WO2019019144A1

WO2019019144A1 - Video social interaction system with desktop robot

Info

Publication number: WO2019019144A1
Application number: PCT/CN2017/094888
Authority: WO
Inventors: 李庆远
Original assignee: 李庆远
Priority date: 2017-07-28
Filing date: 2017-07-28
Publication date: 2019-01-31

Abstract

Disclosed is a video social interaction system with a desktop robot, comprising a data centre, a desktop robot and a remote interaction device, wherein the desktop robot serves as an avatar of a human that is absent to perform video social interaction with a human that is present; the human that is absent controls, by means of the remote interaction device and the data centre, the robot so same moves on a desktop close to the human that is present; the desktop robot comprises a plurality of audio/video input and output devices, a wheeled carrier, one or more sensors, and one or more computers, and has basic intelligence to avoid obstacles; and the remote interaction device comprises a plurality of audio/video input and output devices and a computer. Further disclosed is a method for performing video social interaction by means of a desktop robot.

Description

Desktop robot video social system

Field of invention

The present invention relates to a desktop robot video social system and method, and more particularly to a desktop robot as an incarnate human avatar, and a system and method for video socializing in the presence of humans.

Background technique

Traditional video chats capture live audio and video through a camera/microphone attached to the edge of the screen and communicate through the screen and speakers/earphones. However, as the location of the screen display of the absent human avatar (for the presence of humans), and the location of the camera as the absent human eye (for the absent humans themselves), the absence of human beings is beyond control, video chat Realism is not good. Therefore, even in the era of telephone dialing, everyone is imagining the global video recalls on the private network that only the rich can afford. In today's fiber-optic homes and smart phones, video chat is still limited to meetings and lovers, relatives, etc. Between intimate relationships. Even if someone can't be present and is willing to start a video chat, the people present are not willing to accept video chat (unless the person who is not present is a celebrity).

The popularity of video chat has to jump out of the scope of meetings/private work/intimacy. However, due to the rapid spread of the Internet, video chat does not have the "magic" aura of the telephone dialing era. Therefore, the present invention introduces a social robot to improve the realism of video chat to both ends of the network.

The prior art social robots, based on neural networks and cloud computing, have the following problems:

· Unless specific needs, basic chat, humans are far better than artificial intelligence (AI);

· The prior art AI has no self-awareness, and its vehicle/mechanical limbs have little practical significance;

· Collecting large amounts of personal data, invading privacy and data leakage risks;

· High cost and high price, and wide-ranging popularity is slow;

Summary of invention

The present invention provides a desktop robot that is an incarnation of a human avatar, and a system for video socializing with a human being, the advantages of which are:

· As an incarnation of a human being, the social ability is indistinguishable from the human being represented;

· As a human avatar not present, its vehicle/mechanical limb enhances the social interaction capabilities of absent humans, such as socializing with many different people present;

· Low cost, suitable for rapid and in-depth popularization in a wide range;

Typical application scenarios of the desktop robot included in the present invention include, but are not limited to:

· Participate in human gatherings, representing the absence of human beings to socialize with the people present;

· As an incarnation of a distant lover, interact with the other party at any time when conditions permit;

However, it is to be understood that the invention is not intended to be limited or limited by the scope of the invention, and the invention disclosed herein The skilled artisan includes significant improvements and modifications thereto.

Detailed ways

The invention will now be described more fully hereinafter. However, the invention may be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. The present invention is intended to be thorough and complete, and the scope of the invention will be fully conveyed by those skilled in the art.

It will be appreciated that various changes can be made in the function and arrangement of the elements without departing from the spirit and scope of the invention. Thus, embodiments are examples or implementations of the invention, not the only implementation. The appearances of "one embodiment", "an embodiment" or "an embodiment" are not necessarily referring to the same embodiment. Although various features of the invention may be described in the context of a single embodiment, the features may be provided separately or in any suitable combination. Conversely, although the invention may be described herein in the context of a separate embodiment, the invention may be practiced in a single embodiment or any combination of the embodiments.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the related art and the present disclosure, and will not be construed as idealized or excessive. Formal meaning, unless explicitly defined in this article.

The invention includes a data center, a desktop robot, and a remote interactive device. The desktop robot acts as an incarnation of human avatars and socializes with the presence of humans. Absence Humans control desktop robots through remote interactive devices and data centers, moving on the desktop near the human beings present.

The remote interactive device includes several audio and video input and output devices and a computer.

