WO2017177441A1

WO2017177441A1 - Cloud computing robot control device, cognition platform, and control method

Info

Publication number: WO2017177441A1
Application number: PCT/CN2016/079427
Authority: WO
Inventors: 王森
Original assignee: 深圳前海达闼云端智能科技有限公司
Priority date: 2016-04-15
Filing date: 2016-04-15
Publication date: 2017-10-19
Also published as: CN107107340A

Abstract

A cloud computing robot control device, cognition platform, and control method. The cloud computing robot control device determines, after receiving user instructions, the types of the instructions, locally processes locally processable instructions, and sends non-locally processable instructions to a cloud computing robot cognition platform for processing, such that a robot can complete more complex tasks without being limited by local resources. The cloud computing robot cognition platform is provided with a public cognition unit and a private cognition unit which has one-to-one correspondence to the robot body, and a public data acquisition instruction may be directly obtained from the public cognition unit, such that the utilization rate of computing resources can be further improved, and construction costs are reduced.

Description

Cloud computing robot control device, cognitive platform and control method

Technical field

The invention relates to the field of artificial intelligence, in particular to a cloud computing robot control device, a cognitive platform and a control method.

Background technique

In the prior art, the realization of the robot basically adopts a solution integrating the sensing system, the cognitive system and the control system, wherein the cognitive system is the core system of the robot, which is equivalent to the human brain. In the specific implementation, the robot's sensing system, cognitive system and control system are placed locally on the robot to realize human-like work.

In the above method, the cognitive system (that is, the brain of the robot) is placed on the robot local. Due to the development of current computer and artificial intelligence technologies, and the local imitating human brain requires a huge amount of computing resources, it is subject to local intelligence. The limitations of the humanoid machine's size, power consumption, mobility, etc., make existing robots can only achieve some simple tasks and cannot complete complex tasks.

The shortcoming of the prior art is that the existing robot solution is limited by local resources and cannot complete the processing of complex tasks.

Summary of the invention

The embodiment of the invention provides a cloud computing robot control device, a cognitive platform and a control method, which are used to solve the problem that the prior art robot solution is limited to local resources and cannot complete the processing of complex tasks.

An embodiment of the present invention provides a cloud computing robot control apparatus, including:

The instruction processing unit is configured to distinguish whether the instruction sensed by the robot body belongs to a local processable instruction, and send the local processable instruction to the body control unit for processing, which is non-locally available The instruction is sent to the cloud computing robot cognitive platform for processing;

And a body control unit, configured to control the robot body to perform a corresponding operation according to the received control instruction fed back by the cloud computing robot cognitive platform.

Correspondingly, an embodiment of the present invention further provides a cloud computing robot cognitive platform, including:

a common cognitive unit corresponding to the plurality of robot bodies for storing common data of the corresponding plurality of robot bodies;

a private cognitive unit, in one-to-one correspondence with the robot body, configured to receive an instruction issued by the robot body, and if the instruction is a public data acquisition instruction, obtain corresponding public data from the common cognitive unit and send the The robot body, otherwise processing the instruction, sends a corresponding control command to the robot body.

Embodiments of the present invention provide a cloud computing robot control method, including the following steps:

Receiving an instruction sensed by the robot body;

Distinguishing whether the instruction sensed by the robot body belongs to a local processable instruction, directly processing the local processable instruction, and transmitting the non-local processable instruction to the cloud computing robot cognitive platform for processing;

Receiving a control instruction fed back by the cloud computing robot cognitive platform, and controlling the robot body to perform a corresponding operation.

Correspondingly, an embodiment of the present invention further provides a cloud computing robot control method, including the following steps:

Receiving an instruction issued by the robot body;

Determining whether the instruction is a public data acquisition instruction, and if yes, acquiring corresponding public data and transmitting the same to the robot body; otherwise, processing the instruction, and then sending a corresponding control instruction to the robot body.

