Control method, system and device for collaborative robot and medium

Abstract

The embodiment of the invention provides an operation control method, system and device for a collaborative robot and a medium, and the method comprises the steps: judging whether the robot is in an operation range or not based on the environment information of an operation scene where the robot is located and the state information of the robot; and when the robot is not in the operation range, generating a first navigation instruction based on the at least one target feature, and controlling the robot to go to the target operation position based on the first navigation instruction.

Description

Technical Field

[0001] This specification relates to the field of robot control, and in particular to a control method, system, device and medium for collaborative robots. Background Technology

[0002] With societal development and increasing industry demands, infrastructure construction such as rail transit, highways, and energy transportation requires the installation and maintenance of numerous electromechanical equipment and power pipelines, often involving complex high-altitude operations. Currently, these operations primarily rely on manual labor or general-purpose aerial work platforms, resulting in high safety risks for workers, low work efficiency, and high costs.

[0003] To address these challenges, collaborative robots can be used to perform tasks within the work environment. However, due to the complex and varied environment and different working conditions, collaborative robots cannot achieve fully autonomous operation throughout the entire process. In fact, this results in the efficiency of collaborative robots being lower than that of traditional manual operations.

[0004] Therefore, we hope to propose a control method, system, device and medium for collaborative robots, which can adaptively control the actions of collaborative robots by sensing environmental information in the work scene, so as to realize intelligent control of collaborative robots and improve work efficiency. Summary of the Invention

[0005] This specification provides one or more embodiments of a control method for a collaborative robot. The method includes: determining a target control task based on environmental information of the robot's work environment and the robot's state information; when the target control task is to find a target work location, generating a first navigation command based on at least one target feature, and controlling the robot to move to the target work location based on the first navigation command; when the robot reaches the target work location, determining a target horizontal support, generating a support control command based on the target horizontal support, and controlling the robot's balance system to contact the fixed support and apply a support load based on the support control command until the support load reaches the target support load; when the robot completes the target horizontal support at the target work location, determining a target vertical lifting, generating a lifting control command based on the target vertical lifting, and controlling the robot's work platform to reach a target work height based on the lifting control command.

[0006] This specification also provides a control system for a collaborative robot in one or more embodiments. The system includes a sensing module, a control module, and a decision module. The sensing module is configured to sense environmental information of the robot's work environment and the robot's state information. The control module is configured to: control the robot to move to a target work location based on a first navigation command; control the robot's balance system to contact a fixed support and apply a support load based on a support control command until the support load reaches a target support load; and control the robot's work platform to reach a target work height based on a lifting control command. The decision module is configured to: determine a target control task based on the environmental information and the state information; when the target control task is to find a target work location, generate the first navigation command based on at least one target feature; when the robot reaches the target work location, determine a target horizontal support and generate the support control command based on the target horizontal support; and when the robot completes the target horizontal support at the target work location, determine a target vertical lifting and generate the lifting control command based on the target vertical lifting.

[0007] One or more embodiments of this specification also provide a control device for a collaborative robot, the device including at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least a portion of the computer instructions to implement the methods described in the above embodiments.

[0008] One or more embodiments of this specification also provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method described in the above embodiments. Attached Figure Description

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein: Figure 1 This is a modular schematic diagram of a control method for a collaborative robot according to some embodiments of this specification; Figure 2 This is an exemplary flowchart of a control method for a collaborative robot according to some embodiments of this specification; Figure 3 This is an exemplary flowchart illustrating how to control a robot to stay in place, according to some embodiments of this specification; Figure 4 This is an exemplary flowchart illustrating the adjustment of support loads according to some embodiments of this specification; Figure 5 This is a schematic diagram illustrating the workflow of a control system for a collaborative robot according to some embodiments of this specification. Detailed Implementation

[0010] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. The accompanying drawings do not represent all implementation methods.

[0011] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. If other terms can achieve the same purpose, they may be replaced by other expressions.

[0012] In the embodiments of this specification, the order of the steps described in the step-by-step instructions is interchangeable unless otherwise specified, and steps may be omitted. Other steps may also be included in the operation process.

[0013] Figure 1 This is a modular schematic diagram of a control method for a collaborative robot according to some embodiments of this specification.

[0014] like Figure 1 As shown, the control method 100 for collaborative robots may include a sensing module 110, a control module 120, and a decision module 130.

[0015] The perception module is configured to perceive the environmental information of the working scene where the collaborative robot (hereinafter referred to as the robot) is located and the robot's status information.

[0016] In some embodiments, the sensing module may include various sensing devices, such as locators, radar, cameras, tilt sensors, force sensors, and various environmental sensors. Environmental sensors may be sensors used to sense data related to the environment; for example, environmental sensors may include at least one of a barometric pressure sensor, a temperature sensor, a gas concentration sensor, a dust concentration sensor, and a wind speed sensor.

