Hospital service robot walking speed control system based on smart medical treatment

Abstract

The invention discloses a hospital service robot walking speed control system based on intelligent medical treatment, relates to the technical field of intelligent medical treatment, and discloses a mobile shooting module, a constant speed adjusting module and a speed control module. The default set speed of the hospital service robot can be adjusted according to the front video and the rear video, the default speed of the hospital service robot is reasonably adjusted according to the actual situation of pedestrians in a hospital on the basis of ensuring the service efficiency of the hospital service robot, and a speed control module is arranged; meanwhile, the moving speed of the hospital service robot is controlled and adjusted in real time according to the front video and the rear video by referring to the front and the rear of the hospital service robot.

Description

Technical Field

[0001] The present invention relates to the field of smart medical technology, and more specifically, to a walking speed control system of a hospital service robot based on smart medical care. Background Art

[0002] Smart healthcare creates a regional medical information platform for health records and uses the most advanced Internet of Things technology to achieve interaction between patients and medical staff, medical institutions, and medical equipment, gradually achieving informatization. With the development of smart healthcare, more and more hospitals are using service robots to deliver and pick up medicines for patients and medical staff in the hospital. However, current hospital service robots only consider pedestrians in front of them when walking, which can easily lead to collisions with pedestrians behind them without noticing. Summary of the invention

[0003] In view of the deficiencies in the prior art, the object of the present invention is to provide a walking speed control system for a hospital service robot based on smart medical care.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A walking speed control system for a hospital service robot based on smart medical care, comprising a mobile shooting module, a constant speed adjustment module, and a speed control module;

[0006] The mobile shooting module is used to control the hospital service robot to move in the hospital based on a default set speed, and to shoot the front and rear of the hospital service robot while moving, so as to obtain the front video and the rear video;

[0007] The fixed speed adjustment module is used to adjust the default set speed of the hospital service robot, specifically:

[0008] Convert both the front video and the rear video into video image frames, use the video image frames as input data of the walking detection model, mark the image label of the output data of the walking detection model as the pedestrian distance value, set the pedestrian distance threshold to Sz, and when the pedestrian distance value ≥ the pedestrian distance threshold Sz, do not process it. When the pedestrian distance value < the pedestrian distance threshold Sz, mark the pedestrian distance value as a dangerous distance value, obtain the constant speed adjustment value Kc, set the constant speed adjustment high value to Fb, set the constant speed adjustment low value to Qw, when the constant speed adjustment value Kc ≥ the constant speed adjustment high value Fb, adjust the default setting speed of the hospital service robot downward, when the constant speed adjustment low value Qw ≤ the constant speed adjustment value Kc < the constant speed adjustment high value Fb, do not adjust the default setting speed of the hospital service robot, and when the constant speed adjustment value Kc < the constant speed adjustment low value Qw, adjust the default setting speed of the hospital service robot upward;

[0009] The speed control module is used to control and adjust the moving speed of the hospital service robot, specifically:

[0010] Obtain all speed judgment values ​​Gd of the hospital service robot n seconds before the current time of the system, sort all speed judgment values ​​in chronological order, calculate the difference between the adjacent next speed judgment value Gd and the previous speed judgment value Gd after sorting, and obtain the speed judgment variable value. When the speed judgment variable value is greater than 0, mark the speed judgment variable value as a speed judgment increase value, and obtain the judgment increment value Ms. When the speed judgment variable value is less than 0, mark the speed judgment variable value as a speed judgment decrease value, and obtain the judgment decrease value Cy. When the speed judgment variable value = 0, do nothing, obtain the speed control value Uj, set the speed control upper value to Yw, and set the speed control lower value to Vt. When the speed control value Uj ≥ the speed control upper value Yw, accelerate the hospital service robot. When the speed control lower value Vt ≤ the speed control value Uj < the speed control upper value Yw, maintain the current movement speed of the hospital service robot. When the speed control value Uj < the speed control lower value Vt, decelerate the hospital service robot.

[0011] Furthermore, the walking detection model is obtained through the following steps: obtaining multiple video image frames, marking the video image frames as training images, assigning image labels to the training images, dividing the training images into training sets and validation sets according to a set ratio, constructing a neural network model, iteratively training the neural network model through the training set and the validation set, and when the number of iterative training is greater than the iteration number threshold, it is determined that the neural network model has completed training, and the trained neural network model is marked as a walking detection model. The larger the image label value of the walking detection model output data, the farther the distance of the pedestrian in the corresponding video image frame.

