Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and system for distributed learning and adaptation in autonomous driving vehicles

A technology for vehicles, projects, applied in the field of distributed learning and adaptation and systems used in autonomous vehicles, which can solve problems such as the inability to provide depth measurement

Pending Publication Date: 2020-03-06
PLUSAI CORP
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

2D images also do not provide depth measurements
However, how to adapt while the vehicle is running remains an unsolved problem since traditional methods cannot label these data on the fly to generate meaningful training data.
Also, given the volume of data that fleets can collect, how to adapt based on the experience of thousands of vehicles remains an unsolved problem

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system for distributed learning and adaptation in autonomous driving vehicles
  • Method and system for distributed learning and adaptation in autonomous driving vehicles
  • Method and system for distributed learning and adaptation in autonomous driving vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In the following detailed description, numerous specific details are given by way of example in order to provide a thorough understanding of the relevant teachings. It will be apparent, however, to one skilled in the art that the present teachings may be practiced without these details. In other instances, well-known methods, procedures, components, and / or circuits have been described at a relatively high level without detail in order to avoid unnecessarily obscuring the present teachings.

[0051] The present disclosure generally relates to systems, methods, media, and other implementations for developing, training, and configuring efficient computer-aided perception systems for autonomous vehicles. In various embodiments, the present teachings disclose in-situ computer-aided perception systems, methods, and media for cross-validation across dimensions and object detection based on on-the-fly models, enabling automatic labeling of on-the-fly training data. With the ab...

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

No PUM Login to View More

Abstract

The present teaching relates to system, method, medium for in-situ perception in an autonomous driving vehicle. A plurality of types of sensor data acquired continuously by a plurality of types of sensors deployed on the vehicle are first received, where the plurality of types of sensor data provide information about surrounding of the vehicle. Based on at least one model, one or more items are tracked from a first of the plurality of types of sensor data acquired by one or more of a first type of the plurality of types of sensors, wherein the one or more items appear in the surrounding of thevehicle. At least some of the one or more items are then automatically labeled on-the-fly via either cross modality validation or cross temporal validation of the one or more items and are used to locally adapt, on-the-fly, the at least one model in the vehicle.

Description

[0001] Cross References to Related Applications [0002] This application claims priority to US Application 15 / 615,198, filed June 6, 2017, which is hereby incorporated by reference in its entirety. technical field [0003] The present teachings generally relate to computer-aided perception. In particular, the present teachings relate to adaptive computer-aided perception. Background technique [0004] With recent technological developments in artificial intelligence (AI), there has been a wave of applying AI in various application fields. This includes the field of autonomous driving, where it is critical to recognize and track objects or obstacles around the vehicle. Traditionally, sensors have been installed around the vehicle to continuously collect surrounding data. Then, the collected data is analyzed in real time to detect obstacles so that the vehicle can be controlled to avoid them. Both 2D and 3D sensors have been used in these applications. For example, camer...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/00G06N20/00G06V10/98
CPCG06N3/006G06N20/00G06V20/56G06V10/95G06V10/98G06V10/82G06V10/811G06V30/1916G06V30/19173G06V30/19147G06F18/256G05D1/0251G05D1/0287G05D1/0088G06F18/214G06F18/24143G06V30/194
Inventor H·郑D·W·刘小T·P·戴利
Owner PLUSAI CORP