Animal upper limb exercise training device and operation method thereof

Abstract

The invention provides an animal upper limb movement training device and an operation method thereof, and the device comprises a data collection module which is used for collecting behavior data of a target animal; the controller is used for generating a first control instruction according to the behavior data; the executing mechanism comprises a mechanical arm and a plurality of touch objects; the plurality of touch objects are located in a contactable range of the target animal; the mechanical arm is used for driving the target touch object to change the position and the moving track according to the first control instruction; and for each touch object, the touch object is used for sending feedback information to the controller under the condition of confirming that the target animal touches the target touch object so as to instruct the controller to allocate an award to the target animal. According to the device, the animal training task process can be adjusted in real time by collecting the macaque visual gazing information, the multi-joint point pose information and the task performance information, and the animal exercise training efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of robotic arm motion control, and particularly to an animal upper limb motion training device and an operation method thereof. Background Art

[0002] In the field of brain function research, non-human primates (such as macaques) are key experimental models for studying motor cognitive function, neural plasticity, and brain-computer interface technology due to their highly similar neural structures to humans.

[0003] However, the current animal behavior training system has a single function, lacks a dynamic adjustment strategy for the content and difficulty of training tasks, and does not provide timely feedback on the detected macaque behavior data during the task process, resulting in difficulties in the learning process of macaques, a single behavior strategy, and thus low efficiency of motion training. Summary of the Invention

[0004] The present invention provides an animal upper limb motion training device and an operation method thereof to solve the defect that the existing animal behavior training system has a single function and cannot dynamically adjust the training strategy, resulting in low efficiency of animal motion training; the device of the present invention improves the efficiency of animal motion training.

[0005] The present invention provides an animal upper limb motion training device, including: A data acquisition module for acquiring behavior data of a target animal, where the behavior data includes at least one of limb movement data and eye movement data; A controller electrically connected to the data acquisition module, and the controller is configured to generate a first control instruction according to the behavior data; An actuator electrically connected to the controller; the actuator includes a robotic arm and a plurality of touch objects; The plurality of touch objects are respectively mechanically connected to the robotic arm; the plurality of touch objects are within the reach of the target animal; The robotic arm is configured to drive a target touch object to change its position and movement trajectory according to the first control instruction; wherein, the target touch object belongs to the plurality of touch objects; For each touch object, the touch object is configured to send feedback information to the controller to indicate that the controller assigns a reward to the target animal when it is confirmed that the target animal touches the target touch object.

[0006] According to the animal upper limb motion training device provided by the present invention, the actuator further includes: An LED lamp installed within the visual field of the target animal, and the LED lamp is electrically connected to the controller; different lighting colors of the LED lamp correspond to different touch objects; The controller is further configured to send a second control instruction to the LED lamp to control the LED lamp to display a target lighting color, and send a third control instruction to the robotic arm to control the robotic arm to drive the target touch object corresponding to the target lighting color to change its position and movement trajectory; wherein, the target lighting color belongs to the different lighting colors.

[0007] According to an animal upper limb movement training device provided by the present invention, the touch object includes: A touch sensing device, which is installed at one end of the touch object close to the target animal; The touch sensing device is configured to generate the feedback information according to the target touch object and the time when the target animal touches the target touch object.

[0008] According to an animal upper limb movement training device provided by the present invention, the data acquisition module includes: An eye movement recording unit, which is configured to monitor the eye movement data of both eyes of the target animal in real time; An action capture unit, which is configured to monitor the upper limb joint point positions of the target animal and the three-dimensional spatial positions of the multiple touch objects in real time to obtain the limb movement data.

[0009] According to an animal upper limb movement training device provided by the present invention, the device further includes: A reward module, which is electrically connected to the controller, and the reward module is configured to provide water source or food for the target animal; The controller is further configured to send a fourth control instruction to the reward module to control the working state of the reward module.

[0010] The present invention also provides an operation method for an animal upper limb movement training device, including: Collecting the behavior data of the target animal through a data acquisition module, where the behavior data includes at least one of limb movement data and eye movement data; Generating a first control instruction by a controller according to the behavior data; Driving the target touch object to change its position and movement trajectory by the robotic arm of the actuator according to the first control instruction, and when it is confirmed that the target animal touches the target touch object by each touch object of the actuator, sending feedback information to the controller to instruct the controller to allocate rewards to the target animal; Wherein, each of the touch objects is mechanically connected to the robotic arm; each of the touch objects is within the reachable range of the target animal; the target touch object belongs to each of the touch objects.