[0012] Furthermore, the constant speed adjustment value Kc is obtained by the following steps: marking all the video image frames of the front video of the hospital service robot before the current time of the system as the front video frames, obtaining the total number of times Dw in which the pedestrian distance value in the front video frame is marked as the dangerous distance value, sorting the front video frames corresponding to the dangerous distance value in chronological order, calculating the time difference between the times corresponding to the two adjacent front video frames after sorting, obtaining the front dangerous interval, summing up all the front dangerous intervals and taking the average, obtaining the average front dangerous interval, and marking it as Lp; marking all the video image frames of the rear video of the hospital service robot before the current time of the system as the rear video frames, obtaining the total number of times Bn in which the pedestrian distance value in the rear video frame is marked as the dangerous distance value, sorting the rear video frames corresponding to the dangerous distance value in chronological order, calculating the time difference between the times corresponding to the two adjacent rear video frames after sorting, obtaining the rear dangerous interval, summing up all the rear dangerous intervals and taking the average, obtaining the average rear dangerous interval, and marking it as Ac, using the formula The constant speed adjustment value Kc is obtained, wherein a1 is the front danger distance frequency coefficient, a2 is the average front danger interval coefficient, a3 is the rear danger distance frequency coefficient, and a4 is the average rear danger interval coefficient.

[0013] Furthermore, the speed judgment value Gd is obtained by the following steps: obtaining the front video and the rear video n seconds before the current time of the system, performing difference calculation on the pedestrian distance value of the front video and the pedestrian distance value of the rear video at the same time, obtaining the speed judgment value, and marking it as Gd.

[0014] Furthermore, the judgment value Ms is obtained by the following steps: summing up all the speed judgment appreciations to obtain the total speed judgment appreciation, and marking it as Bt; obtaining the speed judgment variable value marked as the total number of speed judgment appreciations, and marking it as Kq; and using the formula Ms=Bt×b1+Kq×b2 to obtain the judgment value Ms, wherein b1 is the total speed judgment appreciation coefficient, and b2 is the speed judgment appreciation quantity coefficient.

[0015] Furthermore, the speed reduction value Cy is obtained by the following steps: taking the absolute values ​​of all the speed reduction values ​​and then summing them up to obtain the total speed reduction value, which is marked as Gm; obtaining the speed variable value marked as the total number of speed reduction values, which is marked as Xp; and using the formula Cy=Gm×c1+Xp×c2 to obtain the speed reduction value Cy, where c1 is the total speed reduction coefficient and c2 is the speed reduction quantity coefficient.

[0016] Furthermore, the speed control value Uj is obtained by the following steps: the speed control value Uj is obtained by using the formula Uj=Ms×d1-Cy×d2, wherein d1 is the value-added coefficient and d2 is the value-reduced coefficient.

[0017] Compared with the prior art, the present invention has the following beneficial effects:

[0018] 1. Set up a fixed speed adjustment module and a mobile shooting module, which can adjust the default setting speed of the hospital service robot according to the front video and the rear video. On the basis of ensuring the service efficiency of the hospital service robot, the default speed of the hospital service robot can be rationally adjusted according to the actual situation of pedestrians in the hospital;

[0019] 2. Set up a speed control module, and refer to the front and back of the hospital service robot at the same time, and control and adjust the moving speed of the hospital service robot in real time according to the front video and the rear video. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a principle block diagram of the constant speed adjustment module of the present invention;

[0021] Figure 2 It is a principle block diagram of the speed control module of the present invention. DETAILED DESCRIPTION

[0022] Example 1

[0023] Reference Figure 1 , a walking speed control system of a hospital service robot based on smart medical care, including a mobile shooting module and a constant speed adjustment module.

[0024] The mobile shooting module is used to control the movement of the hospital service robot in the hospital based on the default set speed, and to capture the front and rear of the hospital service robot while moving, so as to obtain the front video and the rear video.

