Multi-sensor fusion obstacle avoidance method and system for explosion-proof floor cleaning robot

Abstract

The present application relates to the technical field of explosion-proof robots and intelligent obstacle avoidance, and proposes a multi-sensor fusion obstacle avoidance method and system for an explosion-proof floor washing robot, which comprises: determining the material properties and potential ignition risk level of an obstacle by collecting multi-source perception data of the explosion-proof floor washing robot, and defining a safety distance threshold of the explosion-proof floor washing robot and the current obstacle; when the relative distance between the explosion-proof floor washing robot and the obstacle is less than the safety distance threshold, combining the electrostatic potential monitoring value, the material properties and the potential ignition risk level to generate a zero-collision obstacle avoidance instruction for the explosion-proof floor washing robot; based on the zero-collision obstacle avoidance instruction, constructing an obstacle avoidance action constraint space for the explosion-proof floor washing robot, and executing differentiated obstacle avoidance processing of the explosion-proof floor washing robot within the obstacle avoidance action constraint space. The present application can effectively eliminate the spark and electrostatic risk caused by physical contact, and realize zero-collision safe operation of the explosion-proof floor washing robot in a high-risk scene.

Description

Technical Field

[0001] This invention belongs to the field of explosion-proof robots and intelligent obstacle avoidance technology, and relates to a multi-sensor fusion obstacle avoidance method and system for an explosion-proof floor cleaning robot. Background Technology

[0002] Explosion-proof floor cleaning robots are intelligent cleaning equipment with explosion-proof safety features. They are mainly suitable for high-risk work scenarios such as petroleum, chemical, and military industries where flammable and explosive gases or dust may be present. In such hazardous locations, collisions, friction, or compression of the equipment may generate sparks, thereby posing a risk of environmental explosion. Therefore, in the process of autonomous cleaning, the robot has real-time obstacle detection and autonomous avoidance functions while meeting the explosion-proof safety requirements of hazardous locations. This is a key technical means to ensure safe on-site operations.

[0003] Traditional explosion-proof floor cleaning robots mainly rely on collision sensors to achieve close-range obstacle avoidance. Although this method can achieve basic obstacle avoidance in ordinary clean environments, in high-risk explosion-proof scenarios, physical collisions between the robot body can easily generate mechanical friction sparks and induce electrostatic discharge, posing a risk of igniting flammable and explosive media on site, resulting in significant safety hazards when the robot operates in high-risk areas.

[0004] Therefore, existing technologies lack a solution that can effectively eliminate the risks of sparks and static electricity caused by physical contact, and achieve zero-collision safe operation of explosion-proof floor cleaning robots in high-risk scenarios. Summary of the Invention

[0005] This invention provides a multi-sensor fusion obstacle avoidance method and system for explosion-proof floor cleaning robots. Its main purpose is to effectively eliminate the risk of sparks and static electricity caused by physical contact, and to achieve zero-collision safe operation of explosion-proof floor cleaning robots in high-risk scenarios.

[0006] To achieve the above objectives, the present invention provides a multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot, comprising: A multi-sensor fusion array is deployed on the explosion-proof floor cleaning robot to collect multi-source sensing data of the explosion-proof floor cleaning robot. The multi-sensor fusion array includes intrinsically safe lidar, ultrasonic sensors, multispectral sensors, electrostatic potential sensors, and dust concentration sensors. Using the multi-source sensing data, the material properties and potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located are determined, and a safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle is defined. The electrostatic potential of the explosion-proof floor cleaning robot is monitored in real time, and the relative distance between the explosion-proof floor cleaning robot and the obstacle is obtained in real time as the explosion-proof floor cleaning robot approaches the obstacle. When the relative distance is less than the safe distance threshold, the zero-collision obstacle avoidance command of the explosion-proof floor cleaning robot is generated by combining the electrostatic potential monitoring value, the material properties and the potential ignition risk level. Based on the zero-collision obstacle avoidance command, an obstacle avoidance action constraint space for the explosion-proof floor cleaning robot is constructed, and the differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot is performed within the obstacle avoidance action constraint space.

[0007] Optionally, by combining the electrostatic potential monitoring value, the material properties, and the potential ignition risk level, a zero-collision obstacle avoidance command for the explosion-proof floor cleaning robot is generated, including: Based on the electrostatic potential monitoring value, the material properties, and the potential ignition risk level, the obstacle avoidance decision priority of the explosion-proof floor cleaning robot is determined; Identify the obstacle avoidance response mode of the explosion-proof floor cleaning robot corresponding to the obstacle avoidance decision priority; Based on the obstacle avoidance response mode, the response action type and action execution sequence of the explosion-proof floor cleaning robot are set for each obstacle avoidance stage; In response to the response action type and the action execution sequence, a zero-collision obstacle avoidance command for the explosion-proof floor cleaning robot is generated.

[0008] Optionally, the obstacle avoidance response mode of the explosion-proof floor cleaning robot corresponding to the obstacle avoidance decision priority is identified, including: The priority attribute parameters of the obstacle avoidance decision priority are analyzed to determine the obstacle avoidance response category of the explosion-proof floor cleaning robot; Based on the obstacle avoidance response category, the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set; Based on the obstacle avoidance response category and the obstacle avoidance execution sequence, the obstacle avoidance response mode of the explosion-proof floor cleaning robot is determined.

[0009] Optionally, based on the obstacle avoidance response category, the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set, including: If the obstacle avoidance response category is a normal response category, then the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set to a normal obstacle avoidance sequence; If the obstacle avoidance response type is electrostatic priority response type, then the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set to electrostatic priority braking sequence; If the obstacle avoidance response category is the contact prohibition response category, then the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set to the contact prohibition obstacle avoidance sequence.