[0017] In some embodiments, the sensing module can be located at any feasible location on the robot, for example, the sensing module can be located on the robot's chassis.

[0018] The control module is configured to control the robot to move to the target work position based on the first navigation command; to control the robot's balance system to contact the fixed support and apply the support load based on the support control command until the support load reaches the target support load; and to control the robot's work platform to reach the target work height based on the lifting control command.

[0019] In some embodiments, the control module 120 may include a travel control module 121 and a work control module 122. The travel control module 121 is configured to control the robot's travel movements. The work control module 122 is configured to control the robot's work movements.

[0020] The decision module is configured to determine the target control task based on environmental and status information; when the target control task is to find the target work location, it generates the first navigation command based on at least one target feature; when the robot reaches the target work location, it determines the target horizontal support and generates the support control command based on the target horizontal support; when the robot completes the target horizontal support at the target work location, it determines the target vertical lifting and lowering and generates the lifting and lowering control command based on the target vertical lifting and lowering.

[0021] In some embodiments, the control module may be a controller mounted on the robot. The decision module may include a processor and memory mounted on the robot or in the cloud. In some embodiments, the processor may process information and / or data related to the control method 100 for the collaborative robot to perform one or more functions described herein. In some embodiments, the processor may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction processor (ASIP), a graphics processing unit (GPU), a physical processor (PPU), a digital signal processor (DSP), or any combination thereof. In some embodiments, the storage device may include a mass storage device, removable memory, or any combination thereof.

[0022] In some embodiments, the robot may be a robot designed for operation in complex workspaces. Complex workspaces may include railway or highway tunnels, utility tunnels, underground pedestrian passages, and underground parking lots, etc. For example only, the specification uses a railway tunnel as the work scenario, and the robot may be a robot operating within a railway tunnel.

[0023] In some embodiments, the robot's structure may include a support system, a chassis, steering wheels mounted on the chassis (e.g., one steering wheel below each of the four corners of the chassis), a robotic arm for operation, and a controller. The operation may include at least one of the following: paint spraying, segment installation, and material transportation.

[0024] In some embodiments, the sensing module, control module, and decision module can be communicatively connected.

[0025] In some embodiments, the support system may include leveling legs and a drive device. The drive device can provide a pushing force to extend the leveling legs obliquely downwards until they contact the fixed support and level the work platform. After the leveling legs contact the fixed support, the drive device can further provide a pushing force so that the leveling legs can apply a supporting load to the fixed support. The drive device may include hydraulic cylinders, servo motors, and pneumatic cylinders, corresponding to hydraulic drive, electric drive, and pneumatic drive methods, respectively.

[0026] The fixed support point can be the location where the leveling support foot contacts the object. In some embodiments, the fixed support point can be a fixed structure or fixed object in the work environment. For example, when the work environment is a railway tunnel, the fixed support point can be the bottom surface of the tunnel.

[0027] For a detailed explanation of the foregoing, please refer to Figures 2 to 5 Related descriptions.

[0028] In some embodiments of this specification, the control method for collaborative robots can adaptively control the actions of collaborative robots based on environmental information within the work scenario and the robot's own state, thereby achieving intelligent control of collaborative robots and improving work efficiency.

[0029] Figure 2 This is an exemplary flowchart illustrating a control method for a collaborative robot according to some embodiments of this specification. In some embodiments, process 200 is executed jointly by a control module and a decision module. Figure 2 As shown, process 200 includes the following steps: Step 210: Determine the target control task based on the environmental information of the robot's work environment and the robot's state information.

[0030] Environmental information refers to information related to the robot's operating scenario. In some embodiments, environmental information may include obstacle information and environmental condition information, etc.

[0031] In some embodiments, obstacle information may include whether there is an obstacle in front of the robot and the type of obstacle. Obstacles may include suspended equipment, ditches, workers, construction vehicles, and other objects that impede the robot's progress.

[0032] Environmental operating condition information refers to environmental information related to the robot's operation. In some embodiments, environmental operating condition information may include at least one of altitude, temperature, dust concentration, harmful gas concentration, wind speed, and oxygen content.

[0033] In some embodiments, the decision-making module can acquire obstacle information through devices such as radar and cameras in the perception module, and acquire environmental condition information through various environmental sensors. For a description of the perception module, see [link to documentation]. Figure 1 And its related descriptions.

[0034] Status information refers to information related to the robot's state. In some embodiments, status information may include positioning information, the robot's current speed, load information, and battery level. The processing unit can obtain positioning information through the locator in the sensing module, and obtain the robot's current speed, load information, and battery level through the robot's controller.

[0035] Load information may include the weight and distribution of the load carried by the robot. In some embodiments, the load distribution can be represented by the pressure distribution borne by multiple steering wheels of the robot. The pressure borne by the steering wheels can be obtained by force sensors located at the steering wheels.