[0025] The fixed speed adjustment module is used to adjust the default set speed of the hospital service robot, specifically:

[0026] The front video and the rear video are converted into video image frames, the video image frames are used as input data of the walking detection model, and the image labels of the output data of the walking detection model are marked as pedestrian distance values. The walking detection model is obtained through the following steps: obtaining multiple video image frames, marking the video image frames as training images, assigning image labels to the training images, dividing the training images into training sets and validation sets according to a set ratio, constructing a neural network model, iteratively training the neural network model through the training set and the validation set, and when the number of iterative training is greater than the iteration number threshold, it is determined that the neural network model has completed training, and the trained neural network model is marked as a walking detection model. The larger the image label value of the output data of the walking detection model, the farther the distance of the pedestrian in the corresponding video image frame. The larger the image label value of the video image frame of the front video, the farther the pedestrian in the video image frame is from the hospital service robot. Set the pedestrian distance threshold to Sz. When the pedestrian distance value is ≥ the pedestrian distance threshold Sz, no processing is performed. When the pedestrian distance value is < the pedestrian distance threshold Sz, the pedestrian distance value is marked as a dangerous distance value, and the constant speed adjustment value Kc is obtained. The constant speed adjustment value Kc is obtained by the following steps: mark all the video image frames of the front video of the hospital service robot before the current time of the system as front video frames, obtain the total number of times Dw in which the pedestrian distance value in the front video frame is marked as a dangerous distance value, sort the front video frames corresponding to the dangerous distance value in chronological order, calculate the time difference between the times corresponding to the two adjacent front video frames after sorting, and obtain Get the front danger interval, sum up all the front danger intervals and take the average, get the average front danger interval, and mark it as Lp, mark all the video image frames of the rear video of the hospital service robot before the current time of the system as rear video frames, get the total number of times Bn that the pedestrian distance value in the rear video frame is marked as the danger distance value, sort the rear video frames corresponding to the danger distance value in chronological order, calculate the time difference between the time corresponding to the two adjacent rear video frames after sorting, get the rear danger interval, sum up all the rear danger intervals and take the average, get the average rear danger interval, and mark it as Ac, use the formula The constant speed adjustment value Kc is obtained, where a1 is the coefficient of the number of front-danger distances, a2 is the average coefficient of the front-danger interval, a3 is the coefficient of the number of rear-danger distances, and a4 is the average coefficient of the rear-danger interval. The value of a1 is 0.83, the value of a2 is 0.57, the value of a3 is 0.82, and the value of a4 is 0.56. The constant speed adjustment high value is set to Fb, and the constant speed adjustment low value is set to Qw. When the constant speed adjustment value Kc ≥ the constant speed adjustment high value Fb, the default setting speed of the hospital service robot is lowered. When the constant speed adjustment low value Qw ≤ the constant speed adjustment value Kc < the constant speed adjustment high value Fb, the default setting speed of the hospital service robot is not adjusted. When the constant speed adjustment value Kc < the constant speed adjustment low value Qw, the default setting speed of the hospital service robot is increased. For example, if the default speed setting of the hospital service robot is 0.5m / s, when the constant speed adjustment value Kc of the hospital service robot is greater than or equal to the constant speed adjustment high value Fb, the default speed setting of the hospital service robot is adjusted to below 0.5m / s, and the system can preset the adjustment range. By setting the constant speed adjustment module and the mobile shooting module, the default speed setting of the hospital service robot can be adjusted according to the front video and the rear video. On the basis of ensuring the service efficiency of the hospital service robot, the default speed of the hospital service robot can be rationally adjusted according to the actual situation of the pedestrians in the hospital.

[0027] Example 2

[0028] Reference Figure 2 On the basis of Example 2, it also includes a speed control module, which is used to control and adjust the moving speed of the hospital service robot, specifically:

