors, computing units and their power requirements. Those distributions have been employed within a Monte Carlo method simulation to evaluate the effect on vehicle energy consumption and energy saving, using optimal driving behaviour, and considering the power consumption from additional CAV hardware. The results show that the assumption that CAV technologies will reduce energy consumption compared to the reference vehicle, should not be taken for granted. In 75% of scenarios, simulated light-duty CAVs worsen energy efficiency, while the results are more promising for heavy-duty vehicles.

show abstract

Section: Data Processingmentioning

confidence: 99%

Architecture and Potential of Connected and Autonomous Vehicles

Pipicelli,

Gimelli,

Sessa

et al. 2024

Vehicles

View full text Add to dashboard Cite

show abstract

“…It transmits it to the flight platform, executing the patrol following the predetermined route. For the second, the operator wears a helmet with a Augmented reality represents a technological approach that merges the physical world with virtual information through real-time computational processing and multi-sensor fusion [31][32][33][34][35][36][37]. This technology superimposes virtual information on factual data and provides an interface for human-digital world interaction [9,38].…”

Section: Our Approachmentioning

confidence: 99%

VisionICE: Air–Ground Integrated Intelligent Cognition Visual Enhancement System Based on a UAV

Yang

et al. 2023

Drones

View full text Add to dashboard Cite

Post-disaster search and rescue is critical to disaster response and recovery efforts and is often conducted in hazardous and challenging environments. However, the existing post-disaster search and rescue operations have problems such as low efficiency, limited search range, difficulty in identifying the nature of the target, and wrong target location. Therefore, this study develops an air–ground integrated intelligent cognition visual enhancement system based on a UAV (VisionICE). The technique combines a portable AR display device, a camera-equipped helmet, and a quadcopter UAV for efficient patrols over a wide area. First, the system utilizes wireless image sensors on the UAV and helmet to capture images from the air and ground views. Using the YOLOv7 algorithm, the cloud server calculates and analyzes these visual data to accurately identify and detect targets. Lastly, the AR display device obtains real-time intelligent cognitive results. The system allows personnel to simultaneously acquire air and ground dual views and achieve brilliant cognitive results and immersive visual experiences in real time. The findings indicate that the system demonstrates significant recognition accuracy and mobility. In contrast to conventional post-disaster search and rescue operations, the system can autonomously identify and track targets of interest, addressing the difficulty of a person needing help to conduct field inspections in particular environments. At the same time, the system can issue potential threat or anomaly alerts to searchers, significantly enhancing their situational awareness capabilities.

show abstract

“…Note that the computation time reported here is based solely on the measurement of the traffic states, excluding the time required for object detection, inference, and data transmission. Interested readers are referred to [16], [17].…”

Section: B Computation Timementioning

confidence: 99%

Real-Time Traffic State Measurement Using Autonomous Vehicles Open Data

Wang,

Keo,

Saberi

2023

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

Autonomous vehicle (AV) technologies are expected to disrupt the existing urban transportation systems. AVs' multi-sensor system can generate large amount of data, often used for localization and safety purposes. This study proposes and demonstrates a practical framework for real-time measurement of local traffic states using LiDAR data from AVs. Fundamental traffic flow variables including volume, density, and speed are computed along with the traffic time-space diagrams. The framework is tested using the Waymo Open dataset. Results provide insights into the possibility of real-time traffic state estimation using AVs' data for traffic operations and management applications.INDEX TERMS Autonomous vehicles, traffic flow, real-time state measurement, Lagrangian sensing.

show abstract

An automated driving systems data acquisition and analytics platform

Cited by 129 publications

References 31 publications

Architecture and Potential of Connected and Autonomous Vehicles

Architecture and Potential of Connected and Autonomous Vehicles

VisionICE: Air–Ground Integrated Intelligent Cognition Visual Enhancement System Based on a UAV

Real-Time Traffic State Measurement Using Autonomous Vehicles Open Data

Contact Info

Product

Resources

About