A voice and image compound interactive execution method and system for robots

An execution method and robot technology, applied in the field of robotics, can solve the problems of large amount of computation and high computational complexity, and achieve the effects of improving accuracy and robustness, effective interaction, and improving accurate recognition

CN105957521BActive Publication Date: 2020-07-10青岛路腾智能装备科技有限公司
4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2020-07-10

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The present invention relates to a voice and image composite interaction execution method and system for a robot. The method comprises: the step 1: a robot detects the surrounding sound, and the sound source is located; the step 2, the robot detects the human faces around, the human faces are located, the location of the human faces and the location of the sound source are compared and matched, the interference sound source is filtered, the voice sound source is initially determined, and a voice command is initially determined; the step 3, the robot detects the human objects around, the human objects are tracked, the limb command is identified and is compared and matched with the initially determined voice command, the interference sound command is filtered, and the effective user command is determined; and the step 4, the robot executes the corresponding operation according to the user command. The robot is able to accurately understand the user's command in a complex background and accurately identify the user command sent to the robot, and is higher in robustness, more intelligent, and more efficient for interaction with people.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of robots, in particular to a method and system for executing compound interactive voice and images for robots. Background technique

[0002] In order to realize the interaction between the robot and the human user, some technologies in the prior art recognize user commands by voice. Due to the complex real environment, there are voice interference from other users and non-voice interference in the environment (such as TV, sound box, etc.). Sound source, etc.), multiple users send out voice signals, but some are sending voice commands to the robot, and some are doing conversations and other behaviors that have nothing to do with the robot. Therefore, the sound positioning results may include both the user who issued the voice command and the interfering sound source. Accurately locating the user's sound source from a complex environment containing interfering sound sources is a difficult point in voice command recogn...

Examples

Embodiment Construction

[0024] The specific implementations of the constant pressure tensioning device and the crawler robot according to the present invention will be described with reference to the accompanying drawings. The following detailed description and accompanying drawings serve to illustrate the principles of the present invention. The present invention is not limited to the described preferred embodiments, but the scope of the present invention is defined by the claims.

[0025] Such as Figure 1-3 As shown, a voice and image composite interactive execution method for a robot described in the present invention comprises the following steps:

[0026] Step 1: The robot detects the surrounding sounds and locates the sound source; that is, detects all the sounds around the robot;

[0027] Step 2: The robot detects the surrounding faces, locates the faces, compares and matches the location of the faces with the location of the sound source, filters out the interference sound source, prelimina...