Robot control method, system and electroencephalogram acquisition device
By using EEG signal acquisition equipment and intention recognition models, the intention information of users who have lost the ability to speak is collected and recognized in real time, and the robot is controlled to perform corresponding operations. This solves the communication problem of users who have lost the ability to speak and improves communication efficiency and the accuracy of intention information recognition.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SOUNDAI TECH CO LTD
- Filing Date
- 2023-11-29
- Publication Date
- 2026-07-14
AI Technical Summary
People who have lost the ability to speak are unable to communicate effectively with others, and current technology lacks an effective robot control system to help them achieve normal communication.
The system uses an EEG signal acquisition device to collect the target user's EEG signals in real time. First, it searches for matching intent information in the signal database. If no match is found, the intent information is determined through an intent recognition model, and the intent command is sent to the robot to execute the corresponding operation.
It enables the recognition and execution of intentions for users who have lost the ability to speak, improving communication efficiency, and ensuring the success rate of intention information recognition through the intention recognition model when there is no match in the database.
Smart Images
Figure CN117681191B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of control technology, and in particular to a robot control method, system, and electroencephalogram (EEG) signal acquisition device. Background Technology
[0002] According to a national survey of disabled persons, there are millions of people with physical disabilities in China, including those who were born without the ability to speak and those who lost their ability to speak due to illness. These individuals cannot communicate like able-bodied people and rely on their families for round-the-clock care in their daily lives. Therefore, there is an urgent need for a robotic control system to help these people achieve normal communication. Summary of the Invention
[0003] To address the problems existing in the prior art, embodiments of the present invention provide a robot control method, system, and electroencephalogram (EEG) signal acquisition device.
[0004] This invention provides a robot control system, including an electroencephalogram (EEG) signal acquisition device and a robot;
[0005] The EEG signal acquisition device is used to acquire the first EEG signal of the target user and search the signal database to see if it includes intention information that matches the first EEG signal; the signal database stores the correspondence between EEG signals and intention information.
[0006] The EEG signal acquisition device is further configured to, when no intention information matching the first EEG signal is found in the signal database, input the first EEG signal into the intention recognition model to obtain the target intention information output by the intention recognition model, determine the target intention instruction corresponding to the target intention information, and send the target intention instruction to the robot.
[0007] The robot is used to execute the corresponding intention operation in response to the target intention instruction.
[0008] According to a robot control system provided by the present invention, the EEG signal acquisition device is specifically used to acquire the second EEG signal of the target user in real time, and to acquire the first EEG signal when the intention information corresponding to the second EEG signal is found in the wake-up database; the wake-up database stores the correspondence between EEG signals and intention information used to wake up the EEG signal acquisition device.
[0009] According to a robot control system provided by the present invention, the electroencephalogram (EEG) signal acquisition device is specifically used to acquire the eye movements of the target user in real time through a camera device, and to acquire the first EEG signal when the eye movements match a preset eye movement; the preset eye movement is the action of waking up the EEG signal acquisition device.
[0010] According to a robot control system provided by the present invention, the EEG signal acquisition device is further configured to match the target intention information with sensitive intention information in a sensitive database; the sensitive intention information is used to characterize the negative emotions of the target user.
[0011] In the event of a failed match, the target intent instruction corresponding to the target intent information is determined based on the correspondence between intent information and intent instruction.
[0012] According to a robot control system provided by the present invention, the electroencephalogram (EEG) signal acquisition device is further configured to send an alarm command to the robot when a match is successful.
[0013] The robot is also used to output alarm information in response to the alarm command.
[0014] According to a robot control system provided by the present invention, the robot is specifically used to perform semantic understanding of the target intention instruction. When the target intention instruction is determined to be an instruction to instruct the robot to move based on the semantic understanding result, the robot determines the target position corresponding to the target intention instruction based on the correspondence between the intention instruction and the position, performs path planning based on the robot's current position and the target position, moves to the target position based on the planned path, and executes the intention operation corresponding to the target intention instruction.
[0015] According to a robot control system provided by the present invention, the robot is specifically configured to, in response to the target intention instruction, convert the target intention instruction into speech and play the converted speech signal when the target intention instruction is determined to be an instruction to instruct the robot to play speech based on the semantic understanding result.
