Medical robot adaptive motion control and obstacle avoidance method and system

Abstract

The application discloses a medical robot adaptive motion control and obstacle avoidance method and system, which identifies and classifies obstacles in the sensing range around the robot; for different categories of obstacles, corresponding motion prediction models are used for trajectory prediction; a bypass path is planned based on the obstacle classification results and the output of the corresponding prediction model; the maximum travel speed of the robot is dynamically adjusted based on the current environment complexity index; hierarchical emergency stop control is executed: when an unclassified obstacle is detected within a first distance range, deceleration stop is executed; when an unidentified obstacle suddenly appears within a second distance range smaller than the first distance on the travel path, emergency braking is executed. In the application, obstacles within the current position range of the robot are identified and classified, and the maximum travel speed of the robot is dynamically adjusted through environment complexity analysis, thereby ensuring the safety of the robot operation in a medical environment.

Description

Technical Field

[0001] This invention relates to the field of robot motion control technology, specifically to a method and system for adaptive motion control and obstacle avoidance of robots for medical applications. Background Technology

[0002] POCT robots face unique challenges in autonomous movement within a hospital environment: 1. Dynamic high-density pedestrian flow: Hospital corridors and emergency rooms have dense and unpredictable pedestrian flow, which traditional SLAM path planning algorithms cannot handle.

[0003] 2. Special obstacles: Hospital beds, wheelchairs, IV stands, emergency equipment, etc. come in various shapes and sizes and may be moved quickly by medical staff.

[0004] 3. Safety-sensitive scenarios: The robot must be absolutely safe, as any collision could injure the patient, and speed control needs to be extremely conservative.

[0005] 4. Multi-task priority scheduling: Emergency calls take precedence over regular rounds, and the robot needs to dynamically adjust the task queue and path.

[0006] 5. Passing through narrow spaces: ICU beds are close together, and robots need to accurately determine whether they can pass through.

[0007] 6. Complex ground conditions: Hospital floors may have slopes, thresholds, and slippery areas, requiring stable posture control. Summary of the Invention

[0008] To address the aforementioned problems, this invention provides a method for adaptive motion control and obstacle avoidance of robots in the medical field, specifically including the following steps: S1. Identify and classify obstacles within the robot's perception range; specifically, obstacle categories include pedestrian obstacles, hospital beds, wheelchairs, medical equipment, and fixed obstacles; S2. For different types of obstacles, corresponding motion prediction models are used to predict the trajectory: A social force model is used to predict the walking trajectory of pedestrians facing obstacles. A uniform motion model is used to predict the movement trajectory of obstacles such as hospital beds and wheelchairs. Medical devices and fixed obstacles are considered as static obstacles; S3. Based on the obstacle classification results and the output of the corresponding prediction model, plan the detour path, where different detour safety distances are set for different types of obstacles, and the safety distance for pedestrians is greater than the safety distance for fixed obstacles; S4. The maximum travel speed of the robot is dynamically adjusted based on the current environmental complexity index (ECI). The ECI is calculated by weighting the obstacle density, the proportion of dynamic obstacles, and the parameters representing the passability of the passage. The higher the ECI value, the lower the maximum speed allowed. S5. Execute graded emergency stop control: When an unclassified obstacle is detected within the first distance range, deceleration and stop are executed; when an unidentified obstacle is detected suddenly within the second distance range on the travel path that is smaller than the first distance, emergency braking is executed.

[0009] Furthermore, in step S1, 2D LiDAR, 3D ToF depth camera, and ultrasonic sensor are used to perceive obstacles within the robot's current position range; specifically, the robot's current position range is within a radius of 5m centered on the robot.

[0010] Furthermore, the formula for calculating the current environmental complexity in step S4 is: ECI = w1×(obstacle density) + w2×(dynamic obstacle ratio) + w3×(robot width / channel width); where ECI represents the current environmental complexity; w1, w2, and w3 are all weighting coefficients, specifically w1=0.5, w2=0.3, and w3=0.2.

[0011] Furthermore, the maximum travel speed of the robot is dynamically adjusted based on ECI as follows: when the robot is in an open corridor, the maximum speed is 1 m / s; when the robot is in a populated area, the maximum speed is 0.5 m / s; when the robot is in a narrow space or next to a hospital bed, the maximum speed is 0.2 m / s; when a pedestrian or patient is detected within 2 meters of the robot, the speed is automatically reduced to 0.5 m / s.