[0011] According to an operation method of an animal upper limb movement training device provided by the present invention, the actuator further includes an LED lamp, the LED lamp is installed within the visual field of the target animal, and different lighting colors of the LED lamp correspond to different touch objects; When each touch object of the actuator confirms that the target animal touches the target touch object, the feedback information sent to the controller includes: When the LED lamp displays the target lighting color, based on the controller, control the robotic arm to drive the target touch object corresponding to the target lighting color to change its position and movement trajectory; When the target animal touches the target touch object within the specified time, generate the feedback information based on the target touch object and send the feedback information to the controller; wherein, the target lighting color belongs to the different lighting colors.

[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the operation method of the animal upper limb movement training device as described in any one of the above.

[0013] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the operation method of the animal upper limb movement training device as described in any one of the above.

[0014] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the operation method of the animal upper limb movement training device as described in any one of the above.

[0015] The animal upper limb movement training device and its operation method provided by the present invention collect the behavior data of the target animal through a data acquisition module, generate a first control instruction by a controller according to the behavior data, drive the target touch object to change its position and movement trajectory by an actuator according to the first control instruction, and send feedback information to the controller when it is confirmed that the target animal touches the target touch object, so as to instruct the controller to allocate rewards to the target animal. It can collect the visual fixation information, multi-joint pose information and task performance information of macaques, and adjust the animal training task process in real time, improving the animal movement training efficiency. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0017] Figure 1 It is one of the structural schematic diagrams of the animal upper limb movement training device provided by the present invention.

[0018] Figure 2 It is another structural schematic diagram of the animal upper limb movement training device provided by the present invention.

[0019] Figure 3 It is the schematic diagram of the operation process of the upper control machine provided by the present invention.

[0020] Figure 4 It is the schematic diagram of the operation process of the lower execution machine provided by the present invention.

[0021] Figure 5 It is the schematic diagram of the operation process of the motion capture unit provided by the present invention.

[0022] Figure 6 It is the schematic diagram of the operation method of the animal upper limb movement training device provided by the present invention.

[0023] Figure 7 It is the structural schematic diagram of the electronic device provided by the present invention.

[0024] Reference numerals: 100: Data acquisition module; 110: Eye movement recording unit; 120: Motion capture unit; 200: Controller; 300: Actuator; 310: Robot arm; 320: Touch object; 321: Touch sensing device; 330: LED lamp; 400: Reward module. Detailed implementation manners

[0025] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0026] The following will describe Figures 1-6 the animal upper limb movement training device and its operation method of the present invention.

[0027] The present invention provides an animal upper limb movement training device, including: a data acquisition module 100, a controller 200, an actuator 300, a robotic arm 310, and a touch object 320.

[0028] The data acquisition module 100 is used to acquire the behavior data of the target animal, and the behavior data includes at least one of limb movement data and eye movement data.

[0029] In this embodiment, the acquisition module may be an image or video acquisition device. For example, the acquisition module is a camera or an image recognition device with a camera function.

[0030] In this embodiment, the target animal includes non-human primates, such as macaques.

[0031] Taking the macaque as an example of the experimental object, by using the acquisition module to record data such as the upper limb movement of the macaque and the interaction behavior with the touch object 320, and real-time monitoring the three-dimensional spatial positions of each joint point of the upper limb of the macaque and the touch target, the trajectory, speed, and strength of the extension-grasp action can be accurately quantified, and thus the complexity of the movement trajectory and the magnitude of the movement speed of the actuator 300 for assisting training can be adjusted.

[0032] In this embodiment, by acquiring the eye movement data through the acquisition module, the fixation direction can be real-time monitored, and the visual attention distribution of the macaque during the execution of complex movement tasks can be quantified. The eye movement data can assist in judging whether the macaque adjusts the movement path through visual feedback (such as correcting the grasping angle after fixing on the target), providing behavioral evidence for understanding the "perception-action" closed loop, especially playing a significant role in multi-target selection tasks.

[0033] Optionally, the data acquisition module 100 includes: an eye movement recording unit 110, which is used to real-time monitor the eye movement data of the two eyes of the target animal; an action capture unit 120, which is used to real-time monitor the positions of the upper limb joint points of the target animal and the three-dimensional spatial positions of multiple touch objects 320 to obtain limb movement data.