[0010] Optionally, based on the zero-collision obstacle avoidance command, the obstacle avoidance action constraint space of the explosion-proof floor cleaning robot is constructed, including: In the workspace of the explosion-proof floor cleaning robot, multiple obstacle avoidance constraint directions corresponding to the zero-collision obstacle avoidance command are determined. The obstacle avoidance constraint directions include at least one of forward constraint, backward constraint, lateral constraint and vertical constraint. The obstacle avoidance constraint direction is mapped to the corresponding degree of freedom constraint axis in the kinematic model of the explosion-proof floor cleaning robot. The kinematic model is a mathematical model that describes the mapping relationship between the linear velocity and steering angular velocity of the drive wheel of the explosion-proof floor cleaning robot and the translational velocity and rotational velocity of the robot body. Calculate the upper and lower limits of motion for the freedom constraint axes to determine the obstacle avoidance constraint space of the explosion-proof floor cleaning robot.

[0011] Optionally, the differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot is performed within the obstacle avoidance action constraint space, including: Identify the current obstacle avoidance response mode of the explosion-proof floor cleaning robot; Based on the current obstacle avoidance response mode, determine the amplitude limiting priority of each degree of freedom constraint axis within the obstacle avoidance action constraint space; According to the aforementioned limiting priority, the target movement speed of the explosion-proof floor cleaning robot is subject to graded limiting processing. Based on the target motion speed after the graded amplitude limiting process, the explosion-proof floor cleaning robot performs differentiated obstacle avoidance actions.

[0012] Optionally, the target movement speed of the explosion-proof floor cleaning robot is subjected to graded limiting processing according to the limiting priority, including: Based on the aforementioned limiting priority, the limiting order of each degree of freedom constraint axis is specified; According to the aforementioned limiting order, the target motion velocity on each degree of freedom constraint axis is judged sequentially: If the target's movement speed is greater than the upper limit of the movement in the corresponding dimension of the obstacle avoidance action constraint space, then the target's movement speed is limited to the upper limit of the movement. If the target motion speed is less than the lower limit of motion in the corresponding dimension, then the target motion speed is limited to the lower limit of motion. If the target speed is between the upper limit and the lower limit of the movement, then the target speed remains unchanged.

[0013] Optionally, the potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located is determined using the multi-source sensing data, including: Extract the spectral reflectance vector of the obstacle in multiple preset bands from the multispectral sensor data of the multi-source sensing data; The standard ignition material spectral feature matrix of the obstacle is obtained in multiple spectral bands. The standard ignition material spectral feature matrix is ​​established in advance through laboratory testing and includes typical spectral features of high ignition risk materials, medium ignition risk materials and low ignition risk materials. Based on the spectral characteristic matrix of the standard ignition material, the ignition risk index of the obstacle is calculated; The potential ignition risk level of the obstacle is determined based on the ignition risk index.

[0014] Optionally, using the multi-source sensing data, a safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle is defined, including: The real-time electrostatic potential monitoring value of the explosion-proof floor cleaning robot and the ambient dust concentration of the current environment are obtained from the multi-source sensing data. Based on the material properties of the obstacle, determine the triboelectric tendency level and ignition sensitivity level of the obstacle; Based on the triboelectric tendency level, the ignition sensitivity level, and the real-time electrostatic potential monitoring value, the basic safe distance between the explosion-proof floor cleaning robot and the current obstacle is calculated; The basic safe distance value is corrected by using the ambient dust concentration to obtain the safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle.

[0015] To address the aforementioned problems, the present invention also provides a multi-sensor fusion obstacle avoidance system for an explosion-proof floor cleaning robot, which implements the multi-sensor fusion obstacle avoidance method described above. The system includes: The data sensing module is used to deploy a multi-sensor fusion array on the explosion-proof floor cleaning robot to collect multi-source sensing data of the explosion-proof floor cleaning robot. The multi-sensor fusion array includes an intrinsically safe lidar, an ultrasonic sensor, a multispectral sensor, an electrostatic potential sensor, and a dust concentration sensor. The safety risk identification module is used to determine the material properties and potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located through the multi-source sensing data, and to define the safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle. The status monitoring module is used to monitor the electrostatic potential value of the explosion-proof floor cleaning robot in real time, and to obtain the relative distance between the explosion-proof floor cleaning robot and the obstacle in real time as the explosion-proof floor cleaning robot approaches the obstacle. The instruction generation module is used to generate a zero-collision obstacle avoidance instruction for the explosion-proof floor cleaning robot when the relative distance is less than the safe distance threshold, by combining the electrostatic potential monitoring value, the material properties and the potential ignition risk level. The control execution module is used to construct the obstacle avoidance action constraint space of the explosion-proof floor cleaning robot based on the zero-collision obstacle avoidance command, and to perform differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot within the obstacle avoidance action constraint space.

[0016] Compared to the problems described in the background art, this invention, through the multi-source sensing data, determines the material properties and potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located. It can set differentiated safety distances and obstacle avoidance strategies for obstacles of different materials, effectively reducing the ignition risk caused by sparks or static electricity generated by collisions or friction. Furthermore, this invention, through the multi-source sensing data, defines a safety distance threshold between the explosion-proof floor cleaning robot and current obstacles, enabling the dynamic setting of differentiated safety distances for different obstacles, balancing explosion-proof safety and operational efficiency, and avoiding the risk redundancy or excessive obstacle avoidance problems caused by a uniform threshold. This invention combines the electrostatic potential monitoring value, the material properties, and the potential ignition risk level... The invention generates zero-collision obstacle avoidance commands for the explosion-proof floor cleaning robot, enabling obstacle avoidance decisions to simultaneously consider collision avoidance and ignition source control, achieving risk-driven safe obstacle avoidance. Furthermore, by constructing an obstacle avoidance action constraint space, the invention transforms explosion-proof safety requirements into constraints on the robot's degrees of freedom, preventing the robot from entering potentially hazardous areas that could lead to physical contact, thus upgrading safety from passive response to active constraint. Finally, by executing differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot within the obstacle avoidance action constraint space, the invention transforms explosion-proof safety requirements into spatial constraints on robot movement, fundamentally eliminating the risks of sparks and static electricity caused by physical contact, achieving zero-collision safe operation of the floor cleaning robot in high-risk scenarios. Therefore, the invention effectively eliminates the risks of sparks and static electricity caused by physical contact, achieving zero-collision safe operation of the explosion-proof floor cleaning robot in high-risk scenarios. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the composition of a multi-sensor fusion array for a multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a multi-sensor fusion obstacle avoidance system for an explosion-proof floor cleaning robot according to an embodiment of the present invention; Figure 4 A schematic diagram of a computer device for implementing a multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot, as provided in an embodiment of the present invention; The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. This application provides a multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot. The executing entity of this multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0019] See Figure 1 The diagram shown is a flowchart illustrating a multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot according to an embodiment of the present invention. In this embodiment, the multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot includes: S1. Deploy a multi-sensor fusion array on the explosion-proof floor cleaning robot to collect multi-source sensing data of the explosion-proof floor cleaning robot. The multi-sensor fusion array includes intrinsically safe lidar, ultrasonic sensors, multispectral sensors, electrostatic potential sensors, and dust concentration sensors.