[0016] The present invention also provides a robot control method, comprising:
[0017] The system collects the first EEG signal of the target user and searches the signal database to see if it contains intention information that matches the first EEG signal; the signal database stores the correspondence between EEG signals and intention information.
[0018] If no intention information matching the first EEG signal is found in the signal database, the first EEG signal is input into the intention recognition model to obtain the target intention information output by the intention recognition model, the target intention instruction corresponding to the target intention information is determined, and the target intention instruction is sent to the robot; the target intention instruction is used to instruct the robot to perform the corresponding intention operation.
[0019] The present invention also provides a robot control device, comprising:
[0020] The acquisition unit is used to acquire the target user's initial electroencephalogram (EEG) signal.
[0021] The search unit is used to search in the signal database for whether it includes intention information that matches the first EEG signal; the signal database stores the correspondence between EEG signals and intention information;
[0022] The determining unit is configured to, when no intention information matching the first EEG signal is found in the signal database, input the first EEG signal into the intention recognition model to obtain the target intention information output by the intention recognition model, and determine the target intention instruction corresponding to the target intention information;
[0023] The sending unit is used to send the target intent instruction to the robot; the target intent instruction is used to instruct the robot to perform the corresponding intent operation.
[0024] The present invention also provides an electroencephalogram (EEG) signal acquisition device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the robot control method described above.
[0025] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the robot control method as described above.
[0026] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the robot control method as described above.
[0027] The present invention provides a robot control method, system, and EEG signal acquisition device. The system includes an EEG signal acquisition device and a robot. When the EEG signal acquisition device acquires a first EEG signal from a target user, it searches a signal database for matching intent information. If no matching intent information is found in the signal database, the first EEG signal is input into an intent recognition model to obtain target intent information output by the intent recognition model. The target intent command corresponding to the target intent information is then sent to the robot, causing the robot to respond to the target intent command and execute the corresponding intent operation. It can be seen that the present invention prioritizes searching the signal database for intent information matching the first EEG signal. Only when no matching intent information is found in the signal database does it determine the target intent information based on the intent recognition model. This achieves intent recognition of the target user and execution of the corresponding intent operation, helping the target user achieve normal communication and increasing the probability of successful intent information recognition. Attached Figure Description
[0028] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0029] Figure 1 This is a schematic diagram of the robot control system provided in an embodiment of the present invention;
[0030] Figure 2 This is a flowchart illustrating the robot control method provided in an embodiment of the present invention;
[0031] Figure 3 This is a schematic diagram of the robot control device provided in an embodiment of the present invention;
[0032] Figure 4 This is a schematic diagram of the physical structure of the electroencephalogram (EEG) signal acquisition device provided in an embodiment of the present invention. Detailed Implementation
[0033] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0034] Figure 1 This is a schematic diagram of the robot control system provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the robot control system includes an electroencephalogram (EEG) signal acquisition device and the robot.
[0035] The EEG signal acquisition device is used to acquire the first EEG signal of the target user and search the signal database to see if it includes intention information that matches the first EEG signal; the signal database stores the correspondence between EEG signals and intention information.
[0036] The EEG signal acquisition device is further configured to, when no intention information matching the first EEG signal is found in the signal database, input the first EEG signal into the intention recognition model to obtain the target intention information output by the intention recognition model, determine the target intention instruction corresponding to the target intention information, and send the target intention instruction to the robot.
[0037] The robot is used to execute the corresponding intention operation in response to the target intention instruction.
[0038] The target user can be a user who has lost the ability to speak, and the EEG signal acquisition device can be an EEG signal acquisition cap.
[0039] For example, when a target user wants to communicate, an EEG signal acquisition device can be worn on the head, allowing the device to collect the target user's first EEG signal in real time. The device then searches a signal database for intent information that matches the first EEG signal. If a matching intent information is found in the database, it means that the database pre-stores the intent information for the matching EEG signal, and this intent information can be directly identified as the target intent information. If no matching intent information is found in the database, it means the first EEG signal is a new EEG signal. In this case, the target intent information cannot be determined based on the signal database, and the first EEG signal needs to be input into an intent recognition model. The intent recognition model then performs feature analysis on the first EEG signal to determine the target intent information corresponding to it.
