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

Method for predicting pedestrian trajectory by robot based on social network model

A trajectory prediction and social network technology, applied in biological neural network models, instruments, motor vehicles, etc., can solve problems such as low work efficiency, low precision of robot path planning, poor obstacle avoidance effect, etc., to achieve comity and efficiency problem effect

Active Publication Date: 2019-11-22
SHANGHAI YOGO ROBOTICS CO LTD
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, and provide a method for predicting pedestrian trajectories by robots based on social network models, so as to solve the problem that robots cannot predict pedestrian trajectories in advance and lead to accurate robot path planning. The invention has the advantages of improving the accuracy of the robot's prediction of pedestrian trajectory, reasonably avoiding obstacles, and improving the working efficiency of the robot.

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 for predicting pedestrian trajectory by robot based on social network model
  • Method for predicting pedestrian trajectory by robot based on social network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Embodiment 1 discloses a method for predicting pedestrian trajectories by a robot based on a social network model, comprising the following steps:

[0035] Step 101: Build a pedestrian target detection model. The target detection module detects pedestrian targets through the data collected by the sensors carried by the robot, obtains the position of pedestrian targets, and constructs a pedestrian target detection model. Follow the steps below:

[0036] First, the target detection module obtains the distance between the pedestrian target and the target detection module;

[0037] Then, the target detection module estimates the position of the pedestrian target according to the distance between the pedestrian target and the target detection module, and constructs a pedestrian target detection model;

[0038] Wherein, the target detection module obtains the distance between the pedestrian target and the target detection module specifically includes the following steps:

...

Embodiment 2

[0051] Embodiment 2 discloses a method for predicting pedestrian trajectories by a robot based on a social network model, such as figure 1 shown, including the following steps:

[0052] Step 101: Build a pedestrian target detection model. The target detection module detects pedestrian targets through the data collected by the sensors carried by the robot, and builds a pedestrian target detection model. The sensors are visual sensors and laser sensors;

[0053] Step 102: Build a pedestrian target tracking model. The target tracking module performs real-time tracking and position update of the pedestrian targets detected by the pedestrian target detection model in real time, and outputs the real-time position of the pedestrian targets, constructs the pedestrian target tracking model, and constructs the pedestrian target tracking model. Including the following steps:

[0054] First, the target tracking module synchronizes the timestamps of the sensors;

[0055] Then, the target...

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 method for predicting a pedestrian trajectory by a robot based on a social network model. The method comprises the following steps of: the step 1, constructing a pedestrian target detection model; the step 2, constructing a pedestrian target tracking model; the step 3, generating a real-time motion track of the pedestrian target; the step 4, constructing a social networktrajectory prediction model; and the step 5, planning a reasonable motion path of the robot. In the prior art, a robot cannot predict a pedestrian motion trail in advance so that robot path planning precision is low, by improving the technical problems of the poor avoidance effect, the low working efficiency and the like of the moved obstacle, the method has the advantages that the pedestrian trajectory prediction accuracy of the robot is improved, the obstacle is reasonably avoided, the working efficiency of the robot is improved and the like.

Description

technical field [0001] The invention relates to the technical field of pedestrian trajectory prediction, in particular to a method for predicting pedestrian trajectory by a robot based on a social network model. Background technique [0002] With the development of robot technology and the popularization of robots, modern robots will share the same working or living space with people. Humans are intelligent bodies. In the process of movement, humans will accurately avoid obstacles and choose the optimal walking route. Therefore, modern robots also need to have the ability to plan paths reasonably, so that they can better integrate into human living space and improve The degree of human favorability towards robots. [0003] In the prior art, the avoidance effect of the robot on moving obstacles is poor. Therefore, the robot cannot accurately arrive at the designated place. The robot is produced to replace human beings to perform some difficult tasks. At the same time, the r...

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): G05D1/02G06K9/00G06N3/04
CPCG05D1/0246G06V40/20G06V20/10G06N3/044G06N3/045Y02T10/40
Inventor 袁典
Owner SHANGHAI YOGO ROBOTICS CO LTD
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