[0029] All speed judgment values ​​Gd of the hospital service robot n seconds before the current system time are obtained. The speed judgment value Gd is obtained through the following steps: obtain the front video and the rear video n seconds before the current system time, calculate the difference between the pedestrian distance value of the front video and the pedestrian distance value of the rear video at the same time, obtain the speed judgment value, and mark it as Gd. All speed judgment values ​​are sorted in chronological order, and the difference between the adjacent next speed judgment value Gd and the previous speed judgment value Gd after sorting is calculated to obtain the speed judgment variable value. When the speed judgment variable value is greater than 0, the speed judgment variable value is marked as the speed judgment increase value to obtain the judgment value Ms. The judgment value Ms is obtained by the following steps: all the speed judgment increases are summed to obtain the total speed judgment increase value, which is marked as Bt, the speed judgment variable value is marked as the total number of speed judgment increases, which is marked as Kq, and the judgment value Ms is obtained using the formula Ms=Bt×b1+Kq×b2, wherein b1 is the total speed judgment increase coefficient, b2 is the speed judgment increase quantity coefficient, the value of b1 is 0.71, and the value of b2 is 0.38. When the speed judgment variable value is less than 0, the speed judgment variable value is marked as a speed judgment reduction value, and the judgment reduction value Cy is obtained. The judgment reduction value Cy is obtained by the following steps: taking the absolute values ​​of all the speed judgment reduction values ​​and then summing them up to obtain the total speed judgment reduction value, which is marked as Gm; the speed judgment variable value is obtained as the total number of speed judgment reduction values, which is marked as Xp; the judgment reduction value Cy is obtained using the formula Cy=Gm×c1+Xp×c2, wherein c1 is the total speed judgment reduction coefficient, and c2 is the speed judgment reduction quantity coefficient. The value of c1 is 0.72, and the value of c2 is 0.37. When the speed variable value is 0, no processing is performed, and the speed control value Uj is obtained. The speed control value Uj is obtained by the following steps: The speed control value Uj is obtained by using the formula Uj = Ms × d1-Cy × d2, where d1 is the value-added coefficient, d2 is the value-reduced coefficient, d1 is 0.65, and d2 is 0.64. Set the speed control upper value to Yw, and set the speed control lower value to Vt. When the speed control value Uj ≥ the speed control upper value Yw, the hospital service robot is accelerated. When the speed control lower value Vt ≤ the speed control value Uj < the speed control upper value Yw, the current movement speed of the hospital service robot is maintained. When the speed control value Uj < the speed control lower value Vt, the hospital service robot is decelerated. Set the speed control module, and refer to the front and rear of the hospital service robot at the same time, and control and adjust the movement speed of the hospital service robot in real time according to the front video and the rear video.

[0030] Working principle:

[0031] The fixed speed adjustment module and the mobile shooting module can be set to adjust the default speed of the hospital service robot according to the front video and the rear video. On the basis of ensuring the service efficiency of the hospital service robot, the default speed of the hospital service robot can be rationally adjusted according to the actual situation of the pedestrians in the hospital. The speed control module is set to refer to the front and rear of the hospital service robot at the same time, and the moving speed of the hospital service robot can be controlled and adjusted in real time according to the front video and the rear video.

[0032] The above is only a preferred embodiment of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of this template.

[0033] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A walking speed control system for a hospital service robot based on smart medical care, characterized in that: It includes a mobile shooting module, a constant speed adjustment module, and a speed control module; The mobile shooting module is used to control the hospital service robot to move in the hospital based on a default set speed, and to shoot the front and rear of the hospital service robot while moving, so as to obtain the front video and the rear video; The fixed speed adjustment module is used to adjust the default setting speed of the hospital service robot, specifically: Convert both the front video and the rear video into video image frames, use the video image frames as input data of the walking detection model, mark the image label of the output data of the walking detection model as the pedestrian distance value, set the pedestrian distance threshold to Sz, and when the pedestrian distance value ≥ the pedestrian distance threshold Sz, do not process it. When the pedestrian distance value < the pedestrian distance threshold Sz, mark the pedestrian distance value as a dangerous distance value, obtain the constant speed adjustment value Kc, set the constant speed adjustment high value to Fb, set the constant speed adjustment low value to Qw, when the constant speed adjustment value Kc ≥ the constant speed adjustment high value Fb, adjust the default setting speed of the hospital service robot downward, when the constant speed adjustment low value Qw ≤ the constant speed adjustment value Kc < the constant speed adjustment high value Fb, do not adjust the default setting speed of the hospital service robot, and when the constant speed adjustment value Kc < the constant speed adjustment low value Qw, adjust the default setting speed of the hospital service robot upward; The speed control module is used to control and adjust the moving speed of the hospital service robot, specifically: Obtain all speed judgment values ​​Gd of the hospital service robot n seconds before the current time of the system, sort all speed judgment values ​​in chronological order, calculate the difference between the adjacent next speed judgment value Gd and the previous speed judgment value Gd after sorting, and obtain the speed judgment variable value. When the speed judgment variable value is greater than 0, mark the speed judgment variable value as a speed judgment increase value, and obtain the judgment increment value Ms. When the speed judgment variable value is less than 0, mark the speed judgment variable value as a speed judgment decrease value, and obtain the judgment decrease value Cy. When the speed judgment variable value = 0, do nothing, obtain the speed control value Uj, set the speed control upper value to Yw, and set the speed control lower value to Vt. When the speed control value Uj ≥ the speed control upper value Yw, accelerate the hospital service robot. When the speed control lower value Vt ≤ the speed control value Uj < the speed control upper value Yw, maintain the current movement speed of the hospital service robot. When the speed control value Uj < the speed control lower value Vt, decelerate the hospital service robot.