[0020] This invention embodiment collects multi-source perception data of the explosion-proof floor cleaning robot through a multi-sensor fusion array, which can obtain more comprehensive environmental and obstacle information and improve the reliability of obstacle avoidance decisions. The multi-source perception data includes the geometric position data of obstacles, the material property data of obstacles, the real-time electrostatic potential data of the explosion-proof floor cleaning robot, and the environmental dust concentration data.

[0021] See Figure 2The diagram shows the composition of a multi-sensor fusion array provided in an embodiment of the present invention. The multi-sensor fusion array includes an intrinsically safe lidar, an ultrasonic sensor, a multispectral sensor, an electrostatic potential sensor, and a dust concentration sensor. The intrinsically safe lidar is used to collect distance and contour information of obstacles. The ultrasonic sensor is used to collect echo information of obstacles made of transparent or low-reflectivity materials. The multispectral sensor is used to collect spectral characteristics of obstacles to identify their material properties. The electrostatic potential sensor is used to monitor the real-time electrostatic potential value of the explosion-proof floor cleaning robot body. The dust concentration sensor is used to collect dust concentration data in the environment. The data collected by each sensor is input as multi-source sensing data to the fusion processing unit. The fusion processing unit processes the multi-source sensing data and outputs the location information of the obstacles, the material properties of the obstacles, the electrostatic state of the robot, and the environmental dust level. Based on the above information, it performs an ignition risk level assessment and determines the dynamic safety distance threshold.

[0022] It should be noted that the multi-sensor fusion array does not include any collision sensors that rely on physical contact for triggering. Specifically, in high-risk explosion-proof scenarios, collision sensors require physical contact to trigger obstacle avoidance responses. However, this physical contact process may generate mechanical friction sparks or induce electrostatic discharge, posing a risk of igniting surrounding flammable and explosive media. Therefore, by excluding such collision sensors, the explosion-proof floor cleaning robot can perceive its environment without relying on physical contact, laying the foundation for achieving zero-collision obstacle avoidance.

[0023] S2. Using the multi-source sensing data, determine the material properties and potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located, and define a safe distance threshold between the explosion-proof floor cleaning robot and the current obstacles.

[0024] This invention uses multi-source sensing data to determine the material properties and potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located. It can set different safety distances and obstacle avoidance strategies for obstacles of different materials, effectively reducing the risk of ignition caused by sparks or static electricity generated by collisions or friction.

[0025] The obstacles include one or more of the following: fixed facilities such as equipment bases, pipes, and bridge piers; temporary storage items such as tools, raw material barrels, and pallets; and mobile equipment such as workers and forklifts. The material properties include at least one of metal, glass, plastic, wood, and fabric, and can be identified and determined by at least one of the following: multispectral sensor data, lidar echo data, or ultrasonic sensor data.

[0026] As an embodiment of the present invention, the potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located is determined by the multi-source sensing data, including: Extract the spectral reflectance vector of the obstacle in multiple preset bands from the multispectral sensor data of the multi-source sensing data; The standard ignition material spectral feature matrix of the obstacle is obtained in multiple spectral bands. The standard ignition material spectral feature matrix is ​​established in advance through laboratory testing and includes typical spectral features of high ignition risk materials, medium ignition risk materials and low ignition risk materials. Based on the spectral characteristic matrix of the standard ignition material, the ignition risk index of the obstacle is calculated; The potential ignition risk level of the obstacle is determined based on the ignition risk index.

[0027] The multispectral sensor data is collected by a multispectral sensor deployed on the explosion-proof floor cleaning robot, and includes reflectance information of the obstacle in multiple discrete spectral bands. The preset multiple bands include at least two bands from the visible light bands: red (620nm-750nm), green (495nm-570nm), and blue (450nm-495nm), as well as near-infrared (780nm-2500nm) and short-wave infrared (1000nm-1700nm). The spectral reflectance vector is a multidimensional vector composed of reflectance values ​​measured by the obstacle in the preset multiple bands, and its expression is: Where n is the number of bands Here is the reflectivity value in the i-th band; the potential ignition risk level is a discrete level index determined based on the preset threshold range into which the ignition risk index falls, including low ignition risk level, medium ignition risk level, and high ignition risk level. Specifically, when the ignition risk index is less than or equal to the first threshold, it is determined to be a low ignition risk level; when the ignition risk index is greater than the first threshold and less than or equal to the second threshold, it is determined to be a medium ignition risk level; and when the ignition risk index is greater than the second threshold, it is determined to be a high ignition risk level.

[0028] Optionally, the specific process for constructing the standard ignition material spectral feature matrix of the obstacle under the multiple bands is as follows: metal, glass, plastic, wood and fabric are selected as standard ignition material samples. Under standard illumination conditions, the spectral reflectance data of each sample under multiple preset bands are collected by a multispectral sensor. After repeated collection of each sample, the average reflectance value of each sample under each band is calculated. Finally, the average reflectance values ​​of each sample under each band are arranged in matrix form with material type as the row and band as the column to obtain the standard ignition material spectral feature matrix.