[0034] In this embodiment, the controller 200 simultaneously receives the eye movement data and the limb movement data of the target animal, calculates the action fluency index (such as the variance of the joint movement angular velocity) through the limb movement data, and can adaptively adjust the training difficulty level (for example, adjusting the speed and deflection angle of the robotic arm 310, etc.). By dynamically adjusting the layout of the touch object 320 through the eye movement data (such as moving the object in the high-frequency fixation area farther away), the fit between the movement control of the robotic arm 310 and the animal training can be improved, and thus the accuracy of the animal upper limb movement training can be improved.

[0035] The controller 200 is electrically connected to the data acquisition module 100, and the controller 200 is configured to generate a first control instruction based on the behavioral data.

[0036] In this embodiment, the data acquisition module 100 collects in real time behavioral data such as the upper limb joint movement trajectories and touch target positions of the macaque, and transmits the data to the controller 200 through electrical signals. The controller 200 analyzes the data based on a preset algorithm (such as motion pattern recognition or neural network model) to generate a first control instruction.

[0037] In this embodiment, the first instruction may instruct the actuator 300 to adjust the position, speed, and movement trajectory.

[0038] The actuator 300 is electrically connected to the controller 200; the actuator 300 includes a robotic arm 310 and a plurality of touch objects 320; the plurality of touch objects 320 are respectively mechanically connected to the robotic arm; the plurality of touch objects 320 are within the reach of the target animal.

[0039] In this embodiment, the robotic arm 310 and the plurality of touch objects 320 may be detachably connected or fixedly connected. The robotic arm 310 may also be detachably connected to a part of the touch objects and fixedly connected to another part of the touch objects.

[0040] For example, the detachable connection may be by screw connection or by snap connection; the fixed connection may be welding or the like.

[0041] In this embodiment, the robotic arm 310 may include multiple degrees of freedom to ensure that the robotic arm 310 can move flexibly in three-dimensional space.

[0042] The robotic arm 310 is configured to drive the target touch object to change its position and movement trajectory according to the first control instruction; wherein, the target touch object belongs to the plurality of touch objects 320; for each touch object 320, the touch object 320 is configured to send feedback information to the controller 200 when it is confirmed that the target animal touches the target touch object, so as to instruct the controller 200 to allocate rewards to the target animal.

[0043] In this embodiment, when the controller 200 determines that the macaque is ready to grasp the target touch object based on the macaque's behavioral data, the controller 200 sends a first control instruction to the robotic arm 310. The robotic arm 310 moves to the designated position according to the first instruction along a preset movement path and drives the target touch object to move. When the sensing device installed on the actuator 300 detects that the macaque touches the touch object 320, a feedback information (such as the touched target object number) is generated and sent to the controller 200. When the controller 200 confirms that the feedback information matches the target touch object, the controller 200 allows a physical reward (providing food or water source) to the macaque to strengthen the macaque's motor learning behavior.

[0044] In this embodiment, when the controller 200 confirms that the feedback information does not match the target touch object, it does not allow a material reward to be given to the macaque, or continues to repeat the current movement operation until the macaque successfully touches the target touch object, and then provides a material reward to the macaque.

[0045] The animal upper limb movement training device provided by the embodiment of the present invention collects the behavioral data of the target animal through a data acquisition module, generates a first control instruction by the controller according to the behavioral data, drives the target touch object to change its position and movement trajectory by an actuator according to the first control instruction, and sends feedback information to the controller when it is confirmed that the target animal touches the target touch object, so as to instruct the controller to allocate rewards to the target animal. It can collect the visual fixation information, multi-joint pose information and task performance information of the macaque, and adjust the animal training task process in real time, improving the animal movement training efficiency.

[0046] Optionally, the actuator 300 further includes: an LED lamp 330, which is installed within the visual field of the target animal, and the LED lamp 330 is electrically connected to the controller 200; different lighting colors of the LED lamp 330 correspond to different touch objects 320; the controller 200 is further configured to send a second control instruction to the LED lamp 330 to control the LED lamp 330 to display the target lighting color, and send a third control instruction to the robotic arm 310 to control the robotic arm 310 to drive the target touch object corresponding to the target lighting color to change its position and movement trajectory; wherein, the target lighting color belongs to different lighting colors.

[0047] In this embodiment, the visual cue for the macaque's grasping process can be carried out through different lighting colors of the LED, that is, a color-object-reward ternary mapping mechanism is established to assist the macaque in accurately grasping the target touch object.

[0048] In this embodiment, the color-object-reward ternary mapping mechanism is set in the following manner: (1) The controller 200 generates a second control instruction, which can instruct the LED lamp 330 to randomly display the target lighting color or specify to display the target lighting color; the lighting colors of the LED lamp 330 include multiple types.