The desktop robot contains several audio and video input and output devices, wheeled vehicles, one or more sensors, and one or more computers with basic intelligence to avoid obstacles. As a key innovation of the present invention, the current state of the field of consumer robots is discussed in detail below.

First of all, the robot mentioned here includes all machines that simulate human behavior or thought and simulate other creatures, and is not limited to humanoid robots. Robots can be moved by mechanical limbs or by other vehicles, such as two-wheeled balancers, multi-axis drones, submersibles, and even spacecraft to accompany astronauts.

Secondly, the robot can be autonomous (such as Honda's humanoid robot ASIMO, Softbank's emotional simulation robot Pepper) or semi-autonomous robot. The robot included in the present invention belongs to a semi-autonomous robot as an incarnate human avatar, accepting its instructions to move, and having basic intelligence to avoid obstacles.

Obstacle avoidance can be said to be the most basic function of various robots. This is a basic safety movement requirement for autonomous mobile robots, and it is also the key to whether robots can achieve autonomous operations.

The definition of obstacle avoidance refers to the mobile robot in the process of walking, through the sensor to sense that there are static or dynamic obstacles on its planned route, update the path in real time according to a certain algorithm, bypass the obstacle, and finally reach the target point.

Whether it is to navigate planning or avoid obstacles, sensing the surrounding environment information is the first step. In terms of obstacle avoidance, mobile robots need to obtain real-time obstacle information, including size, shape and position, through sensors. There are many kinds of sensors for obstacle avoidance, each with different principles and characteristics, which can be divided into visual and non-visual. The visual system can be used to avoid obstacles to obtain more complete environmental information, but the image processing operation is large, and the technology and cost of equipment and data processing are high. Relatively speaking, ultrasonic sensors, laser sensors, infrared sensors and other non-visual sensors have low cost and relatively simple data processing technology.

Ultrasonic sensors are sensors that convert ultrasonic signals into other energy signals (usually electrical signals). The principle of ranging is to measure the time difference between the ultrasonic wave and the detected ultrasonic wave, and calculate the distance of the obstacle according to the sound speed. It has the advantages of high frequency, short wavelength, small diffraction phenomenon, especially good directivity, and can be directional and propagated. Ultrasonic sensors are low cost, simple to implement, and mature in technology. They are commonly used sensors in mobile robots. However, the ultrasonic sensor has a short working distance, and the common effective detection distance is between several meters, and there is a minimum detection dead zone, generally a few centimeters.

·Infrared sensor refers to the measurement system using infrared as the medium. The general ranging is based on the principle of triangulation. The emitter emits an infrared beam at a certain angle. When the obstacle is encountered, the beam will be reflected back. After the reflected infrared light is detected by the CCD detector, an offset value is obtained and the sensor is used to calculate the sensor to the object. the distance. The infrared sensor is not affected by visible light, and can be measured during day and night. The angle sensitivity is high, the structure is simple, the price is cheap, and the presence of the object can be quickly perceived. However, the infrared sensor is greatly affected by the environment, and the color, direction, and surrounding infrared radiation of the object can cause measurement errors, and the measurement is not accurate enough. For transparent or near-black objects, the infrared sensor cannot detect the distance. The infrared sensor measures less than the ultrasonic sensor.

• A laser sensor is a parameter that uses a laser to measure the distance to an object to be measured, or the displacement of an object to be measured. The principle of the commonly used ranging method is as follows: the pulsed laser emits a pulsed laser with a very short duration, and passes through the distance to be measured and then hits the target to be measured, and the echo returns, and is received by the photodetector. Then, based on the interval between the main wave signal and the echo signal, that is, the round trip time between the laser pulse and the target to be measured, the distance of the target to be measured can be calculated. The laser sensor can realize non-contact long-distance measurement, fast speed, high precision, large range, strong resistance to light and electric interference. However, because the speed of light is much higher than the speed of sound, high-precision time measuring components are required, so it is expensive. And for transparent materials, such as glass, nothing can be done.

• Vision sensor refers to an instrument that acquires image information of an external environment using an optical component and an imaging device, and generally describes the performance of the visual sensor with image resolution. After the image is captured by the vision sensor, it is compared to the reference image stored in memory for analysis. The vision sensor has the advantages of wide detection range, rich information acquisition, and no influence on distance and position. However, in image processing, image processing methods such as edge sharpening and feature extraction have large computational complexity, poor real-time performance, and high requirements on the processor. Moreover, the presence of transparent obstacles such as glass cannot be detected, and the intensity of the field of view is strong and the influence of smoke is large.