[0029] As one embodiment of the present invention, the ignition risk index of the obstacle is calculated using the following formula. It should be noted that this calculation method is only one possible method and does not affect the implementation of the basic scheme above:

[0030] in, This represents the ignition risk index of the obstacle, where n represents the number of wavelength bands and m represents the number of standard material types. This represents the measured reflectance of the i-th band. This represents the average reflectance of the j-th standard material in the i-th wavelength band. This represents the standard deviation of the reflectance of the j-th standard material in the i-th wavelength band. This represents the recognition weight of the i-th band for the j-th material. This represents the dust concentration correction factor. Indicates the concentration of dust in the environment. This represents the electrostatic potential correction factor. This represents the real-time electrostatic potential monitoring value. Indicates the safe threshold for electrostatic potential. This indicates that the static electricity level exceeds the standard. This indicates the maximum reference value for dust concentration.

[0031] In detail, the recognition weight The electrostatic potential correction coefficient was determined using principal component analysis, specifically by performing principal component analysis on the spectral feature matrix of the standard ignition material and extracting the contribution rate of each band to the identification of each material category as a weight value, with a value range of 0 to 1; The value is determined based on the ratio of the real-time electrostatic potential monitoring value of the explosion-proof floor cleaning robot to the preset electrostatic potential safety threshold. Specifically, when the real-time electrostatic potential monitoring value is less than or equal to the preset electrostatic potential safety threshold... =0; when the real-time electrostatic potential monitoring value is greater than the preset electrostatic potential safety threshold, The value ranges from 0 to ,in The preset maximum correction factor is set to 2; the dust concentration correction factor The value is determined based on the ratio of the ambient dust concentration to a preset safe dust concentration threshold. Specifically, when the ambient dust concentration is less than or equal to the preset safe dust concentration threshold, When the ambient dust concentration exceeds the preset dust concentration safety threshold, = Its value ranges from 0 to 2. To preset a safe threshold for dust concentration, This is the maximum reference value for dust concentration.

[0032] The embodiments of the present invention utilize the spectral matching degree in the above formula. Standardized deviation The measured reflectance at different wavelengths Reflectivity of standard materials The deviations are unified into dimensionless quantities, solving the problem of incomparable dimensions in multi-band data. Furthermore, by using squaring operations, the contribution of larger deviations to risk is amplified, making the score differences between high-risk and low-risk materials more significant. This is achieved through environmental correction factors. The ratio term in and The environmental dust concentration and robot electrostatic potential are converted into dimensionless correction coefficients, so that the impact of environmental factors on ignition risk can be quantified into specific numerical multipliers, thus solving the problem that environmental factors are difficult to quantitatively participate in obstacle avoidance decision-making.

[0033] Furthermore, in this embodiment of the invention, the safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle is defined by the multi-source sensing data. Differentiated safe distances can be dynamically set for different obstacles, taking into account both explosion-proof safety and operational efficiency, and avoiding the risk redundancy or excessive obstacle avoidance problems caused by a uniform threshold. The safe distance threshold refers to the critical distance value that triggers the explosion-proof floor cleaning robot to perform obstacle avoidance actions.

[0034] As an embodiment of the present invention, the safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle is defined using the multi-source sensing data, including: The real-time electrostatic potential monitoring value of the explosion-proof floor cleaning robot and the ambient dust concentration of the current environment are obtained from the multi-source sensing data. Based on the material properties of the obstacle, determine the triboelectric tendency level and ignition sensitivity level of the obstacle; Based on the triboelectric tendency level, the ignition sensitivity level, and the real-time electrostatic potential monitoring value, the basic safe distance between the explosion-proof floor cleaning robot and the current obstacle is calculated; The basic safe distance value is corrected by using the ambient dust concentration to obtain the safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle.

[0035] The real-time electrostatic potential monitoring value is the mass concentration value of suspended dust in the environment where the explosion-proof floor cleaning robot is located, which is collected in real time by the electrostatic potential sensor; the environmental dust concentration is the mass concentration value of suspended dust in the environment where the explosion-proof floor cleaning robot is located, which is collected in real time by the dust concentration sensor; the triboelectric tendency level is a grading index used to characterize the ability of the material to generate static electricity when physical contact friction occurs; the ignition sensitivity level is a grading index used to characterize the ease with which the material is ignited by electrostatic discharge or spark.

[0036] Optionally, the triboelectric tendency level and ignition sensitivity level of the obstacle can be determined by pre-constructing and storing a material property-risk level mapping table. The material property-risk level mapping table is constructed as follows: metal, glass, plastic, rubber, wood, and fabric are selected as preset common obstacle material samples; a standard triboelectric tendency test is performed on each sample, and the samples are classified into low, medium, and high triboelectric tendency levels based on the measured surface electrostatic potential rise value; an ignition sensitivity test is performed on each sample, and the samples are classified into low, medium, and high ignition sensitivity levels based on the measured minimum ignition energy; the material type is associated with and stored with the corresponding two levels to form the mapping table.

[0037] As another embodiment of the present invention, based on the triboelectric tendency level, the ignition sensitivity level, and the real-time electrostatic potential monitoring value, the basic safe distance value between the explosion-proof floor cleaning robot and the current obstacle is calculated, including: The first safety factor of the obstacle is determined by the triboelectric tendency level; The second safety factor of the obstacle is determined based on the ignition sensitivity level. Based on the potential deviation between the real-time electrostatic potential monitoring value and the preset electrostatic potential safety threshold, the potential correction coefficient of the explosion-proof floor cleaning robot is determined. The basic safety distance value is calculated based on the first safety factor, the second safety factor, the potential correction factor, and the preset safety distance benchmark value.

[0038] The first safety factor and the second safety factor are determined by querying a preset level-coefficient mapping table based on the triboelectric tendency level and the ignition sensitivity level, respectively. The level-coefficient mapping table is constructed using the same grading and calibration method as the material property-risk level mapping table, with higher levels corresponding to larger safety factors. The preset electrostatic potential safety threshold is an upper limit value of electrostatic potential pre-set according to explosion-proof safety standards. The safety distance reference value is pre-determined based on the braking performance parameters and sensor response delay time of the explosion-proof floor cleaning robot.

[0039] Optionally, the basic safety distance value is calculated using the following formula:

[0040] in, Indicates the basic safety distance value. This represents the baseline value for safe distance. This represents the first safety factor. This represents the second safety factor. This represents the potential correction factor. , , These represent the corresponding weighting coefficients.