[0036] The target control task refers to the task that the robot is to perform. In some embodiments, the target control task may include finding a target work location, staying in place, and automatic recharging. For an explanation of staying in place, see [link to documentation]. Figure 3 And related descriptions. For instructions on automatic charging, please see below and related descriptions.

[0037] In some embodiments, the decision module can determine the target control task based on environmental information and state information. For example, the decision module can determine whether there are danger signals and obstacles in the robot's environment based on environmental information, and determine whether the load information meets the operational requirements and whether the current power level meets the preset power conditions based on state information, thereby determining the target control task.

[0038] In some embodiments, the danger signal may include falling objects from heights, harmful gas concentrations exceeding a first concentration range, oxygen content falling below a second concentration range, etc. The first and second concentration ranges may be preset.

[0039] In some embodiments, the operational requirement may include a uniform load distribution on the robot. Uniform load distribution can be defined as the pressure borne by each of the multiple steering wheels not exceeding a pressure threshold. This pressure threshold can be preset.

[0040] In some embodiments, the power preset condition can be pre-set, including the current power level being lower than a first return trip power threshold. The first return trip power threshold is determined based on the power required for the robot to travel from its current position to the target work position, complete the task, and then proceed to the target power supply for charging. For example, the first return trip power threshold is not less than the sum of the power required for the robot to travel from its current position to the target work position, complete the task, and then proceed to the target power supply for charging, and the reserved power level. The target power supply can be a pre-set charging station.

[0041] Reserved power is a fixed amount of power that is kept in reserve for the robot to deal with unexpected situations. The power required for the robot's round-trip operation and the reserved power can be preset based on historical experience.

[0042] In some embodiments, if there are no danger signals or obstacles in the robot's environment, and the load information meets the operational requirements and the current power level meets the preset power conditions, the decision module determines the target control task as finding the target operational location.

[0043] Step 220: When the target control task is to find the target work location, generate a first navigation command based on at least one target feature, and control the robot to move to the target work location based on the first navigation command.

[0044] The first navigation command is used to control the robot to move forward to the target work position to perform the task.

[0045] The target work position refers to the position where the robot will perform its work. The target work position can be preset.

[0046] Target features refer to inherent or pre-defined features that the robot can recognize. In some embodiments, target features may include tunnel structure features and pre-defined route features, etc.

[0047] Tunnel structural features refer to the inherent structures formed or artificially constructed during the tunnel construction process, such as reserved channels, inherent textures or markings on the walls, and the outlines of supporting components on the tunnel interior walls.

[0048] In some embodiments, the decision-making module can acquire tunnel structural features through devices such as radar and cameras in the perception module.

[0049] Preset route features refer to characteristics associated with a preset route, such as the sequence of coordinate points and inflection point coordinates corresponding to the preset route. A preset route can be a path pre-set by technicians to guide the robot's back-and-forth operations.

[0050] In some embodiments, the decision-making module can construct a coordinate system based on the actual tunnel structure and use the coordinates in the coordinate system to represent the robot's position, target work position, coordinate point sequence corresponding to the preset route, inflection point coordinates, etc.

[0051] In some embodiments, the control module can perform lateral and longitudinal control of the robot's movement state according to a first navigation command or a second navigation command. Movement modes include forward movement modes, etc.

[0052] In some embodiments, lateral control includes setting the robot's four wheels as steering wheels, acquiring environmental information based on sensors mounted on the robot chassis, and controlling the robot's driving stability and directional accuracy in the work scenario.

[0053] Among these, driving stability refers to the robot maintaining a predetermined driving posture during driving, while directional accuracy refers to the robot maintaining an accurate driving direction during driving. Therefore, the first navigation command includes steering parameters, lateral acceleration, etc., and the control module can control the robot to move to the target work position according to the first navigation command to perform the work.

[0054] In some embodiments, longitudinal control is based on environmental information acquired by sensing devices and on controlling the robot's speed stability during movement. Speed ​​stability refers to the robot maintaining a stable speed during movement.

[0055] Therefore, the first navigation command also includes parameters such as travel speed. These parameters can include the robot's travel speed and the speed difference between the left and right front wheels. The robot's travel speed can be preset.

[0056] In some embodiments, the decision module may generate a first navigation command based on at least one target feature and send it to the control module. For example, the decision module may determine whether there are danger signals and obstacles in the environment in which the robot is located when it moves forward based on environmental information acquired during the forward movement, and update the steering parameters and driving speed parameters in real time.

[0057] In some embodiments, the decision module can correct the deviation of the robot's forward trajectory based on the robot's position and preset route characteristics, and determine the steering angle of the robot's left and right steering wheels and the speed deviation between the left and right steering wheels through a four-wheel drive vehicle kinematics algorithm (such as a tracking algorithm or Stanley algorithm), so as to ensure that the robot can move to the target point along the reserved channel, the inherent texture of the wall or the markings.