Since the measurement of environmental information by a single sensor is not ideal, in practical applications, other types of sensors are often needed for compensation to detect the surrounding environment.

In general, human gatherings revolve around one or more tables. The obstacles faced by desktop robots include various cups, cutlery, human items such as cell phones, and table edges, to name a few. The remote operation of social robots is not a human being. After all, it is not a drone pilot. In addition to the communication delay and other factors, it is not realistic from a technical point of view to completely obstruct the robot through the absence of humans.

The desktop robot included in the present invention avoids obstacles autonomously by various sensors included therein. This is mainly due to the fact that under the prior art, as an incarnation of the human being, the remote interactive device can operate with limited instructions, and as a consumer electronic product, the operation cannot be too complicated. Even if the future technology can realize complex remote control, as a social robot, it should not consume too much attention of the user to avoid obstacles. After all, obstacle avoidance is a low-level instinct for human activities.

In addition, the remote operation of the social robot's absent humans does not necessarily have the social robots it operates, and it also needs to eliminate malicious operations, hacker hijacking, communication failures and other unexpected situations. For intercontinental communications, latency is also an important factor.

The video output included in the present invention includes, but is not limited to:

·Projector;

· flat panel display;

· Head-up display (HUD, Head Up Display);

· Head-mounted display (HMD);

The above description is only an embodiment of the invention and is not intended to limit the scope of the invention. Various changes and modifications of the claims and the description of the present invention are still within the scope of the claimed invention. Moreover, each of the embodiments and claims does not necessarily include all of the advantages or features disclosed. In addition, the Abstract and the headings are only used to facilitate the search for patent documents and are not intended to limit the scope of the claimed invention in any way.

Claims

A desktop robot video social system includes a data center, a desktop robot, and a remote interactive device, wherein the desktop robot acts as an in-person human avatar, and a live human social video, the absent human, through the remote The interactive device and the data center control the desktop robot to move on a desktop near the present human being.
The desktop robot video social system of claim 1 wherein said desktop robot comprises:

Video output, outputting the video of the absent human

Audio output, outputting the audio of the absent human

Wheel carrier to move the robot to different positions on the desktop

One or more video inputs, entering the video of the presence of the human being

One or more audio inputs to input the audio of the presence human

One or more sensors for sensing the surroundings of the desktop robot

One or more computers connected to the data center, receiving control commands from the absent human being, controlling input and output transmission of the video and audio, and having basic intelligence to collect data through the sensor to control the The desktop robot avoids obstacles while moving
The desktop robot video social system of claim 1 wherein said remote interaction device comprises:

One or more video outputs that output the video of the presence human

One or more audio outputs that output the audio of the presence human

Video input, enter the video of the absent human

Audio input, input the audio of the absent human

a computer, connected to the data center, controlling input and output transmission of the video and audio, receiving and transmitting the control instructions of the absent human
A desktop robot video social system includes a data center, a desktop robot, and a remote interactive device, wherein the desktop robot acts as an in-person human avatar, and a live human social video, the absent human, through the remote The interactive device and the data center control the robot to move on a desktop near the present human being.
The robot video social system of claim 4, the robot comprising:

Video output, outputting the video of the absent human

Audio output, outputting the audio of the absent human

Wheel carrier to move the robot to different positions on the desktop

One or more video inputs, entering the video of the presence of the human being

One or more audio inputs to input the audio of the presence human

One or more sensors for sensing the surroundings of the robot

One or more computers connected to the data center, receiving control commands from the absent human being, controlling input and output transmission of the video and audio, and having basic intelligence to collect data through the sensor to control the The desktop robot avoids obstacles while moving
The desktop robot video social system of claim 4, the remote interaction device comprising:

One or more video outputs that output the video of the presence human

One or more audio outputs that output the audio of the presence human

Video input, enter the video of the absent human

Audio input, input the audio of the absent human

a computer, connected to the data center, controlling input and output transmission of the video and audio, receiving and transmitting the control instructions of the absent human
The desktop robot of claim 5 further comprising: a battery for providing power to said carrier, audio and video equipment, computer, sensor.
The desktop robot according to claim 5, further comprising: a wireless power supply device that supplies power to said vehicle, audio and video equipment, computer, and sensor.
A method of video socializing through a desktop robot, comprising:

· The desktop robot acts as an avatar of an absent human being, and video socializes with the present human being

The absent human being, remotely controlling the robot to move to the desktop near the presence of the human being

· The desktop robot accepts the absence of the human command, and through its own sensor and computer, has the basic intelligence to avoid obstacles in the movement