[0012] Furthermore, in step S3, corresponding prediction models are constructed and adjusted for different types of obstacles, specifically including: For pedestrian obstacles, the safe distance is 1 meter. The pedestrian's possible position in the next 2-3 seconds is predicted by the social force model and then the pedestrian is detoured in advance. For obstacles such as hospital beds and wheelchairs, the safe distance is 1.2 meters. The pedestrian's forward trajectory is determined by the uniform motion model and then the pedestrian is waited for or detoured in large distance. For medical equipment and fixed obstacles, the pedestrian is detoured when the distance is 0.5 meters.

[0013] Furthermore, it also includes a dynamic priority task scheduling step: when a high-priority task arrives during the execution of the current task, if the estimated time to reach the new task target is less than the deadline of the high-priority task, the current task is interrupted to execute the new task.

[0014] Furthermore, the braking deceleration at which the deceleration stops does not exceed 0.3 m / s². 2To prevent medical samples or reagents carried by the robot from spilling or being damaged due to excessive inertia; the emergency braking is directly applied to the motor controller through a hardware security link independent of the main control chip's conventional data bus.

[0015] An adaptive motion control and obstacle avoidance system for medical robots includes a perception and recognition module, a speed control module, a task receiving and processing module, a priority scheduling module, a path planning module, and an emergency stop control module. The perception and recognition module is used to perceive obstacles within the robot's current location range and to identify and classify the detected obstacles; the obstacle categories specifically include pedestrian obstacles, hospital beds, wheelchairs, medical equipment, and fixed obstacles. The speed control module is used to adaptively control the robot's travel speed based on the path planning module and the perception and recognition module; The task receiving and processing module is used to receive and manage the robot's current task information; The priority scheduling module is used to schedule tasks based on the priority of the robot's current tasks. The path planning module is used to plan the robot's forward path based on the priority-scheduled tasks, and to make real-time adjustments based on the obstacles detected by the perception and recognition module. The emergency stop control module is used to issue a deceleration and stop command when it receives a signal from the perception and recognition module that an unclassified obstacle has appeared within a first distance range; and to issue an emergency braking command when it receives a signal that an unidentified obstacle has suddenly appeared within a second distance range on the travel path that is smaller than the first distance.

[0016] This invention provides a method and system for adaptive motion control and obstacle avoidance of robots in the medical field, which has the following beneficial effects: In this invention, obstacles within the robot's current location range are identified and classified, and environmental complexity analysis is used to dynamically adjust the robot's maximum speed, ensuring the robot's safe operation in a medical environment. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present 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 only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0018] Figure 1 A flowchart of the method provided by the present invention; Figure 2This is a schematic diagram of the system structure provided by the present invention. Detailed Implementation

[0019] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0020] The following detailed description of the implementation method of the present invention is in conjunction with the accompanying drawings. The description is only a partial embodiment and not all embodiments. For clarity, representations and descriptions unrelated to the present invention are omitted in the drawings and description.

[0021] To provide a clearer understanding of the technical features, objectives, and beneficial effects of this invention, the following detailed description of the technical solution is provided. Obviously, the described embodiments are only a portion of the embodiments of this invention, not all of them, and should not be construed as limiting the scope of implementation of this invention. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the protection scope of this invention.

[0022] like Figure 2 As shown, the present invention provides a robot adaptive motion control and obstacle avoidance system for medical applications, including a perception and recognition module, a speed control module, a task receiving and processing module, a priority scheduling module, a path planning module, and an emergency stop control module.

[0023] The perception and recognition module is used to sense obstacles within the robot's current location range and to identify and classify the detected obstacles. Specifically, this module employs 2D LiDAR, a 3D ToF depth camera, and ultrasonic sensors to sense obstacles within the robot's current location range, defined as a radius of 5 meters centered on the robot. The obstacle identification and classification process includes: pedestrian obstacles, hospital beds, wheelchairs, medical equipment, and fixed obstacles.

[0024] The speed control module is used to adaptively control the robot's travel speed based on the path planning and perception recognition modules. Specifically, the speed control module dynamically adjusts the robot's maximum speed based on the current environmental complexity. The current environmental complexity is calculated using the formula: ECI = w1 × (obstacle density) + w2 × (dynamic obstacle ratio) + w3 × (robot width / aisle width); where ECI represents the current environmental complexity; w1, w2, and w3 are weighting coefficients, specifically w1 = 0.5, w2 = 0.3, and w3 = 0.2. A higher ECI results in a lower maximum permissible speed.

