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

Multi-agent autonomous tracking method and device based on adaptive collision avoidance mechanism and computer storable medium

A multi-agent and intelligent-agent technology, applied in the computer field, can solve problems such as difficulty in ensuring motion stability, achieve the effect of ensuring continuity and stability, and reducing the probability of empty sets

Active Publication Date: 2019-09-24
SHENZHEN UNIV
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, although this method alleviates the empty set problem, the movement of the agent depends entirely on the condition of the adjacent agents, and its motion stability is difficult to guarantee.

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
  • Multi-agent autonomous tracking method and device based on adaptive collision avoidance mechanism and computer storable medium
  • Multi-agent autonomous tracking method and device based on adaptive collision avoidance mechanism and computer storable medium
  • Multi-agent autonomous tracking method and device based on adaptive collision avoidance mechanism and computer storable medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] see figure 1 , figure 1 It is a schematic flow diagram of a multi-agent autonomous tracking method based on an adaptive collision avoidance mechanism shown in Embodiment 1 of the present invention, wherein the method includes the following steps:

[0059] 101. Obtain the desired speed of the target agent at the current moment;

[0060] In the embodiment of the present invention, multiple target agents in the environment can calculate their own expected speed based on the positional relationship between the surrounding neighbor agents and their corresponding targets, and maintain a smooth movement at a single moment, so as to ensure that the observed target is at The best position within the own observation area (for example, the center of the observation area).

[0061] 102. Calculate the dynamic adaptive collision avoidance weight of the target agent according to the expected speed.

[0062] 103. Calculate a feasible set of collision avoidance speeds between the tar...

Embodiment 2

[0113] see figure 2 , figure 2 It is a schematic structural diagram of a multi-agent autonomous tracking device based on an adaptive collision avoidance mechanism disclosed in Embodiment 2 of the present invention. like figure 2 As shown, the device may include an acquisition module 201, a first calculation module 202, a second calculation module 203, a third calculation module 204, a fourth calculation module 205, a first judgment module 206, a second judgment module 207, and a construction module 208 , control module 209, wherein:

[0114] The acquisition module 201 is used to acquire the expected speed of the target agent at the current moment. It should be noted that the first calculation module 202 can be triggered to start after the acquisition module 201 is executed.

[0115] The first calculation module 202 is used to calculate the dynamic adaptive collision avoidance weight of the target agent according to the expected speed. It should be noted that the second c...

Embodiment 3

[0139] see image 3 , image 3 It is a schematic structural diagram of a multi-agent autonomous tracking device based on an adaptive collision avoidance mechanism disclosed in Embodiment 3 of the present invention. like image 3 As shown, the device may include:

[0140] A memory 301 storing executable program codes;

[0141] a processor 302 coupled to the memory 301;

[0142] The processor 302 invokes the executable program code stored in the memory 301 to perform the following steps:

[0143] Obtain the expected speed of the target agent at the current moment;

[0144] Calculating the dynamic adaptive collision avoidance weight of the target agent according to the expected speed;

[0145] Calculating a feasible set of collision avoidance speeds between the target agent and the reference agent according to the dynamic adaptive collision avoidance weight;

[0146] If the collision avoidance speed feasible set between the target agent and the reference agent is non-empty...

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 relates to a multi-agent autonomous tracking method and device based on an adaptive collision avoidance mechanism and a computer storable medium. The method, by constructing an agent motion control cost function and introducing violence optimization matching and a dynamic weight strategy, describes a novel dynamically adaptive multi-agent collision avoidance responsibility division method, can greatly reduce the probability of an empty multi-agent collision avoidance speed solution set in the target tracking process, and balances the continuous detection performance and the motion stability of the multiple agents simultaneously by a global optimal controller, thereby effectively ensuring the continuity and the stability of the multi-agent autonomous tracking.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, in particular to a multi-agent autonomous tracking method, device and computer storage medium based on an adaptive collision avoidance mechanism. Background technique [0002] At present, intelligent agent-based automatic tracking technology has broad application prospects in airports, shops, theaters, traffic intersections and many other scenarios. Through the cooperative control of multi-agents and effective information interaction feedback, the purpose of autonomous tracking based on video sensors is to implement continuous high-precision positioning of the target of interest, and at the same time to continuously detect important features such as the shape and size of the target as much as possible. However, in the process of moving video sensor target tracking, the movement of the agent is limited by its own detection method, observation area and motion mode, and...

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): G05D1/12G05B13/04
CPCG05D1/12G05B13/042
Inventor 刘瑜李岩山王海鹏
Owner SHENZHEN UNIV