According to the solution provided by the embodiment of the present invention, after receiving the user instruction, determining the type of the instruction, processing the locally processable instruction locally, and sending the non-locally processable instruction to the cloud computing robot cognitive platform for processing, This way you are not limited by local resources, This allows the robot to perform more complex tasks.

Correspondingly, the cloud computing robot cognitive platform is provided with a public cognitive unit and a private cognitive unit corresponding to the robot body, and the public data acquisition instruction can be obtained from the public cognitive unit, thereby further improving the utilization of the cloud resource. Rate, while saving construction costs.

DRAWINGS

Specific embodiments of the present invention will be described below with reference to the accompanying drawings, in which:

1 is a schematic structural diagram of a cloud computing robot control apparatus according to an embodiment of the present invention;

2 is a schematic structural diagram of a cloud computing robot cognitive platform according to an embodiment of the present invention;

3 is a flowchart of a cloud computing robot control method according to an embodiment of the present invention;

4 is a flowchart of a cloud computing robot control method according to an embodiment of the present invention;

detailed description

The embodiments of the present invention are further described in detail with reference to the accompanying drawings, in which FIG. An exhaustive example. And in the case of no conflict, the features in the embodiments and the embodiments in the description can be combined with each other.

The inventor noticed during the invention:

In the prior art, the realization of the robot basically adopts a solution integrating the sensing system, the cognitive system and the control system, wherein the cognitive system is the core system of the robot, which is equivalent to the human brain. In the specific implementation, the robot's sensing system, cognitive system and control system are placed locally on the robot to realize human-like work. Due to the limitations of current computer and artificial intelligence technologies, and the need to imitate human brains in a large amount of computing resources, the size, power consumption, and mobility of local intelligent humanoid machines are limited, resulting in existing robots only Can achieve some simple tasks, unable to complete complex tasks.

Although there are some robotic solutions that put cognitive systems on the cloud platform, they have invented People believe that if all mission instructions are handed over to the cloud platform, it will not only waste cloud platform resources, but also waste system communication resources.

In view of the above deficiencies, the embodiment of the present invention provides a cloud computing robot control device, a cognitive platform, and a control method, which are described below.

Embodiment 1

FIG. 1 is a schematic structural diagram of a cloud computing robot control apparatus according to Embodiment 1 of the present invention. As shown in the figure, a cloud computing robot control apparatus according to Embodiment 1 of the present invention includes:

The instruction processing unit 101 is configured to distinguish whether the instruction sensed by the robot body belongs to a local processable instruction, send the local processable instruction to the body control unit for processing, and send the non-local processable instruction to the cloud computing robot cognitive platform for processing. ;

The ontology control unit 102 is configured to control the robot body to perform a corresponding operation according to the received control instruction of the cloud computing robot cognitive platform feedback.

In a specific implementation, the instructions sensed by the robot body include user instructions of voice, remote control, button, gesture, touch, and the like.

In a specific implementation, the body control unit controls the type of operation performed by the robot body according to the received control instruction fed back by the cloud computing robot cognitive platform, which mainly includes mechanical, servo, and/or transmission operations.

In this embodiment, the instruction processing unit distinguishes the instruction sensed by the robot body into whether it belongs to a locally processable instruction, wherein the locally processable instruction mainly includes some instructions that can be processed without requiring robot conditional reflection and some local instructions. Concentrated reflexive instructions, mainly including remote control commands, touch commands, and/or button commands. For example, when a user presses a button, the button itself has a certain meaning, and the robot can perform corresponding command processing and perform corresponding operations without performing any conditional reflection. Non-locally processable instructions mainly refer to conditional reflection instructions that do not exist in the local instruction set, and mainly include voice commands, gesture commands, eye commands, and/or expression commands. For example, the user sent a voice and the robot received the phrase. After the tone command, it is found that the instruction does not exist in the local instruction set, and the instruction needs to be sent to the cloud computing robot cognitive platform for speech recognition, analysis and the like.