[0049] For example, the lighting colors of the LED lamp 330 can include red, green, blue, etc.

[0050] (2) The controller 200 generates a second control instruction, which instructs the robotic arm 310 to drive the touch object associated with the current lighting color to move.

[0051] In this embodiment, the association between the touch object and the lighting color can be set by color, shape or other identifiers.

[0052] For example, the colors of multiple touch objects correspond one-to-one with the colors that the LED lamp 330 can light up, or touch objects of different shapes correspond to different lighting colors.

[0053] (3) The robotic arm 310 controls the movement (changing the position, movement trajectory or speed) of the touch object 320 corresponding to the currently lit color. If the sensor detects that the macaque touches the touch object 320, feedback information is generated and sent to the controller 200. The controller 200 determines whether to assign a reward to the macaque according to the feedback information and the currently lit color.

[0054] The animal upper limb movement training device provided by the embodiment of the present invention, by setting different lighting colors of the LED lamp corresponding to different touch objects, controlling the LED lamp to display the target lighting color through the controller, and controlling the robotic arm to drive the target touch object corresponding to the target lighting color to change the position and movement trajectory, can provide visual cues for the movement training process of the target animal, and improve the accuracy of the target animal in grasping the correct touch object when performing tasks.

[0055] Optionally, the touch object 320 includes: a touch sensing device 321, and the touch sensing device 321 is installed at one end of the touch object 320 close to the target animal; the touch sensing device 321 is used to generate feedback information according to the target touch object and the time when the target animal touches the target touch object.

[0056] In this embodiment, the touch sensing device 321 can be a photoelectric sensor, and a corresponding photoelectric sensor is arranged on each touch object 320. The photoelectric sensor is used to generate feedback information according to the touch information between the macaque and the sensor.

[0057] In this embodiment, the touch information can be the pressure or touch time of the macaque on the touch object 320, and the touch information is used to determine whether the macaque effectively touches the target object.

[0058] For example, if the pressure of the macaque on the touch object 320 is less than the pressure threshold, it is determined that the macaque does not touch the target object; or, if the touch time between the macaque and the touch object 320 is less than the time threshold, it is determined that the macaque does not touch the target object; when the pressure of the macaque on the touch object 320 is greater than the pressure threshold and the touch time is greater than the time threshold, it is determined that the macaque touches the target object and corresponding feedback information is generated.

[0059] The animal upper limb movement training device provided by the embodiment of the present invention, by setting the touch sensing device to be installed at one end of the touch object close to the target animal and generating feedback information according to the target touch object and the time when the target animal touches the target touch object, improves the accuracy of detecting that the target animal successfully touches the touch object.

[0060] Optionally, the animal upper limb movement training device further includes: a reward module 400, which is electrically connected to the controller 200. The reward module 400 is used to provide water source or food for the target animal; the controller 200 is further used to send a fourth control instruction to the reward module 400 to control the working state of the reward module 400.

[0061] In this embodiment, the reward module 400 is deployed in the reachable area of the experimental subject to receive the fourth control instruction for adjusting the reward content.

[0062] In this embodiment, the reward module 400 can adopt a quantitative output mechanism driven by a micro servo motor, support water droplet injection or food particle release, and realize dose feedback control through a high-precision flow sensor and a photoelectric switch to ensure that the reward amount error is lower than the set error threshold.

[0063] In this embodiment, the working states of the reward module 400 include: (1) opening the water source slot and closing the food slot; (2) closing the water source slot and opening the food slot; (3) opening the water source slot and the food slot; (4) closing the water source slot and the food slot.

[0064] In this embodiment, the controller 200 generates a fourth instruction according to the feedback information (for example, the target object of interest is touched), and sets the following reward modes for the reward module 400: 1. Immediately release a preset dose of reward after the manipulator 310 completes the task; 2. Increase the reward amount according to the continuous number of task completions to strengthen the long-term learning effect.

[0065] In this embodiment, the reward module 400 dynamically adjusts the reward type (water source or food) and dose according to the generated fourth instruction to strengthen the positive behavior feedback of the target animal.

[0066] The animal upper limb movement training device provided by the embodiment of the present invention provides water source or food for the target animal through the reward module, and sets the reward module to receive the fourth control instruction to control the working state of the reward module, which can be flexibly adjusted according to experimental needs, improving the learning efficiency and task participation of the target animal.