[0058] In some embodiments, the sensing device located on the front side of the robot chassis needs to acquire environmental information during the robot's movement. Therefore, the sensor device start-stop parameters may include turning on the sensing device when the robot starts moving and turning off the sensing device when the robot reaches the target work position.

[0059] In some embodiments, the decision module can determine the target work area based on the work requirements, determine the support stability of multiple points based on the support adaptability and environmental adaptability of multiple points in the target work area, and redetermine the target work location from the multiple points based on the support stability.

[0060] The target work area refers to the area where the robot can perform its work.

[0061] In some embodiments, the decision module can determine the tunnel structure features related to the operation based on the environmental information obtained by the robot at the target operation location, and determine the center of the target operation range based on the tunnel structure features.

[0062] For example, if the robot needs to install overhead pipelines, the decision module can determine the wall support structure at the location where the pipeline needs to be installed as the center of the target work area.

[0063] In some embodiments, operational requirements may also include operational accuracy. Operational accuracy can be categorized into high accuracy and standard accuracy. High accuracy corresponds to operations such as pipeline connection and precision testing. Standard accuracy corresponds to operations such as routine inspections and foundation installation.

[0064] In some embodiments, the decision module can determine the size of the target work area based on the job requirements. For example, if the job requirement is high precision, the decision module can use an area with a radius of a first size and the center of the target work area as its center point as the target work area. Alternatively, if the job requirement is normal precision, the decision module can use an area with a radius of a second size and the center of the target work area as its center point as the target work area.

[0065] In some embodiments, the first size and the second size can be preset based on historical experience, with the first size being smaller than the second size.

[0066] Support stability is used to characterize the stability of the robot when it provides support at a designated point. In some embodiments, the decision module can preset multiple points within the target work area (e.g., multiple points are set at equal intervals with a preset length).

[0067] In some embodiments, the decision module can determine the support stability of each point based on the support adaptability and environmental adaptability of each point.

[0068] Support adaptability characterizes the degree to which the geological conditions at a given location are compatible with the robot's ability to provide support. Environmental adaptability characterizes the degree to which the environmental conditions at a given location are compatible with the robot's ability to provide support.

[0069] In some embodiments, support adaptability may include bottom flatness, load adaptability, etc.

[0070] Bottom flatness can be related to whether there are depressions or bumps on the ground corresponding to the location. In some embodiments, the decision module can evaluate bottom flatness based on environmental information acquired by the robot; for example, the deeper or higher a depression or bump is relative to a flat surface, the lower the bottom flatness.

[0071] Load fit can be related to the uniformity of the robot's load distribution. In some embodiments, the decision module can evaluate load fit based on the robot's load information, such as the load fit being higher if the pressure borne by multiple steering wheels does not exceed a pressure threshold and the difference between the pressures borne by multiple steering wheels is smaller.

[0072] In some embodiments, the decision-making module can assess environmental adaptability based on the environmental information acquired by the robot. For example, the higher the dust concentration, the more likely it is to cause support system failure, and the lower the environmental adaptability.

[0073] In some embodiments, for each point, the decision module can perform a weighted summation of the bottom flatness, load adaptability, and environmental adaptability of the point to obtain the support stability of the point.

[0074] In some embodiments, the decision module may determine the point with the highest support stability among multiple points as the new target operation location based on support stability.

[0075] In some embodiments of this specification, after the robot arrives at the target work location, a suitable work range can be determined based on the work requirements, and the support stability of multiple points within the work range can be evaluated using the acquired environmental information. In this way, the target work location that is most conducive to providing support can be re-determined, rather than simply stopping at a point where work can be carried out.

[0076] In some embodiments, the target control task further includes automatic charging. In response to the robot's current battery level meeting a preset battery level condition, the decision module can determine that the target control task is automatic charging. When the target control task is automatic charging, the decision module can generate a second navigation command based on at least one target feature, and the control module controls the robot to proceed to the target power supply location for charging based on the second navigation command.

[0077] The second navigation command is used to control the robot to go to the target power source for charging.

[0078] The method for determining the second navigation command is similar to that for determining the first navigation command, and will not be repeated here.

[0079] In some embodiments, if the current battery level is greater than a first return trip battery level threshold and less than a second return trip battery level threshold, but the environmental severity meets preset environmental conditions, the decision module can also determine that the target control task is automatic charging, and the control module controls the robot to go to the target power supply location for charging. The second return trip battery level threshold can be preset.

[0080] Understandably, even if the robot's current battery level is sufficient for round-trip operations, harsh environments may accelerate battery consumption. Therefore, to ensure operational safety, the control module can automatically charge the robot.