[0040] When determining the target intent information corresponding to the first EEG signal, the target intent instruction corresponding to the pre-stored correspondence between intent information and intent commands is determined based on the pre-stored correspondence between intent information and intent commands. The target intent instruction is then sent to the robot. When the robot receives the target intent instruction sent by the EEG signal acquisition device through the network transmission module, it responds to the target intent instruction and executes the corresponding intent operation. For example, if the target intent information corresponding to the first EEG signal of the target user is "I want to drink water", and the pre-stored correspondence between the intent information "drink water" and the intent command "go get water", the target intent instruction can be determined to be "go get water". When the robot receives the target intent instruction "go get water", it automatically gets water for the target user, thus realizing the function of helping the target user who has lost the ability to speak to do things through the robot.
[0041] It should be noted that the intent recognition model can be trained in the following way: obtain multiple intent information samples, input the multiple intent information samples into the initial intent recognition model, perform feature analysis on the intent information samples through the initial intent recognition model to obtain the predicted intent command output by the initial intent recognition model, optimize the model parameters of the initial intent recognition model based on the predicted intent command and the real intent command corresponding to the intent information samples until the convergence condition is reached, and obtain the intent recognition model.
[0042] The robot control system provided by this invention includes an electroencephalogram (EEG) signal acquisition device and a robot. When the EEG signal acquisition device acquires the first EEG signal of a target user, it searches a signal database for intention information matching the first EEG signal. If no matching intention information is found in the signal database, the first EEG signal is input into an intention recognition model to obtain the target intention information output by the intention recognition model. The target intention command corresponding to the target intention information is then sent to the robot, causing the robot to respond to the target intention command and execute the corresponding intention operation. It can be seen that this invention prioritizes searching the signal database for intention information matching the first EEG signal. Only when no matching intention information is found in the signal database does it determine the target intention information based on the intention recognition model. This achieves the recognition of the target user's intention and the execution of the corresponding intention operation, helping the target user achieve normal communication and increasing the probability of successful intention information recognition.
[0043] In one embodiment, the EEG signal acquisition device is specifically used to acquire the second EEG signal of the target user in real time, and to acquire the first EEG signal when the intention information corresponding to the second EEG signal is found in the wake-up database; the wake-up database stores the correspondence between EEG signals and intention information used to wake up the EEG signal acquisition device.
[0044] For example, when the target user is constantly wearing an EEG signal acquisition device, the device can collect the target user's second EEG signal in real time and search the wake-up database for intent information corresponding to the second EEG signal used to wake up the device. If the database contains such intent information, it indicates the target user wants to communicate. The device then collects the first EEG signal following the second and performs intent analysis on it. The intent information corresponding to the second EEG signal can be a wake word, such as "little * little *", so that when the device determines the intent information corresponding to the second EEG signal, it can perform intent analysis on subsequent EEG signals and issue intent commands.
[0045] In this embodiment, the EEG signal acquisition device only performs subsequent EEG signal intent analysis and issues intent commands when it finds the intent information for waking up the EEG signal acquisition device corresponding to the second EEG signal in the wake-up database. This eliminates the need to analyze the EEG signals generated by the target user's own thinking or unwillingness to communicate, thus avoiding misanalysis of the EEG signals by the EEG signal acquisition device and improving the accuracy of the robot control system.
[0046] In one embodiment, the EEG signal acquisition device is specifically used to acquire the target user's eye movements in real time via a camera device, and to acquire the first EEG signal when the eye movements match a preset eye movement; the preset eye movement is the action of waking up the EEG signal acquisition device.
[0047] For example, the EEG signal acquisition device can be connected to a camera device via a telescopic rod. With the target user continuously wearing the EEG signal acquisition device, the camera device can continuously acquire at least two images of the target user and send these images to the EEG signal acquisition device. Based on the received images, the EEG signal acquisition device determines the target user's eye movements. When the eye movement matches a preset eye movement, it indicates that the target user intends to communicate. The EEG signal acquisition device then begins acquiring the target user's first EEG signal and performs intent analysis and issues the intent command. The preset eye movement can be a pre-configured action used to wake the EEG signal acquisition device, such as blinking twice consecutively, or closing one eye while opening the other.