[0067] Figure 2 It is the second structural schematic diagram of the animal upper limb movement training device provided by the present invention. In Figure 2 In the shown embodiment, an animal upper limb movement training device includes an upper control computer, a lower execution machine, and a data acquisition module.

[0068] In this embodiment, the upper control computer is the controller in the above embodiment; the lower execution machine includes the execution mechanism in the above embodiment.

[0069] Specifically, the upper control computer is responsible for controlling the task process, receiving the behavioral data fed back by the data acquisition module and the lower execution machine, and sending task instructions and reward instructions to the lower control machine; the data acquisition module is used to collect the behavioral data of the macaque during the task process and send it to the upper control computer. The data acquisition module includes an eye movement recording system (for real-time monitoring of the binocular eye movement information of the macaque) and a video motion capture system (for real-time monitoring of the three-dimensional spatial positions of the joints of the upper limbs of the macaque and the touch target); the lower execution machine includes: an LED lamp (for providing visual cues after receiving the task instructions from the upper control computer), a robotic arm module (for controlling the position and movement trajectory of the touch target after receiving the task instructions from the upper control computer), a touch sensing device (located inside the touch target, for monitoring the target object and time touched by the macaque and feeding back to the upper control computer), and a reward module (for providing a reward to the macaque once after receiving the reward instruction from the upper control computer).

[0070] Figure 3 is a schematic diagram of the operation process of the upper control computer provided by the present invention. In Figure 3 the illustrated embodiment, the operation process of the upper control computer includes: a. Set the initial training task parameters, including the total number of trials, the correct rate target, and the task type for this training.

[0071] b. The upper computer sends task control instructions to the lower execution machine, turning on the appropriate LED lights as visual cues to indicate the movement trajectory, speed, etc. of the robotic arm.

[0072] c. Receive the sensor data transmitted from the lower execution machine and determine whether the macaque touches the correct target.

[0073] d. When the macaque touches the correct target, send a reward instruction to the lower execution machine to control the amount of the reward.

[0074] e. According to the selection result of the macaque in the current trial, combined with the feedback of the eye movement information, hand and joint movement information of the macaque collected by the data acquisition module, adjust the task parameters of the next trial.

[0075] Among them, the adjusted parameters can include the complexity of the movement trajectory of the robotic arm, the magnitude of the movement speed, and the proportion of each candidate target in the visual cue, etc.

[0076] In this embodiment, the experimenter can also be on-site to monitor the behavioral performance of the macaque, analyze and adjust the task parameters, exit the current experimental program, and restart a new experimental program; compared with manual training, this embodiment can achieve an automated process of integrated feedback, analysis, and adjustment through the upper control computer, with a rapid response, saving personnel energy, and having a higher and more reliable fine degree of adjusting the training process, avoiding human beings as interference factors in the training.

[0077] f. Determine that the training volume or training objective is currently met, and exit the current training program.

[0078] Figure 4 It is a schematic diagram of the operation process of the lower-level execution machine provided by the present invention. In Figure 4 the illustrated embodiment, the operation process of the lower-level execution machine includes: a. According to the control instruction received from the upper-level control machine, operate the robotic arm to perform corresponding trajectory movement.

[0079] In this embodiment, the screen can also be used as the execution machine, with the cursor or pattern as the interaction object; the experimenter holds the item module to interact with the macaque; compared with the screen solution, this embodiment realizes the interaction of real objects through the lower-level execution machine, reduces the macaque's difficulty in understanding the task, and is more conducive to revealing the underlying natural and real neural mechanism.

[0080] b. After real-time collecting the movement trajectory data (corresponding behavior data) of the robotic arm, save it and feedback it to the upper-level control machine.

[0081] Figure 5 It is a schematic diagram of the operation process of the motion capture unit provided by the present invention. In Figure 5 the illustrated embodiment, the operation process of the motion capture unit includes: a. The motion capture unit receives the video frame data sent by the camera in real time, and detects the positions of each joint point in the image in real time and converts them into coordinates in three-dimensional space.

[0082] b. Save the joint pose data and feedback it to the upper-level control machine.

[0083] In this embodiment, the upper-level control machine sets the task parameter combination for this training. The task parameters include visual cues, target trajectories, and target movement speeds: the probabilities of the appearance of 2 visual cue categories are 50%-50%; the positions of the interaction targets are divided into 8 trajectories in space; the target moves back and forth on the trajectory with 2 speeds, fast and slow; the condition for giving the macaque a reward is that the macaque touches the target of the same color as the visual cue within the specified time; before each trial, a set of task parameters is randomly sampled and sent to the lower-level control machine. The lower-level control machine presents the task content according to the control instruction, collects the macaque's behavioral performance and feedbacks it to the upper-level control machine. The upper-level control machine judges whether to give a reward according to the result and adjusts the parameters of the next trial; if the macaque makes a mistake in the current trial, the next trial repeats the current parameters instead of randomly selecting.

