SUMMERY OF THE UTILITY MODEL
The utility model provides a robot control system to solve the problem that the mutual function of the most robots of prior art existence is more single.
In order to solve the technical problem, the utility model provides a robot control system, including fuselage main part, head subassembly, position detector, controller, head subassembly and fuselage main part rotatable coupling, install eye subassembly on the head subassembly, position detector installs in the fuselage main part, position detector is used for detecting the positional information of interacted object, positional information includes the position angle that interacted object belongs to and the distance that interacted object apart from the robot, the controller is used for according to positional information control the head subassembly rotates, makes the head subassembly face the position that interacted object belongs to; the eye component is the mechanical component and comprises an eyeball rotator and an eyelid opening and closing structure, and the controller is further used for determining adjustment parameters of the eye component according to the position information and controlling the eye component to make corresponding adjustment according to the adjustment parameters; the robot further comprises a walking chassis, the robot body is connected with the walking chassis, and the controller is further used for controlling the walking chassis to rotate and/or move so that the robot body faces the position of the interactive object.
Further, the adjustment parameters of the ocular component include: the rotation direction and/or rotation angle of the eyeball rotator and/or the rotation angle of the eyelid opening and closing structure.
Further, the position detector includes one or more of a microphone array, a distance sensor, an infrared sensor, a laser sensor, and an ultrasonic sensor.
Further, the system comprises an image recognizer, wherein the image recognizer is used for acquiring an image of the interacted object, and identifying characteristic attributes of the interacted object from the image; wherein the characteristic attribute comprises at least one of the following attributes: the controller is specifically used for determining the adjustment parameters of the eye component and adjusting the rotation angle of the head component according to the position information and/or the characteristic attribute.
Further, the microphone array is further configured to collect a sound signal of the interacted object, the robot further includes a speech recognizer configured to analyze the sound signal to obtain the characteristic attribute of the interacted object, and the controller is specifically configured to determine an adjustment parameter of the eye assembly and adjust a rotation angle of the head assembly according to the position information and/or the characteristic attribute.
Further, the wireless communication device is connected with the controller, and the controller communicates with external equipment through the wireless communication device.
The utility model discloses the beneficial effect who brings: the robot provided by the application detects the position information of the interacted object through the position detector, and the controller determines the adjusting parameters of the robot eye assembly and the rotating direction and rotating angle of the robot head assembly based on the position information, so that the eye assembly and the head assembly of the robot are adjusted, the head assembly and the face eye assembly of the robot can be changed up, down, left and right according to the position change of the interacted object, and the human-computer interaction performance of the robot is expanded.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, the robot control system of the present invention includes a body 1, a head assembly 2, a position detector 3, and a controller 4, wherein the head assembly 2 is rotatably connected to the body 1, an eye assembly 5 is installed on the head assembly, the position detector 3 is installed on the body 1, the position detector 3 is used for detecting position information of an object to be interacted, the position information includes an azimuth angle of the object to be interacted and a distance of the object to be interacted from the robot, and the controller 4 is used for controlling the head assembly to rotate according to the position information, so that the head assembly faces to the azimuth of the object to be interacted; the eye component 5 is the mechanical component, the eye component comprises an eyeball rotator and an eyelid opening and closing structure, and the controller 4 is further used for determining an adjustment parameter of the eye component according to the position information and controlling the eye component to make a corresponding adjustment according to the adjustment parameter; the robot further comprises a walking chassis 6, the robot body 1 is connected with the walking chassis, and the controller is further used for controlling the walking chassis to rotate and/or move so that the robot body faces the direction of the interactive object. The adjustment parameters of the ocular component include: the rotation direction and/or rotation angle of the eyeball rotator and/or the rotation angle of the eyelid opening and closing structure.
Alternatively, the controller 4 may be implemented using various Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), microcontrollers, microprocessors, or other electronic components.
In the present embodiment, the position detector 3 includes one or more of a microphone array, a distance sensor, an infrared sensor, a laser sensor, and an ultrasonic sensor.
Optionally, a microphone array (MIC array) is disposed on the main body, the MIC array is an array formed by arranging a set of omnidirectional microphones at different spatial positions according to a certain shape rule, and is a device for spatially sampling a spatially propagated sound signal, and the acquired signal includes spatial position information thereof. In the embodiment of the present application, the position information of the interactive object is acquired according to MIC array sound source localization, so that the controller 4 sets the rotation parameters of the head assembly after receiving the position information. For example, when the MIC array detects that the interactive object is located in a small angle range on the left side of the robot body, the current rotation angle of the head assembly of the robot can be set to be left rotation, and the rotation included angle is 5-10 degrees; when the MIC array detects that the interactive object is located in the left large-angle range of the robot body, the current rotation angle of the main body of the robot body can be set to be leftward rotation, and the rotation included angle is 15-30 degrees.
The distance sensor, the infrared sensor, the laser sensor and the ultrasonic sensor are position detectors which realize positioning through distance measurement and relative azimuth angles. In general, the detection of the distance and the azimuth angle may be realized by a combination of a plurality of sensors. The working process is as follows: the position detectors simultaneously send out position detection signals, the position detection signals are reflected after reaching the detected object, the position detectors record the round trip time of the position detection signals after receiving the position detection signals, the position information of the detected object is obtained through calculation according to the propagation speed of the position detection signals, and meanwhile, the direction of the detected object is obtained through comprehensive analysis according to the distance detection results of the distance sensors.
The device further comprises an image recognizer 7, wherein the image recognizer is used for acquiring an image of the interacted object, and identifying the characteristic attribute of the interacted object from the image; wherein the characteristic attribute comprises at least one of the following attributes: the emotion, age and gender of the interacted object, and the controller is specifically configured to determine the adjustment parameters of the eye assembly and adjust the rotation angle of the head assembly 2 according to the position information and/or the characteristic attributes.
The image recognizer may be a device integrated with processing capabilities for photographing, image recognition, computing, and the like. By acquiring an image or video stream containing a human face by using a camera or a camera and detecting and tracking the human face in the image, an interacted object can be found in the visual range of the camera or the camera, and the position information of the interacted object can be obtained. Based on the influence of the shooting angle of the image recognizer relative to the interacted object on the image imaging effect, the position information of the interacted object relative to the robot can be determined by calculating the shot image, the calculating process can be realized by referring to the related prior art, and details are omitted in this embodiment.
The microphone array is further configured to collect a sound signal of the interacted object, the robot further includes a speech recognizer 8 configured to analyze the sound signal to obtain the characteristic attribute of the interacted object, and the controller is specifically configured to determine an adjustment parameter of the eye assembly and adjust a rotation angle of the head assembly 2 according to the position information and/or the characteristic attribute.
Specifically, when the characteristic attributes of the interacted objects are acquired by the microphone array, the microphone array samples sound signals of the interacted objects, and the controller performs acoustic identification and classification on the sampled sound signals, so that information such as gender, age, emotion and the like of the interacted objects is acquired according to the sound characteristics of the interacted objects. The image recognizer can perform expression recognition on the face of a person and acquire the gender, age and emotional state of the interacted object from the expression recognition result. It should be understood that the above two methods for feature attribute identification of the interacted object can be used singly or in combination.
The embodiment of the application also comprises a wireless communicator connected with the controller, and the controller is communicated with external equipment through the wireless communicator. The external device can send an instruction to the controller through wireless so as to enable the controller to execute corresponding control actions.
The above description is only an example of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.