[0048] In this embodiment, the EEG signal acquisition device receives images of the target user captured by the camera device in real time. Only when the eye movements determined based on the target user's image match the preset eye movements does the device begin to acquire the target user's first EEG signal and execute the intention analysis and issuance of intention commands based on the first EEG signal. There is no need to analyze the EEG signals generated by the target user's own thinking or unwillingness to communicate, thus avoiding misanalysis of the EEG signals by the EEG signal acquisition device and improving the accuracy of the robot control system.
[0049] In one embodiment, the EEG signal acquisition device is further configured to match the target intent information with sensitive intent information in a sensitive database; the sensitive intent information is used to characterize the negative emotions of the target user; in the event of a matching failure, the target intent instruction corresponding to the target intent information is determined based on the correspondence between intent information and intent instruction.
[0050] The EEG signal acquisition device is also used to send an alarm command to the robot when a match is successful; the robot is also used to respond to the alarm command and output alarm information.
[0051] For example, when determining the target intent information, the EEG signal acquisition device can also match the target intent information with sensitive intent information in a sensitive database. If the match fails, it means that the target user does not have negative emotions and is in a normal emotional state. At this time, based on the correspondence between intent information and intent commands, the target intent command corresponding to the target intent information is determined to determine the action or information that the target user needs to perform at this time. Based on the target intent command, the robot is controlled to perform the corresponding intent operation so that the robot can help the target user achieve normal operation.
[0052] When a match is successful, it indicates that the target user is currently experiencing negative emotions. However, the pre-stored correspondence between intent information and intent commands typically considers the normal actions the target user needs to perform. Therefore, based on this correspondence, it is impossible to determine the target intent command corresponding to the target intent information, resulting in intent command determination failure. In other words, no intentional operation is responded to the target user's first EEG signal. Since the target user's negative emotions may endanger their life, the EEG signal acquisition device sends an alarm command to the robot. Upon receiving the alarm command, the robot outputs alarm information, allowing the guardian to promptly monitor the target user and ensure their safety.
[0053] In this embodiment, the EEG signal acquisition device matches the target intent information with sensitive intent information in the sensitive database. When a match is successful, an alarm command is sent to the robot. Upon receiving the alarm command, the robot outputs alarm information, which allows the guardian to pay attention to the target user in a timely manner and ensure the safety of the target user's life.
[0054] In one embodiment, the robot is specifically used to perform semantic understanding of the target intent instruction. If the target intent instruction is determined to be an instruction to move the robot based on the semantic understanding result, the robot determines the target position corresponding to the target intent instruction based on the correspondence between the intent instruction and the position, performs path planning based on the robot's current position and the target position, moves to the target position based on the planned path, and executes the intent operation corresponding to the target intent instruction.
[0055] For example, when a robot receives a target intent command, it needs to perform semantic understanding on the command to obtain a semantic understanding result. Based on the semantic understanding result, it determines whether the target intent command is an instruction to move the robot or an instruction to play voice commands. If the semantic understanding result determines that the target intent command is an instruction to move the robot, it determines the target position corresponding to the target intent command based on the pre-stored correspondence between intent commands and positions, and obtains the robot's current position. Based on the current position and the target position, a path planning algorithm is used to plan a path. Then, the robot is controlled to move from the current position according to the planned path. When it reaches the target position... The robot executes the intent operation corresponding to the target intent command. For example, if the target intent command is "go get water", after semantic understanding of the target intent command, it is obtained that the target intent command is an instruction to move the robot. The pre-stored correspondence between intent commands and locations can include: the correspondence between going to get water and the kitchen location, the correspondence between going to get paper and the coffee table location in the living room, etc. Based on the correspondence between intent commands and locations, the target location corresponding to the target intent command "go get water" can be determined to be the kitchen location. Then, the robot controls its own chassis motion module to move, so that the robot moves to the kitchen to get water for the target user and delivers the water to the target user according to the planned path.