[0025] When the robot is currently in an open corridor, its maximum speed is 1 m / s; When the robot is currently in a populated area, its maximum speed is 0.5 m / s; When the robot is in a confined space or next to a hospital bed, its maximum speed is 0.2 m / s; When a pedestrian or patient is detected within 2 meters of the robot, it automatically slows down to 0.5 m / s.

[0026] The task receiving and processing module is used to receive and manage the robot's current task information. All task information received by the robot has a static priority set (e.g., emergency call > scheduled rounds > routine test submission).

[0027] The priority scheduling module is used to schedule tasks based on their priority. If, during the execution of the robot's current task, a higher-priority task arrives, and the estimated time for the new task is less than the deadline of the higher-priority task, the current task is interrupted and the new task is executed.

[0028] The path planning module plans the robot's forward path based on priority-scheduled tasks and makes real-time adjustments based on obstacle detection from the perception and recognition module. The path planning module builds corresponding prediction models for different types of obstacles and makes prediction adjustments accordingly, specifically including: For pedestrians, with a safe distance of 1 meter, the social force model is used to predict and judge the pedestrian's walking trajectory, anticipating the pedestrian's possible position in the next 2-3 seconds, and planning a path that conforms to human social habits (not suddenly cutting in, not going against the flow, and not blocking passages), and detouring in advance. The social force model is a theoretical tool used to simulate and predict the movement patterns of crowds. It treats each person as a particle driven by multiple "forces" and calculates the pedestrian's movement trajectory through the resultant force of these forces.

[0029] For hospital beds / wheelchairs, the safe distance is 1.2m. The trajectory of the hospital bed / wheelchair is predicted and judged by a uniform motion model, and the system waits for the hospital bed / wheelchair to pass or detours around it. For medical equipment / fixed obstacles, detour when you are 0.5m away from them.

[0030] The emergency stop control module is used to initiate a soft emergency stop (deceleration, not a sudden stop, to avoid spilling samples and reagents) when the sensing and recognition module detects an unclassified obstacle within 0.5 meters of the robot's current position. The module includes an emergency stop button; when an unclassified obstacle is detected within 0.3 meters of the robot's current path, the button is automatically pressed to bring the robot to a sudden stop. The braking deceleration will not exceed 0.3 m / s². 2To prevent medical samples or reagents carried by the robot from spilling or being damaged due to excessive inertia; the emergency braking is directly applied to the motor controller through a hardware security link independent of the main control chip's conventional data bus.

[0031] Adaptive motion control and obstacle avoidance methods for medical robots, such as Figure 1 As shown, the specific steps include: S1. Identify and classify obstacles within the robot's perception range; specifically, obstacle categories include pedestrian obstacles, hospital beds, wheelchairs, medical equipment, and fixed obstacles; S2. For different types of obstacles, corresponding motion prediction models are used to predict the trajectory: A social force model is used to predict the walking trajectory of pedestrians facing obstacles. A uniform motion model is used to predict the movement trajectory of obstacles such as hospital beds and wheelchairs. Medical devices and fixed obstacles are considered as static obstacles; S3. Based on the obstacle classification results and the output of the corresponding prediction model, plan the detour path, where different detour safety distances are set for different types of obstacles, and the safety distance for pedestrians is greater than the safety distance for fixed obstacles; S4. The maximum travel speed of the robot is dynamically adjusted based on the current environmental complexity index (ECI). The ECI is calculated by weighting the obstacle density, the proportion of dynamic obstacles, and the parameters representing the passability of the passage. The higher the ECI value, the lower the maximum speed allowed. S5. Execute graded emergency stop control: When an unclassified obstacle is detected within the first distance range, deceleration and stop are executed; when an unidentified obstacle is detected suddenly within the second distance range on the travel path that is smaller than the first distance, emergency braking is executed.

[0032] In this invention, obstacles within the robot's current location range are identified and classified, and environmental complexity analysis is used to dynamically adjust the robot's maximum speed, ensuring the robot's safe operation in a medical environment.

[0033] The above description is merely a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the concept described herein through the above teachings or related technologies or knowledge. Modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims.