[0081] For details regarding the severity of the environment and the pre-set environmental conditions, please refer to [link / reference]. Figure 3 And its related descriptions.

[0082] In some embodiments of this specification, since the tunnel environment is relatively narrow, the robot's driving state is controlled laterally and longitudinally to enable the robot to have stronger forward and backward capabilities, thereby reducing the occurrence of construction accidents or collisions in the tunnel.

[0083] In some embodiments of this specification, based on the supplementary conditions that the current power level is insufficient to support the robot's safe return or that the current power level is insufficient to support the robot's safe return due to harsh environment, the target control task of automatic charging is intelligently triggered to prevent the robot from running out of power and being trapped in harsh environment.

[0084] Step 230: When the robot reaches the target working position, the target horizontal support is determined. Based on the target horizontal support, a support control command is generated. Using this command, the robot's balancing system is controlled to contact the fixed support and apply a support load until the support load reaches the target support load. For a description of the support system, please refer to [link to documentation]. Figure 1 And its related descriptions.

[0085] The target horizontal support can be the extension length of the leveling legs that allows the robot to achieve horizontal support. In some embodiments, the decision module can automatically determine the extension length of multiple leveling legs based on the flatness of the bottom of the target working position to obtain the target horizontal support.

[0086] The target support load refers to the support load that the support system needs to apply to the fixed support.

[0087] Understandably, robots need to maintain a fixed position when working. By having a support system contact the fixed support and apply a support load, the robot can perform its work more stably.

[0088] In some embodiments, the decision module can determine the overturning moment by readings from torque sensors deployed on the robot, and determine the target support load based on the overturning moment.

[0089] Overturning moment is used to characterize the degree of overturning tendency of a robot. In some embodiments, the control module can determine the overturning moment from the readings of torque sensors deployed on the robot.

[0090] In some embodiments, the decision module can determine the target support load by constructing a mechanical model based on the overturning moment. The calculation objective of the decision module is that the stabilizing moment provided by the support system (the stabilizing moment equals the product of the target support load and the stabilizing lever arm) must be sufficient to counteract the overturning moment. In practical applications, for construction safety, the stabilizing moment needs to be much larger than the overturning moment.

[0091] The mechanical model can be a static mechanical model that is pre-built based on the robot's actual geometry and stored in the decision module.

[0092] For example, when calculating the stabilizing moment, the decision module needs to input key parameters into the mechanical model to obtain the target support load. Key parameters may include overturning moment, overturning pivot (or overturning axis), stabilizing arm, etc. Among them, the stabilizing arm refers to the horizontal distance between the overturning axis and the leveling support foot that provides the main support force. The leveling support foot that provides the main support force for each overturning axis can be pre-stored in the processor.

[0093] In some embodiments, to ensure operational safety, the decision module may introduce a preset safety factor when calculating the stabilizing moment (i.e., the stabilizing moment is equal to the product of the overturning moment and the preset safety factor).

[0094] In some embodiments, the safety factor can be preset according to the degree of danger of the working condition and relevant industry standards, such as between 1.5 and 3.0.

[0095] In some embodiments, the decision module can calculate the stabilizing moment based on the overturning moment and a preset safety factor. Based on the fact that the stabilizing moment is equal to the product of the target support load and the stabilizing arm, the stabilizing moment is substituted and the target support load is derived in reverse.

[0096] Step 240: When the robot completes the target horizontal support at the target working position, determine the target vertical lifting and lowering, generate lifting and lowering control commands based on the target vertical lifting and lowering, and control the robot's working platform to reach the target working height based on the lifting and lowering control commands.

[0097] The target vertical lift can be the distance the work platform rises or falls. The target working height refers to the desired height the work platform will reach. In some embodiments, the target working height can be the height of the target working point.

[0098] The target work point refers to the position where the robot arm moves to perform the task. For example, if the task is paint spraying, the target work point is the position where the robot arm needs to spray.

[0099] In some embodiments, the decision module can determine the target work point based on at least one target feature. For example, the decision module can determine the spraying location as the target work point based on the inherent texture or markings on the wall surface (such as pre-marked spraying positions on the wall) in the target features.

[0100] In some embodiments, the decision module can take the height of the target work point as the target work height, and based on the difference between the height of the work platform and the target work height, determine the distance that the work platform needs to rise or fall to reach the target work height, obtain the target vertical lifting, and generate lifting control commands based on the target vertical lifting.

[0101] The control module can control the robot's work platform to rise or fall vertically to the target working height based on lifting control commands.

[0102] In some embodiments, the target control task further includes moving the robotic arm to the target work point. When the robot reaches the target work position, the decision module can determine that the target control task is to move the robotic arm to the target work point.

[0103] In some embodiments, when the target control task is for the robotic arm to move to the target work point, the decision module generates a third navigation instruction based on at least one target feature, and the control module controls the robotic arm to find the target work point based on the third navigation instruction.

[0104] The third navigation instruction refers to the instruction used to guide the robotic arm to move to the target work point. In some embodiments, the decision module can generate the third navigation instruction based on the starting position of the robotic arm and the position of the target work point. For example, the decision module generates the movement distance of the robotic arm in six directions based on the starting position of the robotic arm and the position of the target work point, thus obtaining the third navigation instruction.

[0105] In some embodiments, the target control task further includes stopping the point-finding process. Stopping the point-finding process may involve stopping the robotic arm from moving to the target work point.

[0106] In some embodiments, the decision module can determine the difficulty of finding a point based on environmental information. In response to the point-finding difficulty meeting preset environmental conditions, the target control task is determined to be stopping the point-finding. The point-finding difficulty can be the severity of the environment in which the robot is located before the robotic arm moves to the target work point. For an explanation of environmental severity, see [link to relevant documentation]. Figure 3 And its related descriptions.

[0107] In some embodiments, when the target control task is to stop and find a point, the decision module can generate a cooperative control signal based on the robot's position and send the cooperative control signal to the worker's terminal device (such as a smartphone). Based on the cooperative control signal, the worker goes to the robot's location to assist the robot's work (such as re-marking the wall or improving the robot's environment).

[0108] In some embodiments of this specification, by acquiring environmental and status information, the robot can accurately determine the actions it should perform, generate navigation instructions based on target features, control the robot to quickly and accurately reach the target work position, and determine a target support load that enables the robot to work stably. This completes the entire process of autonomously deciding on the robot's work tasks, precisely controlling the robot to move into position, and determining a stable support load.

[0109] In some embodiments, the target control task also includes staying in place. Figure 3This is an exemplary flowchart illustrating the control of a robot to remain stationary according to some embodiments of this specification. Figure 3 As shown, process 300 includes the following steps: Step 310: Determine the severity of the environment based on environmental information.

[0110] For information on environmental information, please refer to [link / reference]. Figure 1 And its related descriptions.

[0111] Environmental severity is used to characterize the degree of negative impact of the environment on robots.

[0112] In some embodiments, the decision module can extract target environmental parameters from environmental information, classify the target environmental parameters, perform a level assessment on each parameter, and determine the degree of environmental severity by performing a weighted sum based on the level assessment results.

[0113] Target environmental parameters can be environmental parameters that directly affect the safety and operation of the robot, such as the concentration of harmful gases, oxygen content, dust concentration, wind speed, altitude, and temperature.

[0114] In some embodiments, the decision-making module can categorize multiple parameters in the target environmental parameters into directly influencing parameters and indirectly influencing parameters. For example, directly influencing parameters include harmful gas concentration and oxygen content, while indirectly influencing parameters include dust concentration, wind speed, altitude, and temperature. The weight of directly influencing parameters is greater than that of indirectly influencing parameters, and the weights of both can be preset.

[0115] In some embodiments, the decision-making module can determine the level of each parameter based on its value and the level evaluation rules for each parameter. The level evaluation rules can be preset. For example, each parameter can be divided into level one, level two, or level three. Level one corresponds to the safe range of the parameter (the parameter has no negative impact on the robot's operation), level two corresponds to the critical range of the parameter (the parameter may have a negative impact on the robot's operation), and level three corresponds to the dangerous range of the parameter (the parameter has a negative impact on the robot's operation).

[0116] For example, the first, second, and third levels of harmful gas concentration correspond to different concentration ranges. The decision module can compare the harmful gas concentration with the magnitude of the three concentration ranges and determine the level corresponding to the concentration range containing the harmful gas concentration as the level corresponding to the harmful gas concentration.

[0117] In some embodiments, the decision module can perform a weighted summation of the assessment results of the target environmental parameters to obtain the degree of environmental severity.

[0118] Step 320: In response to the environmental severity meeting the preset environmental conditions, the target control task is determined to be to remain in place.

[0119] In some embodiments, the environmental preset conditions may include an environmental severity level greater than a severity threshold. The severity threshold may be preset.

[0120] In some embodiments, in response to the environmental severity meeting the preset environmental conditions, the decision module determines the target control task as staying in place. If the current battery level is greater than the first return battery level threshold and less than the second return battery level threshold, the decision module determines the target control task as automatic charging.

[0121] Understandably, if the environment is harsh but the robot has sufficient power, the robot can stay in place and continue to the target work location after the environment improves. However, if the environment is harsh and the robot's power is insufficient, the robot should be controlled to automatically recharge.

[0122] Step 330: When the target control task is to stay in place, generate a collaborative control signal and assign professional workers to work collaboratively based on the collaborative control signal.

[0123] In some embodiments, the decision-making module can generate cooperative control signals based on the robot's location and send these signals to a professional worker's terminal device (such as a smartphone). Based on the cooperative control signals, the professional worker can then proceed to the robot's location to assist in its operations (such as clearing obstacles hindering the robot's movement or improving the robot's environment).

[0124] In some embodiments of this specification, the impact of the robot's environment on its operation is comprehensively analyzed. In hazardous or unsuitable environments, the robot is promptly controlled to remain stationary, and professional workers are assigned to assist in the operation, thereby preventing damage to the robot or construction accidents.

[0125] Figure 4 This is an exemplary flowchart illustrating the adjustment of support loads according to some embodiments of this specification. Figure 4 As shown, process 400 includes the following steps: Step 410: Obtain the actual support load by force sensors deployed on the support system.

[0126] In some embodiments, the force sensor may include a force sensor utilizing strain gauge technology, etc. The force sensor may be communicatively connected to the decision module.

[0127] Actual support load refers to the actual support load applied by the support system to the fixed support. In some embodiments, the decision module may obtain the readings of the force sensor as the actual support load.

[0128] In some embodiments, the force sensor can be installed at the bottom of the leveling support foot of the support system, where it directly contacts the fixed support, to obtain the actual support load and avoid measurement errors caused by force loss during transmission in the mechanical structure.

[0129] In some embodiments, the sensing frequency of the force sensor can be a preset sampling frequency (such as 1 Hz or 10 Hz).

[0130] Step 420: When the actual support load meets the load difference condition, generate a new support control command.

[0131] In some embodiments, the actual support load and the target support load may differ because the support load provided by the leveling feet will naturally decrease over time, or the robot's demand for support load may change due to changes in load weight or distribution during operation.

[0132] In some embodiments, the load difference condition may include the actual support load exceeding a preset range (i.e., not within the upper and lower limits of the preset range). The preset range may be determined based on the target support load, such as the lower limit of the preset range being 90% of the target support load and the upper limit of the preset range being 110% of the target support load.

[0133] In some embodiments, the bottom of the leveling support foot can be equipped with a disc spring. The disc spring can compensate for the actual support load to a certain extent, eliminating the need for frequent adjustments to the hydraulic system to compensate for the difference between the actual support load and the target support load. By setting the disc spring, the accuracy requirements of the support and the complexity of control can be balanced, avoiding frequent start-stop of the support system and ensuring that necessary adjustments can be made in a timely manner when there is a large deviation in the support load.

[0134] In some embodiments, the decision module may generate new support control commands based on the difference between the target support load and the actual support load, so as to make the actual support load reach the target support load.

[0135] Step 430: Based on the new support control command, control the support system to adjust the support load applied to the fixed support until the actual support load reaches the target support load.

[0136] In some embodiments of this specification, by monitoring the actual support load in real time and adjusting the load in a timely manner, the stability and reliability of the support system can be ensured, thus guaranteeing operational safety.

[0137] It should be noted that the descriptions of processes 200, 300, and 400 above are for illustrative purposes only and do not limit the scope of this specification. Those skilled in the art can make various modifications and changes to the above processes under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0138] Figure 5 This is a schematic diagram illustrating the workflow of a control system for a collaborative robot according to some embodiments of this specification.

[0139] like Figure 5 As shown, the control system for collaborative robots is started first and initialized (such as self-test and data loading), and then it can determine whether the robot is in the target working position.

[0140] If the robot is in the target working position, the control system can control the leveling legs to level it, so that the robot can be stably fixed. Then the working platform can be raised or lowered to reach the target working height.

[0141] If the robot is not at the target work location, the control system can determine whether the robot needs human assistance based on environmental and status information. If no human assistance is needed, the system generates a first navigation command and controls the robot to move to the target work location according to the first navigation command.

[0142] If human assistance is required, the control system can generate collaborative control signals and send them to the terminal devices of skilled workers. Based on the collaborative control signals, the skilled workers go to the robot's location to assist it in reaching the target work location (such as clearing obstacles hindering the robot's movement or improving the robot's environment), and provide real-time feedback on whether the task is completed. Once the robot can move autonomously, the system generates the first navigation command and controls the robot to move to the target work location according to the first navigation command.

[0143] Once the robot is stably anchored and the work platform reaches the target working height, the control system generates a second navigation command and simultaneously determines whether human assistance is needed. If human assistance is required, the control system generates a collaborative control signal and sends it to the worker's terminal device. Based on the collaborative control signal, the worker moves to the robot's location to assist the robotic arm in moving to the target work point (e.g., re-marking the wall or improving the robot's environment), and provides real-time feedback on completion. Once the robot can autonomously move its robotic arm to the target work point, the second navigation command is used to control the robotic arm to move to the target work point.

[0144] If no human assistance is required, the robotic arm will be controlled to move to the target work point according to the second navigation command.

[0145] Once the robotic arm moves to the target work point, the robot begins its work. After completing the work, the control platform resets and retracts its leveling legs. The control system then determines whether the robot has completed its task (i.e., whether there is another target work location). If the robot has completed its task, it proceeds to the target power supply to recharge, ending the process. If the robot has not completed its task, it follows the same procedure to the next target work location.

[0146] Some embodiments of this specification also provide a control device for a collaborative robot, including at least one processor and at least one memory. The at least one memory is used to store computer instructions. The at least one processor is used to execute at least a portion of the computer instructions to implement the method described in any of the above embodiments.

[0147] Some embodiments of this specification also provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the method described in any of the above embodiments.

[0148] Furthermore, certain features, structures, or characteristics in one or more embodiments of this specification may be appropriately combined.

[0149] In some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, the numerical parameters should take into account specified significant digits and employ a general method of digit preservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0150] If there is any inconsistency or conflict between the descriptions, definitions, and / or terms used in the materials referenced in this specification and the content described in this specification, the descriptions, definitions, and / or terms used in this specification shall prevail.

Claims

1. A control method for collaborative robots, characterized in that, The method includes: Based on the environmental information of the robot's operating environment and the robot's state information, the target control task is determined. When the target control task is to find the target work location, a first navigation instruction is generated based on at least one target feature, and the robot is controlled to move to the target work location based on the first navigation instruction; When the robot reaches the target working position, it determines the target horizontal support, generates a support control command based on the target horizontal support, and controls the robot's balance system to contact the fixed support and apply a support load based on the support control command until the support load reaches the target support load. When the robot completes the target horizontal support at the target working position, it determines the target vertical lifting and lowering, generates a lifting and lowering control command based on the target vertical lifting and lowering, and controls the robot's working platform to reach the target working height based on the lifting and lowering control command.

2. The method as described in claim 1, characterized in that, The target control task also includes staying in place. Determining the target control task based on the environmental information of the robot's operating environment and the robot's state information includes: Based on the environmental information, the severity of the environment is determined; In response to the environmental severity meeting preset environmental conditions, the target control task is determined to be stationary. When the target control task is to stay in place, a collaborative control signal is generated, and professional workers are assigned to work collaboratively based on the collaborative control signal.

3. The method as described in claim 1, characterized in that, The target control task also includes automatic charging, and the method further includes: In response to the robot's current battery level meeting the preset battery level condition, the target control task is determined to be automatic charging; When the target control task is automatic charging, a second navigation command is generated based on the at least one target feature, and the robot is controlled to go to the target power supply location for charging based on the second navigation command.

4. The method as described in claim 3, characterized in that, The method further includes: The robot's driving state is controlled laterally and longitudinally according to the first navigation instruction or the second navigation instruction. The lateral control includes setting the robot's four wheels as steering wheels, acquiring environmental information based on sensors installed on the robot chassis, and controlling the robot's driving stability and directional accuracy in the work scenario. The longitudinal control includes acquiring environmental information based on the sensing device and controlling the speed stability of the robot during its movement.

5. The method as described in claim 1, characterized in that, The target control task also includes moving the robotic arm to the target work point, and the method further includes: When the target control task is for the robotic arm to move to the target work point, a third navigation command is generated based on at least one target feature, and the robotic arm is controlled to find the target work point based on the third navigation command.

6. The method as described in claim 5, characterized in that, The target control task also includes stopping the point search, and the method further includes: Based on the environmental information, determine the difficulty of finding the point; In response to the point-finding difficulty meeting the preset environmental conditions, the target control task is determined to be to stop point-finding; When the target control task is to stop finding a point, a cooperative control signal is generated, and professional workers are assigned to cooperate in the operation based on the cooperative control signal.

7. A control system for a collaborative robot, characterized in that, The system includes a sensing module, a control module, and a decision-making module; The sensing module is configured to sense the environmental information of the robot's work environment and the robot's status information. The control module is configured as follows: The robot is controlled to move to the target work location based on the first navigation command; Based on the support control command, the robot's balance system is controlled to contact the fixed support and apply a support load until the support load reaches the target support load; The robot's work platform is controlled to reach the target working height based on lifting control commands; The decision module is configured as follows: Based on the environmental information and the state information, the target control task is determined; When the target control task is to find the target operation location, the first navigation instruction is generated based on at least one target feature; When the robot reaches the target working position, it determines the target horizontal support and generates the support control command based on the target horizontal support; When the robot completes the horizontal support of the target at the target work position, it determines the vertical lifting of the target and generates the lifting control command based on the vertical lifting of the target.

8. A control device for a collaborative robot, characterized in that, The device includes at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is configured to execute at least a portion of the computer instructions to implement the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions from the storage medium, the computer executes the method as described in any one of claims 1 to 6.

Images