[0056] It should be noted that the robot also includes a charging module to provide power to the robot.
[0057] It should be noted that the robot may also include a lidar module and a camera module. The camera module can collect image information of the area and avoid obstacles during movement based on the image information; the lidar module can also collect point cloud data of the area and avoid obstacles during movement based on the point cloud data.
[0058] In this embodiment, when the target intent instruction is determined to be an instruction to move the robot based on the semantic understanding result, the robot can perform path planning based on its current position and the determined target position, and then execute the corresponding intent operation based on the planned path, thereby achieving the purpose of helping the target user perform actions through the robot.
[0059] In one embodiment, the robot is specifically configured to, in response to the target intent instruction, convert the target intent instruction into speech and play the converted speech signal when the target intent instruction is determined to be an instruction to instruct the robot to play speech based on the semantic understanding result.
[0060] For example, when the robot determines, based on semantic understanding, that the target intent instruction is not an instruction to move the robot, it can determine that the target intent instruction is an instruction to play a voice message. In this case, the robot performs speech conversion on the received target intent instruction to obtain a converted voice signal, which is then played through a speaker. For instance, if the target intent information is "Now I want to play with **", and the corresponding target intent instruction is "want to play", the robot will convert "want to play" into a voice signal and play it, allowing the caregiver to interact with the target user after receiving "want to play".
[0061] In this embodiment, if the target intent instruction is determined to be an instruction for the robot to play voice messages based on the semantic understanding result, the robot converts the target intent instruction into voice and plays the converted voice signal to remind the guardian to pay attention to the target user's psychological state in a timely manner.
[0062] This invention integrates EEG signal acquisition and analysis technology with robotics. By using EEG signal acquisition and analysis technology, it provides data generation, data analysis, data feature extraction, and determination of intention commands for target users who have lost the ability to speak. In turn, it controls the robot to realize the target user's desire to speak, increases the life happiness of people who have lost the ability to speak, effectively solves the communication problems of people who have lost the ability to speak, and improves communication efficiency.
[0063] Figure 2 This is a flowchart illustrating the robot control method provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the robot control method includes the following steps:
[0064] Step 201: Collect the first EEG signal of the target user.
[0065] Step 202: Search the signal database for intention information that matches the first EEG signal; the signal database stores the correspondence between EEG signals and intention information.
[0066] Step 203: If no intention information matching the first EEG signal is found in the signal database, the first EEG signal is input into the intention recognition model to obtain the target intention information output by the intention recognition model, and the target intention instruction corresponding to the target intention information is determined.
[0067] Step 204: Send the target intent instruction to the robot; the target intent instruction is used to instruct the robot to perform the corresponding intent operation.
[0068] The robot control method provided by this invention involves an EEG signal acquisition device searching a signal database for matching intent information when it acquires the first EEG signal from a target user. If no matching intent information is found in the database, the first EEG signal is input into an intent recognition model to obtain the target intent information output by the model. The corresponding target intent command is then sent to the robot, enabling it to respond to the intent command and execute the corresponding intent operation. This invention prioritizes searching the signal database for matching intent information. Only when no matching intent information is found in the database does it determine the target intent information based on the intent recognition model. This achieves intent recognition of the target user and execution of the corresponding intent operation, facilitating normal communication and increasing the probability of successful intent information recognition.
[0069] In one embodiment, step 201 above, which involves acquiring the target user's first electroencephalogram (EEG) signal, can be implemented in the following way:
[0070] The second EEG signal of the target user is collected in real time. If the intention information corresponding to the second EEG signal is found in the wake-up database, the first EEG signal is collected. The wake-up database stores the correspondence between EEG signals and intention information used to wake up the EEG signal collection device.
[0071] In one embodiment, step 201 above, which involves acquiring the target user's first electroencephalogram (EEG) signal, can be implemented in the following way:
[0072] The target user's eye movements are captured in real time by a camera device, and the first EEG signal is collected when the eye movements match a preset eye movement; the preset eye movement is the action that wakes up the EEG signal acquisition device.
[0073] In one embodiment, determining the target intent instruction corresponding to the target intent information in step 203 above can be implemented in the following way:
[0074] The target intent information is matched with sensitive intent information in a sensitive database; the sensitive intent information is used to characterize the negative emotions of the target user.
