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

Virtual walkway estimation using recursive ad-hoc maps

A self-organizing map and roadway technology, applied in measurement devices, mapping and navigation, instruments, etc., can solve the problem that roadway detectors do not consider and do not have a reasonable driving behavior model.

Pending Publication Date: 2022-04-08
GM GLOBAL TECH OPERATIONS LLC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Even as more accurate lane detectors are being developed in the autonomous vehicle market, lane detectors still do not account for situations where road markings are clear but conditions make normal driving in those lanes difficult
Furthermore, the vehicle may not have a model of reasonable driving behavior when the autonomous vehicle is unable to detect road markings or encounters unexpected situations

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
  • Virtual walkway estimation using recursive ad-hoc maps
  • Virtual walkway estimation using recursive ad-hoc maps
  • Virtual walkway estimation using recursive ad-hoc maps

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] Embodiments of the present disclosure implement a virtual lane estimation system for autonomous vehicles by observing the past trajectories of other vehicles traveling on the same road. A virtual walkway may be defined as an alternative path for a mobile vehicle to travel. Alternative routes can be used in situations where the lane markings on the road are unclear, or for unexpected road conditions (for example, obstacles in the road) that cause vehicles to bypass the default traffic rules of the lane.

[0069] The system generally uses a recursive self-organizing map (SOM), which takes as input one or more observed vehicle trajectories and presents the average trajectory in the form of a directed graph. By using recursive autonomously organized maps, the system can find drivable lanes and capture temporal data such as speed, direction, and lane change preferences.

[0070] The nodes of the directed graph may represent the coordinates of entities along the trajectory. ...

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

A virtual lane estimation system includes a memory device, a sensor, and a computer. The memory device is configured to store a road map corresponding to a portion of a road in front of the vehicle. The sensor is configured to observe a plurality of trajectories of a plurality of adjacent vehicles traversing a portion of a road. The computer is configured to: initialize a recursive ad hoc map to a plurality of points arranged in a two-dimensional grid aligned with a road map; training points in the recursive ad hoc map in response to the trajectory; generating, in response to the points trained for the trajectory, a directed graph including one or more virtual lanes through the road map; and in response to the virtual lane in the directed graph, generating a control signal that controls the vehicle to navigate through the portion of the roadway.

Description

technical field [0001] The present disclosure relates to systems and methods for virtual roadway estimation using recursive self-organizing maps. Background technique [0002] Lane detection of road markings is part of many autonomous vehicles. Lane departure warning systems are available in many commercial vehicles. However, commercial warning systems rely on small visual cues and have many false positive detections. Such systems are intended to assist human drivers, not be fully autonomous. Even as more accurate lane detectors are being developed in the autonomous vehicle market, lane detectors still do not account for situations where road markings are clear but conditions make normal driving in those lanes difficult. Furthermore, when an autonomous vehicle is unable to detect road markings or encounters unexpected situations, the vehicle may not have a model of reasonable driving behavior. [0003] What is desired are systems and / or techniques for virtual lane estima...

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): G01C21/20
CPCG06N5/022G06N3/088B60W60/00276B60W2556/40G01C21/3822G01C21/3841G06N3/042G06N3/044G06N3/045B60W60/0011G01C21/3815B60W60/0027G06N3/04B60W10/04G01C21/3407G06N3/08B60W30/12
Inventor T·J·吴R·巴塔查里亚M·J·戴利K·金
Owner GM GLOBAL TECH OPERATIONS LLC