[0084] Specifically, it can be stipulated that touching the target with the same color as the visual cue will receive a reward. The accuracy rate of the latest 50 trials is calculated in real time. When the accuracy rate reaches 80%, it is considered that the macaque has completed visual-motor association learning and exits the task program; or when the accuracy rate reaches 80%, the reward rule is reversed, that is, touching the target with a color different from the visual cue can receive a reward, encouraging the macaque to continue learning the reversed visual-motor association rule.

[0085] The operation method of the animal upper limb movement training device provided by the present invention will be described below. The operation method of the animal upper limb movement training device described below can be mutually referred to the animal upper limb movement training device described above.

[0086] Figure 6 It is a schematic flow chart of the operation method of the animal upper limb movement training device provided by the present invention. As Figure 6 shown, the operation method of the animal upper limb movement training device includes the following steps: Step 610: Collect the behavioral data of the target animal through the data collection module. The behavioral data includes at least one of limb movement data and eye movement data.

[0087] In this step, the collection module can be an image or video acquisition device. For example, the collection module is a camera or an image recognition device with a camera function.

[0088] In this embodiment, the target animal includes non-human primates, such as macaques.

[0089] Taking the macaque as an example of the experimental object, by recording the data of the macaque's upper limb movement and interaction behavior with the touch object through the collection module, the three-dimensional spatial positions of each joint point of the macaque's upper limb and the touch target can be monitored in real time, and the trajectory, speed and strength of the extension-grasp action can be accurately quantified, so as to adjust the complexity of the movement trajectory and the speed of the moving of the auxiliary training execution mechanism.

[0090] In this embodiment, by collecting the eye movement data through the collection module, the fixation direction can be monitored in real time, and the visual attention distribution of the macaque during the execution of complex movement tasks can be quantified. The eye movement data can assist in judging whether the macaque adjusts the movement path through visual feedback (such as correcting the grasping angle after fixing on the target), providing behavioral evidence for understanding the "perception-action" closed loop, especially playing a significant role in multi-target selection tasks.

[0091] Step 620: Generate a first control instruction according to the behavioral data through the controller.

[0092] In this step, the data acquisition module collects in real time the behavioral data such as the upper limb joint movement trajectory and the touch target position of the macaque, and transmits the data to the controller through electrical signals. The controller analyzes the data based on a preset algorithm (such as motion pattern recognition or neural network model) to generate a first control instruction.

[0093] In this embodiment, the first instruction may instruct the actuator to adjust the position, speed, and movement trajectory.

[0094] Step 630: The robotic arm of the actuator drives the target touch object to change its position and movement trajectory according to the first control instruction. When each touch object of the actuator confirms that the target animal touches the target touch object, it sends feedback information to the controller to instruct the controller to allocate a reward to the target animal; wherein, each touch object is mechanically connected to the robotic arm; each touch object is within the reach of the target animal; the target touch object belongs to each touch object.

[0095] In this step, the robotic arm and the multiple touch objects may be detachably connected or fixedly connected. The robotic arm may also be detachably connected to a part of the touch objects and fixedly connected to another part of the touch objects.

[0096] For example, the detachable connection may be by screw connection or by snap connection; the fixed connection may be welding, etc.

[0097] In this embodiment, the robotic arm may include multiple degrees of freedom to ensure the flexible movement of the robotic arm in three-dimensional space.

[0098] In this embodiment, when the controller determines from the behavioral data of the macaque that the macaque is ready to grasp the target touch object, it sends a first control instruction to the robotic arm. The robotic arm moves to the designated position according to the first instruction along a preset movement path and drives the target touch object to move. When the sensing device installed on the actuator detects that the macaque touches the touch object, it generates feedback information (such as the number of the touched target object) and sends it to the controller. When the controller confirms that the feedback information matches the target touch object, it allows a material reward (providing food or water source) to the macaque to strengthen the macaque's motor learning behavior.

[0099] In this embodiment, when the controller confirms that the feedback information does not match the target touch object, it does not allow a material reward to the macaque, or continues to repeat the current movement operation until the macaque successfully touches the target touch object and provides a material reward to the macaque.

