Vehicle position tracking method based on Markov decision-making process model

A process model, vehicle technology, applied in the field of target tracking

Active Publication Date: 2019-09-20
NANJING UNIV OF SCI & TECH
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing vehicle position positioning methods, including vehicle trajectory models, discrete linear error models, models based on optimal control algorithms, etc., are all based on the analysis of the target vehicle without starting from the sensor itself, which has strong uncertainty and randomness. sex

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
  • Vehicle position tracking method based on Markov decision-making process model
  • Vehicle position tracking method based on Markov decision-making process model
  • Vehicle position tracking method based on Markov decision-making process model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0038] The present invention utilizes pycharm software to implement said method. Let the mapping of the actual position of the target vehicle in the two-dimensional road network model be (2.1,3.2). There are four sensor clusters in total, and the initial state of the sensor cluster is {0000}. The state transition probability of sensor clusters is assumed to be approximately 1.

[0039] figure 2 Tracking situation graph for sensor clusters. The black circle is the target vehicle; the square is the sensor cluster, when it is black, it means it is in a dormant state, and when it is white, it means it is in a working state. It can be observed that with the movement of the target vehicle, the sensor continuously uses the optimal action sequence to perform state transitions to reach the optimal state to achieve preliminary tracking.

[0040] image 3 It is a comparison chart between the Gaussian weight positioning algorithm based on RSSI and the traditional three-point positio...

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 vehicle position tracking method based on a Markov decision-making process model. The vehicle position tracking method comprises the following steps: establishing a two-dimensional road network model; defining the state, action and reward of the sensor cluster, establishing a Markov decision-making process model, and obtaining an optimal action sequence of the sensor cluster by using reinforcement learning to realize preliminary tracking; and carrying out accurate tracking of the target vehicle by using a Gaussian weight positioning algorithm based on RSSI. Accurate positioning of the vehicle is achieved, and help is provided for effective implementation of vehicle position tracking.

Description

technical field [0001] The invention relates to the technical field of target tracking, in particular to a vehicle position tracking method based on a Markov decision process model. Background technique [0002] The Internet of Vehicles uses GPS, vehicle-mounted terminals and other equipment to realize the effective use of vehicle-related information on the user information platform through wireless communication technology. The Internet of Vehicles uses the vehicle location information and historical driving data information provided by related equipment, stores these information in the cloud, and performs data fusion, data mining and other analysis work to provide users with better location positioning, road matching and other services, so that users can be more Get a good understanding of road traffic conditions, plan road choices reasonably, and ease traffic pressure. Real-time location information can also be used to provide early warning of road traffic conditions. T...

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 & AuthorityApplications(China)
IPC IPC(8): H04W4/02H04W4/40H04W64/00H04L12/24
CPCH04L41/145H04W4/02H04W64/00H04W4/40
Inventor张杰李骏邢志超邵雨蒙梁腾
OwnerNANJING UNIV OF SCI & TECH