[0075] In the event of a failed match, the target intent instruction corresponding to the target intent information is determined based on the correspondence between intent information and intent instruction.
[0076] In one embodiment, the robot control method further includes the following steps:
[0077] If a match is successful, an alarm command is sent to the robot; the alarm command is used to instruct the robot to output alarm information.
[0078] The robot control device provided by the present invention is described below. The robot control device described below and the robot control method described above can be referred to in correspondence.
[0079] Figure 3 This is a schematic diagram of the robot control device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the robot control device 300 includes a data acquisition unit 301, a search unit 302, a determination unit 303, and a transmission unit 304; wherein:
[0080] Acquisition unit 301 is used to acquire the first EEG signal of the target user;
[0081] The search unit 302 is used to search in the signal database for whether it includes intention information that matches the first EEG signal; the signal database stores the correspondence between EEG signals and intention information;
[0082] The determining unit 303 is used to input the first EEG signal into the intention recognition model when no intention information matching the first EEG signal is found in the signal database, to obtain the target intention information output by the intention recognition model, and to determine the target intention instruction corresponding to the target intention information.
[0083] The sending unit 304 is used to send the target intent instruction to the robot; the target intent instruction is used to instruct the robot to perform the corresponding intent operation.
[0084] The robot control device provided by this invention, when acquiring the first EEG signal of a target user, searches a signal database for intent information matching the first EEG signal. If no matching intent information is found in the signal database, the first EEG signal is input into an intent recognition model to obtain the target intent information output by the intent recognition model. The target intent command corresponding to the target intent information is then sent to the robot, causing the robot to respond to the target intent command and execute the corresponding intent operation. It can be seen that this invention prioritizes searching the signal database for intent information matching the first EEG signal. Only when no matching intent information is found in the signal database does it determine the target intent information based on the intent recognition model. This achieves intent recognition of the target user and execution of the corresponding intent operation, helping the target user achieve normal communication and increasing the probability of successful intent information recognition.
[0085] Based on any of the above embodiments, the acquisition unit 301 is specifically used for:
[0086] The second EEG signal of the target user is collected in real time. If the intention information corresponding to the second EEG signal is found in the wake-up database, the first EEG signal is collected. The wake-up database stores the correspondence between EEG signals and intention information used to wake up the EEG signal collection device.
[0087] Based on any of the above embodiments, the acquisition unit 301 is specifically used for:
[0088] The target user's eye movements are captured in real time by a camera device, and the first EEG signal is collected when the eye movements match a preset eye movement; the preset eye movement is the action that wakes up the EEG signal acquisition device.
[0089] Based on any of the above embodiments, the determining unit 303 is specifically used for:
[0090] The target intent information is matched with sensitive intent information in a sensitive database; the sensitive intent information is used to characterize the negative emotions of the target user.
[0091] In the event of a failed match, the target intent instruction corresponding to the target intent information is determined based on the correspondence between intent information and intent instruction.
[0092] Based on any of the above embodiments, the determining unit 303 is further specifically used for:
[0093] If a match is successful, an alarm command is sent to the robot; the alarm command is used to instruct the robot to output alarm information.
[0094] Figure 4 This is a schematic diagram of the physical structure of the electroencephalogram (EEG) signal acquisition device provided in an embodiment of the present invention, such as... Figure 4 As shown, the EEG signal acquisition device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a robot control method, which includes: acquiring the first EEG signal of the target user;
[0095] The signal database is searched to see if it contains intention information that matches the first EEG signal; the signal database stores the correspondence between EEG signals and intention information.
[0096] If no intention information matching the first EEG signal is found in the signal database, the first EEG signal is input into the intention recognition model to obtain the target intention information output by the intention recognition model, and the target intention instruction corresponding to the target intention information is determined.
[0097] The target intent instruction is sent to the robot; the target intent instruction is used to instruct the robot to perform the corresponding intent operation.
[0098] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0099] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being able to be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer is able to execute the robot control method provided by the above methods, the method including: acquiring a first electroencephalogram (EEG) signal of a target user;
[0100] The signal database is searched to see if it contains intention information that matches the first EEG signal; the signal database stores the correspondence between EEG signals and intention information.