In this embodiment, not all the instructions sensed by the robot are processed locally by the robot, nor are all the instructions sensed by the robot sent to the cloud computing robot cognitive platform for processing, but the instructions sensed by the robot first. Classification, some local processing directly, and another part is sent to the cloud computing robot cognitive platform for processing, so that the robot's instruction processing is no longer limited by local resources, thereby expanding the range of tasks that the robot can achieve, and ensuring more complex tasks. It can be completed, and at the same time, since the embodiment only sends the conditional reflection instruction that does not exist in the local instruction set to the cloud computing robot cognitive platform for processing, the conditional reflection instruction existing in the local instruction set is still directly processed locally, thereby greatly reducing the Communication resources and the waste of cloud computing robot cognitive platform resources.

In an implementation, the cloud computing robot control device may further include:

The first identity authentication unit 103 is configured to perform two-way identity authentication with the cloud computing robot cognitive platform when the robot body is connected to the cloud computing robot cognitive platform.

The two-way authentication here means that when the robot body is connected to the cloud computing robot cognitive platform, the cloud computing robot cognitive platform needs to authenticate the robot body, and the robot body authorized for authentication is allowed to access the cloud computing robot. Knowing the platform, the robot body that fails the authentication will refuse to access the cloud computing robot cognitive platform. At the same time, the first identity authentication unit will also authenticate the cloud computing robot cognitive platform. If the cloud computing robot cognitive platform passes the authentication, The robot body can be connected to the cloud computing robot cognitive platform. If the cloud computing robot cognitive platform cannot be authenticated by the first identity authentication unit, the robot body refuses to access the cloud computing robot cognitive platform, and only both parties pass each other. Certification, cloud computing robot cognitive platform and robot body can communicate with each other.

In a specific implementation, the instruction processing unit is further configured to process direct communication between the robot bodies, and the communication manner includes, but is not limited to, using technologies such as Bluetooth, ZigBee, WIFI, and the like. First identity authentication It is also used to perform two-way authentication with the robot body that communicates directly before the robot body communicates directly. The specific two-way authentication process can be performed by the two-way authentication method commonly used in the prior art, and will not be described here.

The cloud computing robot control device in this embodiment can be set independently or integrated with the robot body, but its logic function is completely independent.

Embodiment 2:

FIG. 2 is a schematic structural diagram of a cloud computing robot cognitive platform according to Embodiment 2 of the present invention. As shown in the figure, the cloud computing robot cognitive platform includes:

The public cognitive unit 201 is configured to store common data (for example, encyclopedias, public maps, and the like) of the corresponding plurality of robot bodies, and can be used together by all the robot bodies belonging to the platform. The common cognitive unit Provides common data services to all robot ontology at minimal cost.

The private cognitive unit 202 has a one-to-one correspondence with the robot body. Each independent private cognitive unit is an independent private cloud for receiving instructions issued by the robot body. If the received instruction is a public data acquisition instruction, then The public cognitive unit acquires the corresponding public data and sends it to the corresponding robot body. Otherwise, after processing the received command, the corresponding control command is sent to the corresponding robot body. Independent private cognitive units can communicate with each other through specific protocols.

The cloud computing robot cognitive platform in this embodiment is placed in the cloud, which is equivalent to the human brain, and is used for comprehensive processing of instructions transmitted by the robot body, and gives a robot body control instruction.

In a specific implementation, the cloud computing robot cognitive platform may further include:

The second identity authentication unit 203 is configured to perform two-way identity authentication with the accessed robot body, anchor the private cognitive unit with the corresponding robot body, and establish a correspondence relationship between the public cognitive unit and the robot body.