Claims

1. A method for adaptive motion control and obstacle avoidance of robots for medical applications, characterized in that, The specific steps include: S1. Identify and classify obstacles within the robot's perception range; specifically, obstacle categories include pedestrian obstacles, hospital beds, wheelchairs, medical equipment, and fixed obstacles; S2. For different types of obstacles, corresponding motion prediction models are used to predict the trajectory: A social force model is used to predict the walking trajectory of pedestrians facing obstacles. A uniform motion model is used to predict the movement trajectory of obstacles such as hospital beds and wheelchairs. Medical devices and fixed obstacles are considered as static obstacles; S3. Based on the obstacle classification results and the output of the corresponding prediction model, plan the detour path, where different detour safety distances are set for different types of obstacles, and the safety distance for pedestrians is greater than the safety distance for fixed obstacles; S4. The maximum travel speed of the robot is dynamically adjusted based on the current environmental complexity index (ECI). The ECI is calculated by weighting the obstacle density, the proportion of dynamic obstacles, and the parameters representing the passability of the passage. The higher the ECI value, the lower the maximum speed allowed. S5. Execute graded emergency stop control: When an unclassified obstacle is detected within the first distance range, deceleration and stop are executed; when an unidentified obstacle is detected suddenly within the second distance range on the travel path that is smaller than the first distance, emergency braking is executed.

2. The adaptive motion control and obstacle avoidance method for medical robots according to claim 1, characterized in that, In step S1, 2D LiDAR, 3D ToF depth camera and ultrasonic sensor are used to perceive obstacles within the robot's current position range; the robot's current position range is specifically within a radius of 5m centered on the robot.

3. The adaptive motion control and obstacle avoidance method for medical robots according to claim 1, characterized in that, The formula for calculating the current environmental complexity in step S4 is: ECI = w1×(obstacle density) + w2×(dynamic obstacle ratio) + w3×(robot width / channel width); where ECI represents the current environmental complexity; w1, w2, and w3 are all weighting coefficients, specifically w1=0.5, w2=0.3, and w3=0.

2.

4. The adaptive motion control and obstacle avoidance method for medical robots according to claim 1, characterized in that, The maximum travel speed of the robot is dynamically adjusted based on ECI as follows: when the robot is in an open corridor, the maximum speed is 1 m / s; when the robot is in a populated area, the maximum speed is 0.5 m / s; when the robot is in a narrow space or next to a hospital bed, the maximum speed is 0.2 m / s; when a pedestrian or patient is detected within 2 meters of the robot, the speed is automatically reduced to 0.5 m / s.

5. The adaptive motion control and obstacle avoidance method for medical robots according to claim 1, characterized in that, Step S3 involves constructing and adjusting corresponding prediction models for different types of obstacles, specifically including: For pedestrian obstacles, the safe distance is 1 meter. The pedestrian's possible position in the next 2-3 seconds is predicted by the social force model and then the pedestrian is detoured in advance. For obstacles such as hospital beds and wheelchairs, the safe distance is 1.2 meters. The pedestrian's forward trajectory is determined by the uniform motion model and then the pedestrian is waited for or detoured in large distance. For medical equipment and fixed obstacles, the pedestrian is detoured when the distance is 0.5 meters.

6. The adaptive motion control and obstacle avoidance method for medical robots according to claim 1, characterized in that, It also includes a dynamic priority task scheduling step: when a high-priority task arrives during the execution of the current task, if the estimated time to reach the new task target is less than the deadline of the high-priority task, the current task is interrupted to execute the new task.

7. The adaptive motion control and obstacle avoidance method for medical robots according to claim 1, characterized in that, The braking deceleration at which the deceleration stops does not exceed 0.3 m / s². 2 To prevent medical samples or reagents carried by the robot from spilling or being damaged due to excessive inertia; the emergency braking is directly applied to the motor controller through a hardware security link independent of the main control chip's conventional data bus.

8. A medical-oriented robot adaptive motion control and obstacle avoidance system for implementing the method of any one of claims 1 to 7, characterized in that, It includes a perception and recognition module, a speed control module, a task receiving and processing module, a priority scheduling module, a path planning module, and an emergency stop control module; The perception and recognition module is used to perceive obstacles within the robot's current location range and to identify and classify the detected obstacles; the obstacle categories specifically include pedestrian obstacles, hospital beds, wheelchairs, medical equipment, and fixed obstacles. The speed control module is used to adaptively control the robot's travel speed based on the path planning module and the perception and recognition module; The task receiving and processing module is used to receive and manage the robot's current task information; The priority scheduling module is used to schedule tasks based on the priority of the robot's current tasks. The path planning module is used to plan the robot's forward path based on the priority-scheduled tasks, and to make real-time adjustments based on the obstacles detected by the perception and recognition module. The emergency stop control module is used to issue a deceleration and stop command when it receives a signal from the perception and recognition module that an unclassified obstacle has appeared within a first distance range; and to issue an emergency braking command when it receives a signal that an unidentified obstacle has suddenly appeared within a second distance range on the travel path that is smaller than the first distance.

Images