[0100] The operation method of the animal upper limb movement training device provided by the embodiment of the present invention collects the behavior data of the target animal through the data acquisition module, generates a first control instruction by the controller according to the behavior data, drives the target touch object to change the position and movement trajectory by the actuator according to the first control instruction, and sends feedback information to the controller when it is confirmed that the target animal touches the target touch object, so as to instruct the controller to allocate rewards to the target animal. It can collect the visual fixation information, multi-joint pose information and task performance information of the macaque, and adjust the animal training task process in real time, improving the animal movement training efficiency.

[0101] Optionally, the actuator further includes an LED lamp, which is installed within the visual field of the target animal, and different lighting colors of the LED lamp correspond to different touch objects; when each touch object of the actuator confirms that the target animal touches the target touch object, sending feedback information to the controller includes: when the LED lamp shows the target lighting color, based on the controller's control, the robotic arm drives the target touch object corresponding to the target lighting color to change the position and movement trajectory; when the target animal touches the target touch object within the specified time, generating feedback information based on the target touch object and sending the feedback information to the controller; where the target lighting color belongs to different lighting colors.

[0102] In this embodiment, the visual cue for the macaque's grasping process can be carried out through different lighting colors of the LED, that is, establishing a color-object-reward ternary mapping mechanism to assist the macaque in accurately grasping the target touch object.

[0103] In this embodiment, the color-object-reward ternary mapping mechanism is set in the following way: (1) The controller generates a second control instruction, which can instruct the LED lamp to randomly display the target lighting color or specify the display of the target lighting color; the lighting colors of the LED lamp include multiple kinds.

[0104] For example, the lighting colors of the LED lamp can include red, green and blue, etc.

[0105] (2) The controller generates a second control instruction, which instructs the robotic arm to drive the touch object associated with the current lighting color to move.

[0106] In this embodiment, the association between the touch object and the lighting color can be set through color, shape or other identifiers.

[0107] For example, the colors of multiple touch objects correspond one-to-one with the lighting colors that the LED lamp can show, or different-shaped touch objects correspond to different lighting colors.

[0108] (3) The manipulator controls the movement (changing the position, movement trajectory or speed) of the touch object corresponding to the currently lit color. If the sensor detects that the macaque touches the touch object, feedback information is generated and sent to the controller, and the controller determines whether to allocate a reward to the macaque according to the feedback information and the currently lit color.

[0109] The operation method of the animal upper limb movement training device provided by the embodiment of the present invention can visually prompt the movement training process of the target animal by setting different lit colors of the LED lamps corresponding to different touch objects, controlling the LED lamps by the controller to display the target lit color, and controlling the manipulator to drive the target touch object corresponding to the target lit color to change the position and movement trajectory, thereby improving the accuracy of the target animal in grasping the correct touch object when performing tasks.

[0110] Figure 7 An example of a schematic physical structure diagram of an electronic device is shown as Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730, and a communication bus 740. Among them, the processor 710, the communication interface 720, and the memory 730 complete communication with each other through the communication bus 740. The processor 710 can call the logical instructions in the memory 730 to execute the operation method of the animal upper limb movement training device. The method includes: collecting the behavior data of the target animal through a data acquisition module, where the behavior data includes at least one of limb movement data and eye movement data; generating a first control instruction according to the behavior data by the controller; driving the target touch object to change the position and movement trajectory according to the first control instruction by the manipulator of the actuator, and when it is confirmed that the target animal touches the target touch object by each touch object of the actuator, sending feedback information to the controller to instruct the controller to allocate a reward to the target animal; where each touch object is mechanically connected to the manipulator; each touch object is within the reachable range of the target animal; the target touch object belongs to each touch object.

[0111] In addition, when the logical instructions in the above-mentioned memory 730 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this 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 for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0112] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the operation method of the animal upper limb movement training device provided by the above-mentioned various methods. The method includes: collecting the behavior data of the target animal through a data acquisition module, where the behavior data includes at least one of limb movement data and eye movement data; generating a first control instruction by a controller according to the behavior data; driving a target touch object to change its position and movement trajectory by a robotic arm of an execution mechanism, and when it is confirmed that the target animal touches the target touch object through each touch object of the execution mechanism, sending feedback information to the controller to instruct the controller to allocate rewards to the target animal; where each touch object is mechanically connected to the robotic arm respectively; each touch object is within the reachable range of the target animal; the target touch object belongs to each touch object.