[0101] If no intention information matching the first EEG signal is found in the signal database, the first EEG signal is input into the intention recognition model to obtain the target intention information output by the intention recognition model, and the target intention instruction corresponding to the target intention information is determined.
[0102] The target intent instruction is sent to the robot; the target intent instruction is used to instruct the robot to perform the corresponding intent operation.
[0103] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the robot control methods provided by the above methods, the method comprising: acquiring a first electroencephalogram (EEG) signal of a target user;
[0104] The signal database is searched to see if it contains intention information that matches the first EEG signal; the signal database stores the correspondence between EEG signals and intention information.
[0105] If no intention information matching the first EEG signal is found in the signal database, the first EEG signal is input into the intention recognition model to obtain the target intention information output by the intention recognition model, and the target intention instruction corresponding to the target intention information is determined.
[0106] The target intent instruction is sent to the robot; the target intent instruction is used to instruct the robot to perform the corresponding intent operation.
[0107] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0108] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A robot control system, characterized in that, This includes EEG signal acquisition equipment and robots; The EEG signal acquisition device is used to acquire the first EEG signal of the target user and search the signal database to see if it includes intention information that matches the first EEG signal; the signal database stores the correspondence between EEG signals and intention information. The EEG signal acquisition device is further configured to, when no intention information matching the first EEG signal is found in the signal database, input the first EEG signal into the intention recognition model to obtain the target intention information output by the intention recognition model, determine the target intention instruction corresponding to the target intention information, and send the target intention instruction to the robot. The robot is used to execute the corresponding intention operation in response to the target intention instruction.
2. The robot control system according to claim 1, characterized in that, The EEG signal acquisition device is specifically used to acquire the second EEG signal of the target user in real time, and to acquire the first EEG signal when the intention information corresponding to the second EEG signal is found in the wake-up database. The wake-up database stores the correspondence between EEG signals and the intent information used to wake up the EEG signal acquisition device.
3. The robot control system according to claim 1, characterized in that, The EEG signal acquisition device is specifically used to acquire the target user's eye movements in real time through a camera device, and to acquire the first EEG signal when the eye movements match a preset eye movement. The preset eye movement is the action that wakes up the EEG signal acquisition device.
4. The robot control system according to claim 1, characterized in that, The EEG signal acquisition device is also used to match the target intent information with sensitive intent information in a sensitive database; the sensitive intent information is used to characterize the target user's negative emotions. In the event of a failed match, the target intent instruction corresponding to the target intent information is determined based on the correspondence between intent information and intent instruction.
5. The robot control system according to claim 4, characterized in that, The EEG signal acquisition device is also used to send an alarm command to the robot when a match is successful. The robot is also used to output alarm information in response to the alarm command.
6. The robot control system according to claim 4, characterized in that, The robot is specifically used to perform semantic understanding of the target intent command. If the target intent command is determined to be an instruction to move the robot based on the semantic understanding result, the robot determines the target position corresponding to the target intent command based on the correspondence between the intent command and the position. The robot performs path planning based on the current position of the robot and the target position, moves to the target position based on the planned path, and executes the intent operation corresponding to the target intent command.
7. The robot control system according to claim 6, characterized in that, Specifically, the robot is configured to, in response to the target intent instruction, convert the target intent instruction into speech and play the converted speech signal when it is determined, based on the semantic understanding result, that the target intent instruction is an instruction to instruct the robot to play speech.
8. A robot control method, characterized in that, include: Collect the first EEG signal of the target user; The signal database is searched to see if it contains intention information that matches the first EEG signal; the signal database stores the correspondence between EEG signals and intention information. If no intention information matching the first EEG signal is found in the signal database, the first EEG signal is input into the intention recognition model to obtain the target intention information output by the intention recognition model, and the target intention instruction corresponding to the target intention information is determined. The target intent instruction is sent to the robot; the target intent instruction is used to instruct the robot to perform the corresponding intent operation.
9. A brainwave signal acquisition device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the robot control method as described in claim 8.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the robot control method as described in claim 8.