[0041] S3. Monitor the electrostatic potential value of the explosion-proof floor cleaning robot in real time, and obtain the relative distance between the explosion-proof floor cleaning robot and the obstacle in real time as the explosion-proof floor cleaning robot approaches the obstacle.

[0042] This invention, through real-time monitoring of the electrostatic potential of the explosion-proof floor cleaning robot, can dynamically detect the risk of static electricity accumulation in the robot body and proactively trigger a safety response before the static electricity exceeds the standard, thus preventing the robot itself from becoming an ignition source.

[0043] Furthermore, during the process of the explosion-proof floor cleaning robot approaching the obstacle, the relative distance between the explosion-proof floor cleaning robot and the obstacle is acquired in real time, which can dynamically track the change in distance and provide continuous and timely data support for obstacle avoidance judgment.

[0044] It should be noted that the electrostatic potential monitoring value and the relative distance are collected in parallel and independently of each other, and are used to assess the risk of self-ignition of the robot body and the risk of collision between the robot and external obstacles, respectively. The electrostatic potential monitoring value is used to trigger the obstacle avoidance strategy adjustment based on the body's safety level, and the relative distance is used to trigger the obstacle avoidance response action based on the spatial safety margin.

[0045] S4. When the relative distance is less than the safe distance threshold, the zero-collision obstacle avoidance command of the explosion-proof floor cleaning robot is generated by combining the electrostatic potential monitoring value, the material properties and the potential ignition risk level.

[0046] In this embodiment of the invention, when the relative distance is less than the safe distance threshold, the zero-collision obstacle avoidance command of the explosion-proof floor cleaning robot is generated by combining the electrostatic potential monitoring value, the material properties, and the potential ignition risk level. This enables the obstacle avoidance decision to simultaneously consider collision avoidance and ignition source control, thereby achieving risk-driven safe obstacle avoidance.

[0047] As an embodiment of the present invention, the zero-collision obstacle avoidance command for the explosion-proof floor cleaning robot is generated by combining the electrostatic potential monitoring value, the material properties, and the potential ignition risk level, including: Based on the electrostatic potential monitoring value, the material properties, and the potential ignition risk level, the obstacle avoidance decision priority of the explosion-proof floor cleaning robot is determined; Identify the obstacle avoidance response mode of the explosion-proof floor cleaning robot corresponding to the obstacle avoidance decision priority; Based on the obstacle avoidance response mode, the response action type and action execution sequence of the explosion-proof floor cleaning robot are set for each obstacle avoidance stage; In response to the response action type and the action execution sequence, a zero-collision obstacle avoidance command for the explosion-proof floor cleaning robot is generated.

[0048] The obstacle avoidance decision priority is a priority order of obstacle avoidance response determined by a comprehensive assessment of electrostatic risk, material risk, and environmental risk, including four levels: electrostatic priority, contact prohibition, environmental risk, and conventional obstacle avoidance. The obstacle avoidance response mode refers to a set of obstacle avoidance control strategies corresponding to the obstacle avoidance decision priority, including electrostatic priority braking mode, contact prohibition mode, environmental risk mode, and conventional obstacle avoidance mode. The response action types include deceleration action, steering action, hovering action, and emergency braking action. The action execution sequence is used to indicate the execution order and trigger time of each response action type, including at least one of the following temporal relationships: sequential, parallel, or delayed execution.

[0049] Optionally, the response action type and action execution sequence can be set through a decision tree. For example, if the obstacle avoidance response mode is electrostatic priority braking mode, the response action type is set to emergency braking and the action execution sequence is immediate execution; if the obstacle avoidance response mode is contact prohibition mode, the response action type is set to hovering and the action execution sequence is continuous hold.

[0050] As another embodiment of the present invention, the obstacle avoidance decision priority of the explosion-proof floor cleaning robot is determined based on the electrostatic potential monitoring value, the material properties, and the potential ignition risk level, including: If the electrostatic potential monitoring value is greater than the preset electrostatic potential safety threshold, then the obstacle avoidance decision priority is determined to be the electrostatic priority decision, which represents the first priority level. If the triboelectric tendency level in the material properties is greater than the first level threshold, or the ignition sensitivity level in the material properties is greater than the second level threshold, then the obstacle avoidance decision priority is determined to be a contact prohibition decision that represents the second priority level. The first level threshold is determined based on the electrostatic generation capability when the obstacle rubs against the robot, and the second level threshold is determined based on the minimum ignition energy of the obstacle being ignited by electrostatic discharge. If the potential ignition risk level is greater than the third level threshold, then the obstacle avoidance decision priority is determined to be an environmental risk decision representing the third priority level, and the third level threshold is determined based on at least one parameter among environmental dust concentration, environmental temperature and environmental humidity. If the electrostatic potential monitoring value is less than or equal to the preset electrostatic potential safety threshold, and the triboelectric tendency level is less than or equal to the first level threshold, and the ignition sensitivity level is less than or equal to the second level threshold, and the potential ignition risk level is less than or equal to the third level threshold, then the obstacle avoidance decision priority is determined to be the conventional obstacle avoidance decision representing the fourth priority level.

[0051] As another embodiment of the present invention, the obstacle avoidance response mode of the explosion-proof floor cleaning robot corresponding to the obstacle avoidance decision priority is identified, including: The priority attribute parameters of the obstacle avoidance decision priority are analyzed to determine the obstacle avoidance response category of the explosion-proof floor cleaning robot; Based on the obstacle avoidance response category, the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set; Based on the obstacle avoidance response category and the obstacle avoidance execution sequence, the obstacle avoidance response mode of the explosion-proof floor cleaning robot is determined.

[0052] The obstacle avoidance response category refers to the category identifier obtained after classifying the obstacle avoidance response mode, including electrostatic priority response, contact prohibition response, environmental risk response, and conventional response; the obstacle avoidance execution sequence refers to a set of ordered obstacle avoidance actions associated with the obstacle avoidance response category, including at least one of deceleration, steering, hovering, and emergency braking and their execution order.