[0113] On another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes the operation method of the animal upper limb movement training device provided by the above-mentioned various methods. The method includes: collecting the behavior data of the target animal through a data acquisition module, where the behavior data includes at least one of limb movement data and eye movement data; generating a first control instruction by a controller according to the behavior data; driving a target touch object to change its position and movement trajectory by a robotic arm of an execution mechanism, and when it is confirmed that the target animal touches the target touch object through each touch object of the execution mechanism, sending feedback information to the controller to instruct the controller to allocate rewards to the target animal; where each touch object is mechanically connected to the robotic arm respectively; each touch object is within the reachable range of the target animal; the target touch object belongs to each touch object.

[0114] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

[0115] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, 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 enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An animal upper limb movement training device, characterized in that, Comprising: A data acquisition module for acquiring the behavior data of a target animal, where the behavior data includes at least one of limb movement data and eye movement data; A controller electrically connected to the data acquisition module, the controller being configured to generate a first control instruction according to the behavior data; An actuator electrically connected to the controller; the actuator includes a robotic arm and a plurality of touch objects; The plurality of touch objects are respectively mechanically connected to the robotic arm; the plurality of touch objects are within the touchable range of the target animal; The robotic arm is configured to drive a target touch object to change its position and movement trajectory according to the first control instruction; wherein the target touch object belongs to the plurality of touch objects; For each touch object, the touch object is configured to send feedback information to the controller when it is confirmed that the target animal touches the target touch object, so as to instruct the controller to allocate a reward to the target animal.

2. The animal upper limb movement training device according to claim 1, characterized in that, The actuator further includes: An LED lamp installed within the visual field of the target animal, the LED lamp being electrically connected to the controller; different lighting colors of the LED lamp correspond to different touch objects; The controller is further configured to send a second control instruction to the LED lamp to control the LED lamp to display a target lighting color, and send a third control instruction to the robotic arm to control the robotic arm to drive the target touch object corresponding to the target lighting color to change its position and movement trajectory; wherein the target lighting color belongs to the different lighting colors.

3. The animal upper limb movement training device according to claim 1, characterized in that, The touch object includes: A touch sensing device installed at one end of the touch object close to the target animal; The touch sensing device is configured to generate the feedback information according to the target touch object and the time when the target animal touches the target touch object.

4. The animal upper limb movement training device according to claim 1, characterized in that The data acquisition module includes: An eye movement recording unit for real-time monitoring of the eye movement data of both eyes of the target animal; An action capture unit for real-time monitoring of the upper limb joint point positions of the target animal and the three-dimensional spatial positions of the plurality of touch objects to obtain the limb movement data.

5. The animal upper limb movement training device according to claim 1, characterized in that, The device further includes: A reward module electrically connected to the controller, the reward module being configured to provide water source or food for the target animal; The controller is further configured to send a fourth control instruction to the reward module to control the working state of the reward module.

6. A running method of an animal upper limb movement training device, characterized in that, Comprising: Acquiring the behavior data of a target animal through a data acquisition module, where the behavior data includes at least one of limb movement data and eye movement data; Generating a first control instruction according to the behavior data through a controller; Driving a target touch object to change its position and movement trajectory according to the first control instruction by the robotic arm of the actuator, and sending feedback information to the controller by each touch object of the actuator when it is confirmed that the target animal touches the target touch object, so as to instruct the controller to allocate a reward to the target animal; Wherein, each of the touch objects is mechanically connected to the robotic arm; each of the touch objects is within the reach of the target animal; the target touch object belongs to the touch objects.

7. The operating method of the animal upper limb movement training device according to claim 6, characterized in that, The actuator further includes an LED lamp, the LED lamp is installed within the visual field of the target animal, and different lighting colors of the LED lamp correspond to different touch objects; When each of the touch objects of the actuator confirms that the target animal touches the target touch object, the feedback information sent to the controller includes: When the LED lamp shows the target lighting color, based on the controller, control the robotic arm to drive the target touch object corresponding to the target lighting color to change its position and movement trajectory; When the target animal touches the target touch object within the specified time, generate the feedback information based on the target touch object and send the feedback information to the controller; wherein, the target lighting color belongs to the different lighting colors.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, wherein, When the processor executes the computer program, it implements the operation method of the animal upper limb movement training device according to any one of claims 6 to 7.

9. A non-transitory computer-readable storage medium storing a computer program thereon, characterized in that, When the computer program is executed by the processor, it implements the operation method of the animal upper limb movement training device according to any one of claims 6 to 7.

10. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the operation method of the animal upper limb movement training device according to any one of claims 6 to 7.

Images