2. According to claim 1, a hospital service robot walking speed control system based on smart medical care is characterized in that: The walking detection model is obtained through the following steps: obtaining multiple video image frames, marking the video image frames as training images, assigning image labels to the training images, dividing the training images into training sets and validation sets according to a set ratio, building a neural network model, iteratively training the neural network model through the training set and the validation set, and when the number of iterative training is greater than the iteration number threshold, it is determined that the neural network model has completed training, and the trained neural network model is marked as a walking detection model. The larger the image label value of the walking detection model output data, the farther the distance of the pedestrian in the corresponding video image frame.

3. According to claim 2, a hospital service robot walking speed control system based on smart medical care is characterized in that: The constant speed adjustment value Kc is obtained by the following steps: marking all the video image frames of the front video of the hospital service robot before the current time of the system as the front video frames, obtaining the total number of times Dw in which the pedestrian distance value in the front video frame is marked as the dangerous distance value, sorting the front video frames corresponding to the dangerous distance value in chronological order, calculating the time difference between the time corresponding to the two adjacent front video frames after sorting, obtaining the front dangerous interval, summing up all the front dangerous intervals and taking the average, obtaining the average front dangerous interval, and marking it as Lp; marking all the video image frames of the rear video of the hospital service robot before the current time of the system as the rear video frames, obtaining the total number of times Bn in which the pedestrian distance value in the rear video frame is marked as the dangerous distance value, sorting the rear video frames corresponding to the dangerous distance value in chronological order, calculating the time difference between the time corresponding to the two adjacent rear video frames after sorting, obtaining the rear dangerous interval, summing up all the rear dangerous intervals and taking the average, obtaining the average rear dangerous interval, and marking it as Ac, using the formula The constant speed adjustment value Kc is obtained, wherein a1 is the front danger distance frequency coefficient, a2 is the average front danger interval coefficient, a3 is the rear danger distance frequency coefficient, and a4 is the average rear danger interval coefficient.

4. According to claim 3, a hospital service robot walking speed control system based on smart medical care is characterized in that: The speed judgment value Gd is obtained by the following steps: obtaining the front video and the rear video n seconds before the current time of the system, performing difference calculation on the pedestrian distance value of the front video and the pedestrian distance value of the rear video at the same time, obtaining the speed judgment value, and marking it as Gd.

5. According to claim 4, a hospital service robot walking speed control system based on smart medical care is characterized in that: The judgment value added Ms is obtained by the following steps: summing up all the speed judgment appreciations to obtain the total speed judgment appreciation, and marking it as Bt; obtaining the speed judgment variable value and marking it as the total number of speed judgment appreciations, and marking it as Kq; and using the formula Ms=Bt×b1+Kq×b2 to obtain the judgment value added Ms, wherein b1 is the total speed judgment appreciation coefficient, and b2 is the speed judgment appreciation quantity coefficient.

6. A walking speed control system for a hospital service robot based on smart medical care according to claim 5, characterized in that: The speed reduction value Cy is obtained by the following steps: taking the absolute values ​​of all the speed reduction values ​​and then summing them up to obtain the total speed reduction value, which is marked as Gm; obtaining the speed variable value marked as the total number of speed reduction values, which is marked as Xp; and using the formula Cy=Gm×c1+Xp×c2 to obtain the speed reduction value Cy, where c1 is the total speed reduction coefficient and c2 is the speed reduction quantity coefficient.

7. A walking speed control system for a hospital service robot based on smart medical care according to claim 6, characterized in that: The speed control value Uj is obtained by the following steps: The speed control value Uj is obtained by using the formula Uj=Ms×d1-Cy×d2, where d1 is the value-added coefficient and d2 is the value-reduced coefficient.

Images