Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intention-based computer depth learning automatic navigation and driving system and method thereof

A deep learning and automatic navigation technology, applied in the direction of motor vehicles, navigation computing tools, control/regulation systems, etc., can solve problems such as indistinguishable decision-making, and achieve low-cost effects

Inactive Publication Date: 2018-08-31
重庆嵩岳贸易服务有限公司
View PDF12 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, Nvidia's system can only run a fixed route and cannot make different decisions based on actual road conditions

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
  • Intention-based computer depth learning automatic navigation and driving system and method thereof
  • Intention-based computer depth learning automatic navigation and driving system and method thereof
  • Intention-based computer depth learning automatic navigation and driving system and method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] The top layer of the system plans the path from the start point to the end point (such as figure 1 , figure 2 ). The core innovation of this part is that the path planning of our system does not require a high-precision map, or even an incomplete map. For example, store floor plans, Google Maps, etc. Dynamic obstacles can be missing on the map, such as pedestrians and moving vehicles; static obstacles can be missing, such as shopping mall renovations, road maintenance and other situations where the map is not updated in time. The path planning of our system needs to ensure the most basic geometric structure, for example, where there are multiple intersections. Given such a map, we do the simplest path planning. For example, indoor robots: A star path planning, automatic driving, Google navigation. Since the top-level decision-making information of our system is very rough, we move the problem of maintaining the dynamic environment to the bottom-level decision-maki...

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 an intention-based computer depth learning automatic navigation and driving system and a method thereof; the method is featured by comprising the following steps: S1, top routeplanning; S2, intention extraction; S3, base layer decisions based on intention. The top route planning uses heuristic A-star route planning to make point-to-point route calculations; the advantagesare that the method does not need a high precision radar map in conventional meanings, and a common map navigation result can be applied to automatic driving. The route planning is only for intentionextraction, and the intention extraction comes from route planning for automatic driving; the base layer decision based on intention uses depth simulation learning to learn various driving skills, thus saving high precision map and equipment maintenance troubles and costs, and enabling a vehicle to drive to any road with no pre-built map. Because of the abstractness, the system can be directly applied to the indoor robot navigation, and only a people needed market plane needs to be provided.

Description

technical field [0001] The invention relates to the technical field of automobile automatic driving, in particular to an intention-based computer deep learning automatic navigation and driving system and a method thereof. Background technique [0002] In the prior art, point-to-point navigation is the most basic requirement for unmanned driving and indoor robot navigation. However, the existing automatic navigation technology cannot yet reach the level of human navigation. For example, when people come to a new mall, they can easily get to the store they want to go to, just need the navigation floor plan of the mall. People can easily avoid crowds, avoid obstacles, open and close glass doors, and even take elevators to reach their destinations. Similarly, when people drive to a new city, they can easily drive to the destination with only GPS navigation. People can easily avoid vehicles and obstacles on the road, wait for traffic lights, and drive to their destination in c...

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
IPC IPC(8): G05D1/02G01C21/20
CPCG05D1/0214G05D1/0221G05D1/0223G05D1/0246G05D1/0276G05D1/0278G01C21/20
Inventor 不公告发明人
Owner 重庆嵩岳贸易服务有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com