The two-way authentication here refers to: when the second identity authentication unit accesses the robot body to the cloud computing robot cognitive platform, the identity of the robot body is authenticated, and the robot body authorized for authentication is allowed to access the cloud computing robot cognition. Platform, the robot body that fails to pass the certification will refuse to access the cloud computing robot cognitive platform. At the same time, the first identity authentication unit will also authenticate the cloud computing robot cognitive platform. If the cloud computing robot cognitive platform passes the authentication, then The robot body can be connected to the cloud computing robot cognitive platform. If the cloud computing robot cognitive platform cannot be authenticated by the first identity authentication unit, the robot body refuses to access the cloud computing robot cognitive platform, and only both parties are mutually authenticated. The cloud computing robot cognitive platform and the robot body can communicate with each other.

The cloud computing robot cognitive platform of the second embodiment and the cloud computing robot control device of the first embodiment can implement communication by using any wireless communication technology such as LTE/WCDMA/CDMA2000/TD-SCDMA/GPRS, WIFI, or can be completed by wired communication.

For convenience of description, the various parts of the above described devices are described in terms of functions divided into various modules or units. Of course, the functions of the various modules or units may be implemented in one or more software or hardware in the practice of the invention.

Embodiment 3:

Corresponding to the first embodiment, the embodiment of the present invention further provides a computing robot control method, and FIG. 3 is a flowchart of the cloud computing robot control method according to the third embodiment of the present invention. As shown in the figure, the present invention is shown. Embodiment 3 The cloud computing robot control method includes the following steps:

Step 301: Receive an instruction sensed by the robot body, and the instructions sensed by the robot body mainly include user instructions in a manner of voice, remote control, button, gesture, touch, and the like.

In the specific implementation, the locally processable instructions mainly include some instructions that can be processed without the need for robot conditional reflection and some conditional reflection instructions that exist in the local instruction set, and mainly include remote control instructions, touch commands, and/or button commands. For example, when a user presses a button, the button itself has a certain meaning, and the robot can perform corresponding finger without any conditional reflection. Let the processing and execution of the corresponding operations. Non-locally processable instructions mainly refer to conditional reflection instructions that do not exist in the local instruction set, and mainly include voice commands, gesture commands, eye commands, and/or expression commands. For example, the user sends a voice, and after receiving the voice command, the robot finds that the command does not exist in the local command set, and needs to send the command to the cloud computing robot cognitive platform for voice recognition, analysis, and the like.

Step 302: It is determined whether the instruction sensed by the robot body belongs to a local processable instruction, and if yes, step 303 is performed; otherwise, step 304 is performed.

In step 303, the locally processable instructions are processed directly.

In step 304, the non-locally processable instructions are sent to the cloud computing robotic cognitive platform for processing.

Step 305: Receive a control instruction fed back by the cloud computing robot cognitive platform, and control the robot body to perform a corresponding operation, and the operation type mainly includes mechanical, servo, and/or transmission operations.

In a specific implementation, before the non-locally processable instruction is sent to the cloud computing robot cognitive platform, the method further includes the step of performing two-way identity authentication with the cloud computing robot cognitive platform.

Embodiment 4:

Corresponding to the second embodiment, the embodiment of the present invention further provides a computing robot control method, and FIG. 4 is a flowchart of a fourth cloud computing robot control method according to an embodiment of the present invention. As shown in the figure, the present invention is implemented. The fourth example of the cloud computing robot control method includes the following steps:

Step 401: Receive an instruction issued by a robot body.

Step 402, it is determined whether the received instruction issued by the robot body is a public data acquisition instruction, and if so, step 403 is performed, otherwise, step 404 is performed;

Step 403: Acquire corresponding public data and send the same to the robot body;

Step 404: After processing the instruction, send a corresponding control instruction to the robot body.

In a specific implementation, before receiving the instruction issued by the robot body, the two-way identity authentication is performed with the accessed robot body, and after the two-way authentication is passed, the robot body is anchored, so that the robot body and the body corresponding to the body are privately recognized. The cloud establishes a one-to-one correspondence, and at the same time establishes the correspondence between the public cognitive cloud and the robot ontology. For the robot that establishes the anchor relationship between the ontology and the private cognitive cloud, the cloud computing robot cognitive platform can handle Information sent by the ontology.

Those skilled in the art will appreciate that embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.

These computer program instructions can also be loaded into a computer or other programmable data processing device Having a series of operational steps performed on a computer or other programmable device to produce computer-implemented processing such that instructions executed on a computer or other programmable device are provided for implementing one or more processes in a flowchart and/or Or block diagram the steps of a function specified in a box or multiple boxes.

While the preferred embodiment of the invention has been described, it will be understood that Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and the modifications and

Claims

A cloud computing robot control device, comprising:

The instruction processing unit is configured to distinguish whether the instruction sensed by the robot body belongs to a local processable instruction, send the local processable instruction to the body control unit for processing, and send the non-local processable instruction to the cloud computing robot cognitive platform for processing;

And a body control unit, configured to control the robot body to perform a corresponding operation according to the received control instruction fed back by the cloud computing robot cognitive platform.
The device of claim 1 further comprising:

The first identity authentication unit is configured to perform two-way identity authentication with the cloud computing robot cognitive platform when the robot body is connected to the cloud computing robot cognitive platform.
The device according to claim 2, wherein the first identity authentication unit is further configured to perform bidirectional identity authentication on the robot body directly communicating before the robot body directly communicates.
The device of claim 1, wherein the locally processable instructions comprise remote control instructions, touch instructions, and/or key instructions; the non-locally processable instructions comprise voice instructions, gesture instructions, eye instructions, and/or Emoticon instructions.
The apparatus according to claim 1, wherein the body control unit is configured to control the robot body to perform a corresponding mechanical, servo, and/or transmission operation according to the received control instruction of the cloud computing robot cognitive platform. .
The apparatus of claim 1 wherein direct communication is achieved between said robot bodies by said instruction processing unit.
A cloud computing robot cognitive platform, comprising:

a common cognitive unit corresponding to the plurality of robot bodies for storing common data of the plurality of robot bodies;

a private cognitive unit, corresponding to the robot body, for receiving the robot body And outputting the corresponding public data from the common cognitive unit to the robot body, if the instruction is a public data acquisition instruction, otherwise sending the corresponding control instruction to the instruction after processing the instruction The robot body.
The platform of claim 7 further comprising:

a second identity authentication unit, configured to perform bidirectional identity authentication with the accessed robot body, anchor the private cognitive unit with the robot body, and establish the public cognitive unit and the robot body Correspondence.
A cloud computing robot control method, comprising the following steps:

Receiving an instruction sensed by the robot body;

Distinguishing whether the instruction sensed by the robot body belongs to a local processable instruction, directly processing the local processable instruction, and transmitting the non-local processable instruction to the cloud computing robot cognitive platform for processing;

Receiving a control instruction fed back by the cloud computing robot cognitive platform, and controlling the robot body to perform a corresponding operation.
The method of claim 9 further comprising the step of performing two-way identity authentication with said cloud computing robotic cognitive platform prior to transmitting the non-locally processable instructions to the cloud computing robotic cognitive platform.
The method of claim 10, wherein the locally processable instructions comprise remote control instructions, touch instructions, and/or key instructions; the non-locally processable instructions comprise voice instructions, gesture instructions, eye instructions, and/or Emoticon instructions.
A cloud computing robot control method, comprising the following steps:

Receiving an instruction issued by the robot body;

Determining whether the instruction is a public data acquisition instruction, and if yes, acquiring corresponding public data and transmitting the same to the robot body; otherwise, processing the instruction, and then sending a corresponding control instruction to the robot body.
The method of claim 12, further comprising the step of performing two-way identity authentication with the accessed robot body prior to receiving an instruction issued by the robot body, and performing anchoring with the robot body.