[0053] Furthermore, based on the obstacle avoidance response category, the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set, including: If the obstacle avoidance response category is a normal response category, then the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set to a normal obstacle avoidance sequence; If the obstacle avoidance response type is electrostatic priority response type, then the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set to electrostatic priority braking sequence; If the obstacle avoidance response category is the contact prohibition response category, then the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set to the contact prohibition obstacle avoidance sequence.

[0054] The conventional obstacle avoidance sequence is used to control the explosion-proof floor cleaning robot to perform deceleration and obstacle avoidance actions when there is no special risk. The electrostatic priority braking sequence is used to control the explosion-proof floor cleaning robot to perform emergency braking and hovering actions and lock the drive motor when the electrostatic potential monitoring value of the explosion-proof floor cleaning robot exceeds the preset electrostatic potential safety threshold, until the electrostatic potential monitoring value returns to below the preset electrostatic potential safety threshold. The contact prohibition obstacle avoidance sequence is used to control the explosion-proof floor cleaning robot to prohibit any physical contact with the obstacle when the triboelectric tendency level of the obstacle is greater than the first level threshold or the ignition sensitivity level is greater than the second level threshold, and to perform hovering, turning and maintaining a safe distance actions.

[0055] S5. Based on the zero-collision obstacle avoidance command, construct the obstacle avoidance action constraint space of the explosion-proof floor cleaning robot, and perform differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot within the obstacle avoidance action constraint space.

[0056] This invention constructs an obstacle avoidance action constraint space, transforming explosion-proof safety requirements into constraints on the robot's degrees of freedom of motion. This prevents the robot from entering dangerous areas that may cause physical contact, achieving a safety upgrade from passive response to active constraint.

[0057] As an embodiment of the present invention, based on the zero-collision obstacle avoidance command, the obstacle avoidance action constraint space of the explosion-proof floor cleaning robot is constructed, including: In the workspace of the explosion-proof floor cleaning robot, multiple obstacle avoidance constraint directions corresponding to the zero-collision obstacle avoidance command are determined. The obstacle avoidance constraint directions include at least one of forward constraint, backward constraint, lateral constraint and vertical constraint. The obstacle avoidance constraint direction is mapped to the corresponding degree of freedom constraint axis in the kinematic model of the explosion-proof floor cleaning robot. The kinematic model is a mathematical model that describes the mapping relationship between the linear velocity and steering angular velocity of the drive wheel of the explosion-proof floor cleaning robot and the translational velocity and rotational velocity of the robot body. Calculate the upper and lower limits of motion for the freedom constraint axes to determine the obstacle avoidance constraint space of the explosion-proof floor cleaning robot.

[0058] Wherein, the workspace refers to the set of all accessible positions of the explosion-proof floor cleaning robot within its range of motion; the degree-of-freedom constraint axis refers to the motion dimension independently controlled by the explosion-proof floor cleaning robot in the kinematic model, including translational degree-of-freedom axes and rotational degree-of-freedom axes, wherein the translational degree-of-freedom axis includes at least one of X-axis translational degree-of-freedom, Y-axis translational degree-of-freedom, and Z-axis translational degree-of-freedom; the rotational degree-of-freedom axis includes at least one of rotational degree-of-freedom around the X-axis, rotational degree-of-freedom around the Y-axis, and rotational degree-of-freedom around the Z-axis. The rotational degree of freedom around the X-axis corresponds to pitch motion, the rotational degree of freedom around the Y-axis corresponds to roll motion, and the rotational degree of freedom around the Z-axis corresponds to yaw motion. The upper limit of motion refers to the maximum permissible speed or displacement of the constrained axis in the positive direction, and the lower limit of motion refers to the maximum permissible speed or displacement of the constrained axis in the negative direction. The obstacle avoidance constraint space is a multi-dimensional space region formed by the constrained axes of each degree of freedom of the explosion-proof floor cleaning robot as dimensions, and the upper and lower limits of motion of each constrained axis as boundaries. Within this space region, all possible motion states of the explosion-proof floor cleaning robot meet the safety requirements of the zero-collision obstacle avoidance command and will not make physical contact with obstacles.

[0059] Optionally, multiple obstacle avoidance constraint directions corresponding to the zero-collision obstacle avoidance command can be determined by parsing the constraint direction field in the zero-collision obstacle avoidance command. The constraint direction field includes a forward constraint flag, a backward constraint flag, a lateral constraint flag, and a vertical constraint flag.

[0060] For example, the upper limit of motion of the degree-of-freedom constraint axis is calculated by the following formula: ,in, This represents the initial upper limit of motion for the i-th degree of freedom constraint axis before considering explosion-proof safety corrections. This represents the electrostatic potential correction factor. This represents the dust concentration correction factor.

[0061] Furthermore, by performing differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot within the obstacle avoidance action constraint space, the explosion-proof safety requirements can be transformed into spatial constraints for robot movement, fundamentally eliminating the risk of sparks and static electricity caused by physical contact, and achieving zero-collision safe operation of the floor cleaning robot in high-risk scenarios.

[0062] As an embodiment of the present invention, the differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot is performed within the obstacle avoidance action constraint space, including: Identify the current obstacle avoidance response mode of the explosion-proof floor cleaning robot; Based on the current obstacle avoidance response mode, determine the amplitude limiting priority of each degree of freedom constraint axis within the obstacle avoidance action constraint space; According to the aforementioned limiting priority, the target movement speed of the explosion-proof floor cleaning robot is subject to graded limiting processing. Based on the target motion speed after the graded amplitude limiting process, the explosion-proof floor cleaning robot performs differentiated obstacle avoidance actions.

[0063] Furthermore, according to the aforementioned limiting priority, the target movement speed of the explosion-proof floor cleaning robot is subjected to graded limiting processing, including: Based on the aforementioned limiting priority, the limiting order of each degree of freedom constraint axis is specified; According to the aforementioned limiting order, the target motion velocity on each degree of freedom constraint axis is judged sequentially: If the target's movement speed is greater than the upper limit of the movement in the corresponding dimension of the obstacle avoidance action constraint space, then the target's movement speed is limited to the upper limit of the movement. If the target motion speed is less than the lower limit of motion in the corresponding dimension, then the target motion speed is limited to the lower limit of motion. If the target speed is between the upper limit and the lower limit of the movement, then the target speed remains unchanged.

[0064] It should be noted that the upper and lower limits of motion in the obstacle avoidance constraint space are not static values, but are dynamically updated based on the real-time pose and velocity information of the explosion-proof floor cleaning robot to adapt to the constantly changing motion state. For example, when the current obstacle avoidance response mode is electrostatic priority braking mode, the limiting priority is configured such that the forward constraint axis takes precedence over the lateral constraint axis, and the upper limit of motion of the forward constraint axis is forcibly limited to zero; when the current obstacle avoidance response mode is conventional obstacle avoidance mode, the limiting priority of each axis is adjusted in real time according to the relative distance between the explosion-proof floor cleaning robot and the obstacle.

[0065] See Figure 3 The diagram shown is a schematic diagram of the multi-sensor fusion obstacle avoidance system of an explosion-proof floor cleaning robot provided in an embodiment of the present invention.

[0066] The multi-sensor fusion obstacle avoidance system 200 for an explosion-proof floor cleaning robot described in this invention can be installed in an electronic device. Depending on the functions implemented, the multi-sensor fusion obstacle avoidance system for the explosion-proof floor cleaning robot includes a data sensing module 201, a safety risk identification module 202, a status monitoring module 203, an instruction generation module 204, and a control execution module 205. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0067] In this embodiment of the invention, the functions of each module / unit are as follows: The data sensing module 201 is used to deploy a multi-sensor fusion array on the explosion-proof floor cleaning robot to collect multi-source sensing data of the explosion-proof floor cleaning robot. The multi-sensor fusion array includes an intrinsically safe lidar, an ultrasonic sensor, a multispectral sensor, an electrostatic potential sensor, and a dust concentration sensor. The safety risk identification module 202 is used to determine the material properties and potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located through the multi-source sensing data, and to define a safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle. The status monitoring module 203 is used to monitor the electrostatic potential monitoring value of the explosion-proof floor cleaning robot in real time, and to obtain the relative distance between the explosion-proof floor cleaning robot and the obstacle in real time as the explosion-proof floor cleaning robot approaches the obstacle. The instruction generation module 204 is used to generate a zero-collision obstacle avoidance instruction for the explosion-proof floor cleaning robot when the relative distance is less than the safe distance threshold, by combining the electrostatic potential monitoring value, the material properties and the potential ignition risk level. The control execution module 205 is used to construct the obstacle avoidance action constraint space of the explosion-proof floor cleaning robot based on the zero-collision obstacle avoidance command, and to perform differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot within the obstacle avoidance action constraint space.

[0068] In detail, the modules in the multi-sensor fusion obstacle avoidance system 200 for an explosion-proof floor cleaning robot described in this embodiment of the invention employ the same methods as described above during use. Figure 1 The method used is the same as the multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot described in the article, and can produce the same technical effect, so it will not be repeated here.

[0069] In one embodiment, a computer device is provided, which may be a server or a client, and its internal structure diagram may be as follows: Figure 4As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used for communication with external clients via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot on the server or client side.

[0070] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: S1. Deploy a multi-sensor fusion array on the explosion-proof floor cleaning robot to collect multi-source sensing data of the explosion-proof floor cleaning robot. The multi-sensor fusion array includes intrinsically safe lidar, ultrasonic sensor, multispectral sensor, electrostatic potential sensor and dust concentration sensor. S2. Using the multi-source sensing data, determine the material properties and potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located, and define the safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle. S3. Monitor the electrostatic potential value of the explosion-proof floor cleaning robot in real time, and obtain the relative distance between the explosion-proof floor cleaning robot and the obstacle in real time as the explosion-proof floor cleaning robot approaches the obstacle; S4. When the relative distance is less than the safe distance threshold, the zero-collision obstacle avoidance command of the explosion-proof floor cleaning robot is generated by combining the electrostatic potential monitoring value, the material properties and the potential ignition risk level. S5. Based on the zero-collision obstacle avoidance command, construct the obstacle avoidance action constraint space of the explosion-proof floor cleaning robot, and perform differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot within the obstacle avoidance action constraint space.

[0071] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: S1. Deploy a multi-sensor fusion array on the explosion-proof floor cleaning robot to collect multi-source sensing data of the explosion-proof floor cleaning robot. The multi-sensor fusion array includes intrinsically safe lidar, ultrasonic sensor, multispectral sensor, electrostatic potential sensor and dust concentration sensor. S2. Using the multi-source sensing data, determine the material properties and potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located, and define the safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle. S3. Monitor the electrostatic potential value of the explosion-proof floor cleaning robot in real time, and obtain the relative distance between the explosion-proof floor cleaning robot and the obstacle in real time as the explosion-proof floor cleaning robot approaches the obstacle; S4. When the relative distance is less than the safe distance threshold, the zero-collision obstacle avoidance command of the explosion-proof floor cleaning robot is generated by combining the electrostatic potential monitoring value, the material properties and the potential ignition risk level. S5. Based on the zero-collision obstacle avoidance command, construct the obstacle avoidance action constraint space of the explosion-proof floor cleaning robot, and perform differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot within the obstacle avoidance action constraint space.

[0072] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0073] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Furthermore, any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory.

[0074] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0075] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0076] Finally, it should be noted that in the above embodiments, each embodiment can be combined with each other or independent. Deleting any one of them will not affect the technical implementation of other embodiments. The above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot, characterized in that, The method includes: A multi-sensor fusion array is deployed on the explosion-proof floor cleaning robot to collect multi-source sensing data of the explosion-proof floor cleaning robot. The multi-sensor fusion array includes intrinsically safe lidar, ultrasonic sensors, multispectral sensors, electrostatic potential sensors, and dust concentration sensors. Using the multi-source sensing data, the material properties and potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located are determined, and a safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle is defined. The electrostatic potential of the explosion-proof floor cleaning robot is monitored in real time, and the relative distance between the explosion-proof floor cleaning robot and the obstacle is obtained in real time as the explosion-proof floor cleaning robot approaches the obstacle. When the relative distance is less than the safe distance threshold, the zero-collision obstacle avoidance command of the explosion-proof floor cleaning robot is generated by combining the electrostatic potential monitoring value, the material properties and the potential ignition risk level. Based on the zero-collision obstacle avoidance command, an obstacle avoidance action constraint space for the explosion-proof floor cleaning robot is constructed, and the differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot is performed within the obstacle avoidance action constraint space.

