Cloud-assisted automatic driving method and system

An autonomous driving, cloud-based technology, applied in control/regulation systems, motor vehicles, non-electric variable control, etc., can solve problems such as inability to meet safety requirements and increase, and achieve the effect of increasing the amount of available information and improving safety

Active Publication Date: 2017-04-05
FUZHOU HUAYING HEAVY IND MACHINERY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For some complex road sections, such as construction, rain, etc., the situation that needs to be analyzed further increases, and it is not enough to rely on on-board sensors for collection, judgment, and driving, and cannot meet the safety requirements

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
  • Cloud-assisted automatic driving method and system
  • Cloud-assisted automatic driving method and system
  • Cloud-assisted automatic driving method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] Embodiment 1 Utilizes octree to realize environment region naming

[0064] Utilizes octrees to identify and name regions in the environment: the world is recursively partitioned into cubes, starting with a dataset of the entire environment with known boundaries for the vehicle. Each cube is then recursively divided into eight smaller cubes. An octree of recursive structure is maintained, each node in the octree represents a multidimensional data set, and the subtrees under the node represent the recursive division of the data set, so that the regions in different positions in the environment can be named. Each node (that is, each region) in the octree is given a globally unique identifier id to distinguish different regions.

[0065] The octree data structure can also be used to represent sensor information (ie 3D point clouds). Each node (i.e., each region) in the octree has one of the following properties: (1) occupied, if any point in the point cloud is in the corr...

Embodiment 2

[0066] Example 2 How the cloud obtains regional information with different resolutions

[0067] The octree data structure provides a mechanism to query information of different resolutions in each region. Information at a deeper level in the octree provides higher resolution information for an area, and information at an upper level provides information at a lower resolution for the same area. Therefore, a request for a region will be represented as a binary array (id, res), where id represents the location of the region, and res represents the resolution (depth) of the requested region. The sensor information of the self-driving car is represented by the octree data structure and the data request is replied. The data reply includes the encoding of the subtree node with the depth res under the octree node id. By adding resolution information to the data request, the important areas are finely described, and the unimportant areas save data space, thereby improving the efficien...

Embodiment 3

[0068] Example 3 Information packet loss can be recovered

[0069] Sensor information transmitted to the cloud is subject to packet loss, and the loss of a packet encoded by the octree often destroys all information stored on the octree. The standard octree encoding technology is carried out in the following steps: each node of the octree is represented as an 8-tuple, which respectively indicates the occupancy of its child nodes; the encoding is through top-down and breadth-first traversal and read out the corresponding tuple. The root node is always assumed to be occupied, and for each node, its occupied and unknown children are recursively encoded. In unoccupied nodes, no information is encoded because the corresponding area is assumed to be completely unoccupied. Furthermore, those child nodes are all occupied or unknown nodes and thus are encoded by a special 8-tuple (all entries are marked as occupied or unknown respectively) and are not further encoded. On the receivi...

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 invention discloses a cloud-assisted automatic driving method and a system thereof. The cloud-assisted automatic driving method is characterized in that a cloud end can be used to transmit data requests to a vehicle end and a roadside static sensor; the vehicle end and the roadside static sensor can be used to transmit the sensor information according to the data requests; the cloud end can be used to receive the sensor information transmitted by the sensor module and the roadside static sensor, and can be used to acquire the planning analyzing result by planning and analyzing the sensor information, and can be used to transmit the planning and analyzing result to the vehicle end; the vehicle end can be used to receive the planning and analyzing result, and can be used for the route planning according to the planning and analyzing result and the sensor information to acquire the route planning result, and then can be used to control the driving of the vehicle according to the route planning result. By adopting the information sharing between the roadside static sensor and the on-board sensor module, a plurality of auxiliary functions such as comprehensive analysis of the passable route by the cloud end can be realized, and the information can be provided for the current vehicle for the reference. The available information amount can be increased, and then the automatic driving safety can be further improved.

Description

technical field [0001] The present invention relates to the field of automatic driving, in particular to a cloud-assisted automatic driving method and system. Background technique [0002] Unmanned driving technology is becoming more and more mature. In many cases, unmanned vehicles or smart vehicles can meet the needs of autonomous navigation. However, unmanned vehicles are machines after all, and need to rely on sensor information for judgment and analysis. For some complex road sections, such as construction, rain, etc., the situation that needs to be analyzed further increases, and it is not enough to rely on on-board sensors for collection, judgment, and driving, and cannot meet the safety requirements. Contents of the invention [0003] To this end, it is necessary to provide a driving method that can provide more sensor information references. Specifically, sensor information sharing and path sharing are provided through multi-sensor and cloud analysis to improve th...

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 Patents(China)
IPC IPC(8): G05D1/02
CPCG05D1/021G05D2201/0212
Inventor 潘晨劲赵江宜
Owner FUZHOU HUAYING HEAVY IND MACHINERY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap