Man-machine cooperation intelligent control system based on AIGC

Through the AIGC's human-machine collaborative intelligent control system, the information channel and holographic perception function between AI, BI and CI are used to solve the problems of accuracy and flexibility of the human-machine collaborative system in the existing technology, and efficient motion planning is achieved and tracking capabilities provide complexity support for robots.

CN119026633APending Publication Date: 2024-11-26ZHEJIANG EMERGEN ROBOT TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202310593201.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-24
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

In the prior art, it is difficult for human-computer collaborative systems to achieve infinitely accurate task goals of expressing the human brain, and the fixed logic of traditional control systems cannot adapt to dynamic changes in various situations.

Method used

Adopt AIGC-based human-machine collaborative intelligent control system to interact through the information channel between artificial intelligence AI, biological intelligence BI and collective intelligent CI. Using holographic perception and advanced reasoning functions, a dynamic programming language is built to realize AI and BI. seamless interaction between them and iterate through feedback to maximize the completion probability of instructions.

Benefits of technology

Realize the perception, reasoning and execution functions of human-computer collaborative intelligent control system, reduce the deviation of natural language description, enhance the robot's ability to plan motion and track trajectory, provide complexity support for the robot, and move towards "silicon-based life" .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026633A_ABST
    Figure CN119026633A_ABST
Patent Text Reader

Abstract

The invention relates to a man-machine cooperation intelligent control system based on AIGC, which is composed of three parts of artificial intelligence AI, biological intelligence BI and collective intelligence CI, and two information channels are formed between every two of the artificial intelligence AI, the biological intelligence BI and the collective intelligence CI. The method has the functions of sensing, reasoning, decision making and action executing, basic motion planning and trajectory tracking capacity can be achieved easily, and complexity support is provided for the robot to move towards'silicon-based life 'to'artificial life'.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an AIGC-based human-machine collaborative intelligent control system. Background Art

[0002] The human brain is an extremely complex and sophisticated organ that enables us to perceive, reason, make decisions, and perform actions.

[0003] In the existing technology, there is no technology that can completely model the tens of billions of neurons in the brain one by one. Therefore, whether the voice commands or operation instructions issued by humans can express their task objectives with infinite precision requires a more intelligent human-computer collaborative system to maximize the probability of completing the real goals of the human brain within the scope of safety constraints through actual operations.

[0004] In traditional control systems, programmers write programs for machines, that is, AI components in this article, in advance. The programs are fixed logic, and once the logic is determined, they will not change. Some programs have a certain degree of flexibility and take into account different treatments in more situations, but in essence they still run under the pre-existing logical conditions. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned prior art, the purpose of the present invention is to provide a human-machine collaborative intelligent control system based on AIGC, which provides complexity support for robots to move towards "silicon-based life" and "artificial life (Artificial Life)".

[0006] To achieve the above-mentioned purpose of the invention, the present invention provides a human-machine collaborative intelligent control system based on AIGC, which consists of three parts: artificial intelligence AI, biological intelligence BI and collective intelligence CI. Two information channels are formed between the artificial intelligence AI, the biological intelligence BI and the collective intelligence CI.

[0007] According to a technical solution of the present invention, the artificial intelligence AI transmits information to the biological intelligence BI through a first channel, and the first channel at least includes a human-computer interaction interface.

[0008] According to a technical solution of the present invention, the biological intelligence BI transmits information to the artificial intelligence AI through a second channel, and the second channel at least includes a human-computer interaction interface.

[0009] According to a technical solution of the present invention, the artificial intelligence AI transmits information to the collective intelligence CI through a third channel, and the information transmitted by the third channel includes at least structured real-time data, database data, various natural languages ​​and programming language texts.

[0010] According to a technical solution of the present invention, the collective intelligence CI transmits information to the artificial intelligence AI through a fourth channel, and the information transmitted by the fourth channel at least includes a programming language text that can be accepted by the artificial intelligence AI.

[0011] According to a technical solution of the present invention, the biological intelligence BI transmits information to the collective intelligence CI through a fifth channel, and the information transmitted by the fifth channel includes at least natural language and brain-computer interface.

[0012] According to a technical solution of the present invention, the collective intelligence CI transmits information to the biological intelligence BI through the sixth channel, and the information transmitted by the sixth channel includes at least visual information and auditory information.

[0013] According to a technical solution of the present invention, the human-machine collaborative intelligent control system has a holographic perception function, which encodes and compresses the input multimodal data into a feature vector, and then decodes the original holographic information from the feature vector.

[0014] According to a technical solution of the present invention, the human-machine collaborative intelligent control system has a high-order reasoning function. By constructing a context training set from cause to effect, the human-machine collaborative intelligent control system is trained based on the attention mechanism of Transformer.

[0015] According to a technical solution of the present invention, the feature coding of holographic perception is directly connected in series to the collective intelligence CI.

[0016] According to a technical solution of the present invention, the intention of the human-machine collaborative intelligent control system is formed by using goals and constraints to limit the generation method.

[0017] The goal is to maximize the probability that the CI-generated content instructs AI to perform operations that comply with the instructions issued by BI;

[0018] The constraints refer to the realistic conditions that constrain the AI's execution capabilities, including the machine's power, speed, acceleration, position range, control capabilities, etc.

[0019] According to a technical solution of the present invention, the human-machine collaborative intelligent control system has a self-adjusting mechanism, which feedback-adjusts the human-machine collaborative intelligent control system based on the self-adjusting parameters generated during the operation of the human-machine collaborative intelligent control system.

[0020] According to one aspect of the present invention, an AIGC-based human-machine collaborative intelligent control system as described in any one of the above technical solutions is proposed and applied to a robot.

[0021] According to one aspect of the present invention, an AIGC-based human-machine collaborative intelligent control system as described in any one of the above technical solutions is proposed and applied to intelligent manufacturing.

[0022] According to one aspect of the present invention, an AIGC-based human-machine collaborative intelligent control system as described in any one of the above technical solutions is proposed, which is applied to unmanned vehicle navigation.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] According to a solution of the present invention, by constructing information channels between artificial intelligence AI, the biological intelligence BI and the collective intelligence CI, it is ensured that artificial intelligence AI can interact seamlessly and effectively with biological intelligence BI and collective intelligence CI. When the above BI issues instructions, CI understands them through artificial intelligence technology including but not limited to large language models, and then generates content through AIGC. The content is the programming language of the dynamically programmable intelligent machine represented by guiding AI. During the execution of AI, it interacts with the BI human user who issues the instructions, and submits whether the interaction results meet human expectations to the artificial intelligence of CI. Through multiple repeated iterations, the maximum probability of completing the instructions issued by BI is achieved. In this way, the opacity of human BI and the problem that natural language descriptions are prone to deviations are minimized. The human-machine collaborative intelligent control system based on AIGC has the functions of perception, reasoning, decision-making and action execution, which is conducive to realizing basic motion planning and trajectory tracking capabilities, and provides complexity support for robots to move towards "silicon-based life" and "artificial life (Artificial Life)". BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 The structure diagram of the human-machine collaborative intelligent control system based on AIGC in an embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0027] The description of the embodiments of this specification should be combined with the corresponding drawings, which should be considered as part of the complete specification. In the drawings, the shape or thickness of the embodiments may be enlarged and indicated for simplification or convenience. Furthermore, the parts of each structure in the drawings will be described separately. It is worth noting that the elements not shown in the drawings or not described in words are in a form known to ordinary technicians in the relevant technical field.

[0028] The description of the embodiments herein and any reference to directions and orientations are only for the convenience of description and are not to be construed as any limitation on the scope of protection of the present invention. The following description of the preferred embodiments may involve combinations of features, which may exist independently or in combination, and the present invention is not particularly limited to the preferred embodiments. The scope of the present invention is defined by the claims.

[0029] like Figure 1 As shown, a human-machine collaborative intelligent control system based on AIGC of the present invention is composed of three parts: artificial intelligence AI, biological intelligence BI and collective intelligence CI. Two information channels are formed between the artificial intelligence AI, the biological intelligence BI and the collective intelligence CI.

[0030] AIGC, which stands for “AI generated content”, is also known as generative AI, which means content generated by artificial intelligence.

[0031] In this embodiment, by constructing information channels between artificial intelligence AI, biological intelligence BI and collective intelligence CI, it is ensured that artificial intelligence AI can interact seamlessly and effectively with biological intelligence BI and collective intelligence CI, so that the human-machine collaborative intelligent control system based on AIGC has the functions of perception, reasoning, decision-making and action execution, which is conducive to realizing basic motion planning and trajectory tracking capabilities. There is no need for programmers to write fixed programs and logic for the machine in advance, providing complexity support for the robot to move towards "silicon-based life" and "artificial life (Artificial Life)".

[0032] Specifically, when BI issues instructions, CI understands them through artificial intelligence technologies including but not limited to large language models, and then generates content through AIGC, which is the programming language that guides the dynamically programmable intelligent machines represented by AI. During the execution of AI, it interacts with the BI human user who issues instructions, and submits whether the interaction results meet human expectations to CI's artificial intelligence. Through multiple repeated iterations, the instructions issued by BI are completed with the highest probability. This minimizes the problem of human BI opacity and the bias of natural language descriptions.

[0033] Furthermore, through the interaction between artificial intelligence AI, biological intelligence BI and collective intelligence CI, and the realization of knowledge fusion in the interaction process, new knowledge is generated through knowledge fusion, which can achieve problem solving and intelligence improvement.

[0034] Among them, artificial intelligence AI refers to the ability of machines to perform tasks that require human intelligence, biological intelligence BI refers to the cognitive ability of organisms (including humans), and collective intelligence CI refers to the ability of individuals in a group to collaborate to solve problems and make decisions, such as GPT.

[0035] In one embodiment of the present invention, preferably, the artificial intelligence AI transmits information to the biological intelligence BI through a first channel, and the first channel at least includes a human-computer interaction interface.

[0036] In one embodiment of the present invention, preferably, the biological intelligence BI transmits information to the artificial intelligence AI through a second channel, and the second channel at least includes a human-computer interaction interface.

[0037] In one embodiment of the present invention, preferably, the artificial intelligence AI transmits information to the collective intelligence CI through a third channel, and the information transmitted by the third channel at least includes structured real-time data, database data, various natural languages ​​and programming language texts.

[0038] In one embodiment of the present invention, preferably, the collective intelligence CI transmits information to the artificial intelligence AI through a fourth channel, and the information transmitted by the fourth channel at least includes a programming language text that can be accepted by the artificial intelligence AI.

[0039] In one embodiment of the present invention, preferably, the biological intelligence BI transmits information to the collective intelligence CI through a fifth channel, and the information transmitted by the fifth channel includes at least natural language and brain-computer interface.

[0040] In one embodiment of the present invention, preferably, the collective intelligence CI transmits information to the biological intelligence BI through a sixth channel, and the information transmitted by the sixth channel includes at least visual information and auditory information.

[0041] In one embodiment of the present invention, preferably, the human-machine collaborative intelligent control system has a holographic perception function, by encoding and compressing the input multimodal data into a feature vector, and then decoding the holographic original information from the feature vector.

[0042] In this embodiment, the human-machine collaborative intelligent control system uses multimodal data (vision, laser, sound, touch, etc.) as input and utilizes holographic perception function to increase information density, which is beneficial to reducing data volume requirements, increasing the collaboration among artificial intelligence AI, the biological intelligence BI and the collective intelligence CI, and the efficiency of information transmission in the cycle process, making the information transmission between artificial intelligence AI, the biological intelligence BI and the collective intelligence CI more efficient.

[0043] Based on the holographic perception function of the human-machine collaborative intelligent control system, there is no need to build a full data set of the original sensor, and efficient storage can be achieved only with the help of holographic perception coding.

[0044] In one embodiment of the present invention, preferably, the human-machine collaborative intelligent control system has a high-order reasoning function, and the human-machine collaborative intelligent control system is trained based on the attention mechanism of Transformer by constructing a context training set from cause to effect.

[0045] In this embodiment, the high-order reasoning function is mainly realized by collective intelligence CI. The basic component of collective intelligence CI is transformer. By introducing the attention mechanism of transformer, the association relationship is learned from massive training sets to achieve cause-to-effect.

[0046] In one embodiment of the present invention, preferably, the feature encoding of holographic perception is directly connected in series to the collective intelligence CI, while the intermediate process (including a large number of algorithms) is completed in a black box.

[0047] In one embodiment of the present invention, preferably, the intention of the human-machine collaborative intelligent control system is formed by using goals and constraints to limit the generation, thereby avoiding the divergence of the intention of the human-machine collaborative intelligent control system and reducing resource usage.

[0048] Among them, the goal refers to maximizing the probability that the CI generates content to guide AI to perform operations in accordance with the instructions issued by BI; the constraints refer to the realistic conditions that constrain AI's execution capabilities, including the machine's power, speed, acceleration, position range, control capabilities, etc.

[0049] In one embodiment of the present invention, preferably, the human-machine collaborative intelligent control system has a self-adjusting mechanism, and the human-machine collaborative intelligent control system is feedback-adjusted based on the self-adjusting parameters generated during the operation of the human-machine collaborative intelligent control system.

[0050] According to one aspect of the present invention, an AIGC-based human-machine collaborative intelligent control system as described in any one of the above technical solutions is proposed and applied to a robot.

[0051] According to one aspect of the present invention, an AIGC-based human-machine collaborative intelligent control system as described in any one of the above technical solutions is proposed and applied to intelligent manufacturing.

[0052] According to one aspect of the present invention, an AIGC-based human-machine collaborative intelligent control system as described in any one of the above technical solutions is proposed, which is applied to unmanned vehicle navigation.

[0053] The human-machine collaborative intelligent control system based on AIGC of the present invention is composed of three parts: artificial intelligence AI, biological intelligence BI and collective intelligence CI. Two information channels are formed between the artificial intelligence AI, the biological intelligence BI and the collective intelligence CI. By constructing information channels between the artificial intelligence AI, the biological intelligence BI and the collective intelligence CI, it is ensured that the artificial intelligence AI can interact seamlessly and effectively with the biological intelligence BI and the collective intelligence CI, so that the human-machine collaborative intelligent control system based on AIGC has the functions of perception, reasoning, decision-making and action execution, which is conducive to realizing basic motion planning and trajectory tracking capabilities, and provides complexity support for robots to move towards "silicon-based life" and "artificial life (Artificial Life)".

[0054] Furthermore, through the interaction between artificial intelligence AI, biological intelligence BI and collective intelligence CI, and the realization of knowledge fusion in the interaction process, new knowledge is generated through knowledge fusion, which can achieve problem solving and intelligence improvement.

[0055] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A human-machine collaborative intelligent control system based on AIGC, characterized in that: It consists of three parts: artificial intelligence AI, biological intelligence BI and collective intelligence CI. Two information channels are formed between the artificial intelligence AI, the biological intelligence BI and the collective intelligence CI.

2. The AIGC-based human-machine collaborative intelligent control system according to claim 1 is characterized in that: The artificial intelligence AI transmits information to the biological intelligence BI through a first channel, and the first channel at least includes a human-computer interaction interface.

3. The human-machine collaborative intelligent control system based on AIGC according to claim 1 is characterized in that: The biological intelligence BI transmits information to the artificial intelligence AI through a second channel, and the second channel at least includes a human-computer interaction interface.

4. The AIGC-based human-machine collaborative intelligent control system according to claim 1 is characterized in that: The artificial intelligence AI transmits information to the collective intelligence CI through a third channel, and the information transmitted by the third channel includes at least structured real-time data, database data, various natural languages ​​and programming language texts.

5. The AIGC-based human-machine collaborative intelligent control system according to claim 1 is characterized in that: The collective intelligence CI transmits information to the artificial intelligence AI through a fourth channel, and the information transmitted through the fourth channel at least includes a programming language text that can be accepted by the artificial intelligence AI.

6. The AIGC-based human-machine collaborative intelligent control system according to claim 1 is characterized in that: The biological intelligence BI transmits information to the collective intelligence CI through the fifth channel, and the information transmitted by the fifth channel includes at least natural language and brain-computer interface.

7. The human-machine collaborative intelligent control system based on AIGC according to claim 1 is characterized in that: The collective intelligence CI transmits information to the biological intelligence BI through the sixth channel, and the information transmitted by the sixth channel includes at least visual information and auditory information.

8. The AIGC-based human-machine collaborative intelligent control system according to claim 1 is characterized in that: It has holographic perception function. It encodes and compresses the input multimodal data into feature vectors, and then decodes the original holographic information from the feature vectors.

9. The AIGC-based human-machine collaborative intelligent control system according to claim 1 is characterized in that: It has high-order reasoning capabilities. By constructing a contextual training set from cause to effect, it trains the human-machine collaborative intelligent control system based on the Transformer's attention mechanism.

10. The AIGC-based human-machine collaborative intelligent control system according to claim 8, characterized in that: The characteristic encoding of holographic perception is directly connected to the collective intelligence CI.

11. The AIGC-based human-machine collaborative intelligent control system according to claim 1 is characterized in that: Use goals and constraints to limit the generation method and form the intention of human-machine collaborative intelligent control system. The goal is to maximize the probability that the CI-generated content instructs AI to perform operations in accordance with the instructions issued by BI; The constraints refer to the realistic conditions that limit the AI's execution capabilities, including the machine's power, speed, acceleration, position range, and control capabilities.

12. The AIGC-based human-machine collaborative intelligent control system according to claim 1 is characterized in that: The human-machine collaborative intelligent control system has a self-adjusting mechanism, which feedback-adjusts the human-machine collaborative intelligent control system based on the self-adjusting parameters generated during the operation of the human-machine collaborative intelligent control system.

13. A human-machine collaborative intelligent control system based on AIGC according to any one of claims 1 to 12, characterized in that: Applied to robots.

14. A human-machine collaborative intelligent control system based on AIGC according to any one of claims 1 to 12, characterized in that: Applied to smart manufacturing.

15. A human-machine collaborative intelligent control system based on AIGC according to any one of claims 1 to 12, characterized in that: Applied to unmanned vehicle navigation.

Citation Information

Cited By

  • Dynamic response analysis method and system for small offset collision vehicle

    CN120429960A