Method and system for automated driving system experience monitoring and/or management
A technology for automatic driving and classification systems, applied in general control systems, traffic control systems, neural learning methods, etc., can solve problems such as congestion, exhaustion, and unrealistic data transmission duration
Pending Publication Date: 2022-05-27
哲内提
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
If all the sensing data utilized by an ADS onboard a vehicle is sent to a remote server for offline processing and analysis while the vehicle is being driven, the large amount of data to be transferred could mean that even over very high bandwidth connections, The duration of the data transfer may also be unrealistic
Furthermore, the high bandwidth, high quality connection and long duration of data transfer will exhaust communication resources as well as power resources on each vehicle and / or monitoring entity whenever data transfer is attempted
For a monitoring entity such as a backend server that monitors and manages a vehicle fleet ADS where the fleet includes a large number of vehicles, if a large number of vehicles in the fleet transmit all the data for configuring their respective onboard ADSs to the backend server at the same time, congestion such as the added complexity of
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0056]The present disclosure will now be described in detail with reference to the accompanying drawings, in which some example embodiments of the disclosed technology are shown. However, the disclosed techniques may be implemented in other forms and should not be construed as limited to the disclosed example embodiments. The disclosed example embodiments are provided to fully convey the scope of the disclosed technology to those skilled in the art. Those skilled in the art will understand that a single hardware circuit may be used, using software working with a programmed microprocessor or general purpose computer, using one or more application specific integrated circuits (ASICs) and / or using one or more digital signals A processor (DSP) to implement the steps, services and functions described herein. It will also be understood that when the disclosure is described in the form of a method, it can also be embodied in a device comprising one or more processors, one or more me...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The disclosure relates to methods and systems for automated driving system experience monitoring and / or management. Various methods for managing and / or monitoring a new experience of an automatic driving system (ADS) of a vehicle are disclosed. In one example, an ADS experience library is used as training data for an auto-encoder onboard a vehicle. A data stream representing a driving experience encountered by a vehicle while it is driven around is appropriately segmented and passed through an autoencoder. The output of the autoencoder amplifies the reconstruction error of any data not included in the data segments in the training dataset. This makes it possible to identify, in the data stream through the autoencoder, abnormal behavior data indicative of a new experience encountered by the vehicle when it is driven around. By identifying anomalous behavior data in the data stream, only the anomalous behavior data may be sent to a back-end fleet server configured to monitor and manage the vehicle fleet in an in-time and bandwidth-efficient manner.
Description
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS [0002] This patent application claims priority to European Patent Office Application No. 20210095.4, filed on November 26, 2020, entitled "Method and System for Experience Monitoring and / or Management of Autonomous Driving Systems", which European Patent Office application Assigned to the assignee of this patent application and expressly incorporated herein by reference. technical field [0003] The present disclosure relates to methods, systems, and related aspects for driving experience monitoring and / or management of an automated or autonomous driving system (ADS) of a vehicle, wherein a new machine learning model, such as an autoencoder, implemented on each vehicle is used to ADS driving experience or rare ADS driving experience is identified as abnormal sensing behavior. The machine learning model is configured to differentiate between any new or rare experiences and experiences the vehicle encounters while driving around ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G05B23/02
CPCG05B23/0221G06V20/56G06N3/088G06N3/047G06N3/044G06N3/045G06F18/2414G06Q50/40G06N20/00B60W2555/20B60W60/001G08G1/20G06F18/214
Inventor 芒努斯·于伦哈马尔卡尔·桑登马吉德·霍桑德·瓦基勒扎德
Owner 哲内提