2. The multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot as described in claim 1, characterized in that, Combining the electrostatic potential monitoring value, the material properties, and the potential ignition risk level, the zero-collision obstacle avoidance command for the explosion-proof floor cleaning robot is generated, including: Based on the electrostatic potential monitoring value, the material properties, and the potential ignition risk level, the obstacle avoidance decision priority of the explosion-proof floor cleaning robot is determined; Identify the obstacle avoidance response mode of the explosion-proof floor cleaning robot corresponding to the obstacle avoidance decision priority; Based on the obstacle avoidance response mode, the response action type and action execution sequence of the explosion-proof floor cleaning robot are set for each obstacle avoidance stage; In response to the response action type and the action execution sequence, a zero-collision obstacle avoidance command for the explosion-proof floor cleaning robot is generated.

3. The multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot as described in claim 2, characterized in that, Identifying the obstacle avoidance response mode of the explosion-proof floor cleaning robot corresponding to the obstacle avoidance decision priority includes: The priority attribute parameters of the obstacle avoidance decision priority are analyzed to determine the obstacle avoidance response category of the explosion-proof floor cleaning robot; Based on the obstacle avoidance response category, the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set; Based on the obstacle avoidance response category and the obstacle avoidance execution sequence, the obstacle avoidance response mode of the explosion-proof floor cleaning robot is determined.

4. The multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot as described in claim 3, characterized in that, Based on the obstacle avoidance response category, the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set, including: If the obstacle avoidance response category is a normal response category, then the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set to a normal obstacle avoidance sequence; If the obstacle avoidance response type is electrostatic priority response type, then the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set to electrostatic priority braking sequence; If the obstacle avoidance response category is the contact prohibition response category, then the obstacle avoidance execution sequence of the explosion-proof floor cleaning robot is set to the contact prohibition obstacle avoidance sequence.

5. The multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot as described in claim 1, characterized in that, Based on the zero-collision obstacle avoidance command, the obstacle avoidance action constraint space of the explosion-proof floor cleaning robot is constructed, including: In the workspace of the explosion-proof floor cleaning robot, multiple obstacle avoidance constraint directions corresponding to the zero-collision obstacle avoidance command are determined. The obstacle avoidance constraint directions include at least one of forward constraint, backward constraint, lateral constraint and vertical constraint. The obstacle avoidance constraint direction is mapped to the corresponding degree of freedom constraint axis in the kinematic model of the explosion-proof floor cleaning robot. The kinematic model is a mathematical model that describes the mapping relationship between the linear velocity and steering angular velocity of the drive wheel of the explosion-proof floor cleaning robot and the translational velocity and rotational velocity of the robot body. Calculate the upper and lower limits of motion for the freedom constraint axes to determine the obstacle avoidance constraint space of the explosion-proof floor cleaning robot.

6. The multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot as described in claim 1, characterized in that, Performing differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot within the obstacle avoidance action constraint space includes: Identify the current obstacle avoidance response mode of the explosion-proof floor cleaning robot; Based on the current obstacle avoidance response mode, determine the amplitude limiting priority of each degree of freedom constraint axis within the obstacle avoidance action constraint space; According to the aforementioned limiting priority, the target movement speed of the explosion-proof floor cleaning robot is subject to graded limiting processing. Based on the target motion speed after the graded amplitude limiting process, the explosion-proof floor cleaning robot performs differentiated obstacle avoidance actions.

7. The multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot as described in claim 6, characterized in that, According to the aforementioned limiting priority, the target movement speed of the explosion-proof floor cleaning robot is subjected to graded limiting processing, including: Based on the aforementioned limiting priority, the limiting order of each degree of freedom constraint axis is specified; According to the aforementioned limiting order, the target motion velocity on each degree of freedom constraint axis is judged sequentially: If the target's movement speed is greater than the upper limit of the movement in the corresponding dimension of the obstacle avoidance action constraint space, then the target's movement speed is limited to the upper limit of the movement. If the target motion speed is less than the lower limit of motion in the corresponding dimension, then the target motion speed is limited to the lower limit of motion. If the target speed is between the upper limit and the lower limit of the movement, then the target speed remains unchanged.

8. The multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot as described in claim 1, characterized in that, Using the multi-source sensing data, the potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located is determined, including: Extract the spectral reflectance vector of the obstacle in multiple preset bands from the multispectral sensor data of the multi-source sensing data; The standard ignition material spectral feature matrix of the obstacle is obtained in multiple spectral bands. The standard ignition material spectral feature matrix is ​​established in advance through laboratory testing and includes typical spectral features of high ignition risk materials, medium ignition risk materials and low ignition risk materials. Based on the spectral characteristic matrix of the standard ignition material, the ignition risk index of the obstacle is calculated; The potential ignition risk level of the obstacle is determined based on the ignition risk index.

9. The multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot as described in claim 1, characterized in that, Based on the multi-source sensing data, a safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle is defined, including: The real-time electrostatic potential monitoring value of the explosion-proof floor cleaning robot and the ambient dust concentration of the current environment are obtained from the multi-source sensing data. Based on the material properties of the obstacle, determine the triboelectric tendency level and ignition sensitivity level of the obstacle; Based on the triboelectric tendency level, the ignition sensitivity level, and the real-time electrostatic potential monitoring value, the basic safe distance between the explosion-proof floor cleaning robot and the current obstacle is calculated; The basic safe distance value is corrected by using the ambient dust concentration to obtain the safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle.

10. A multi-sensor fusion obstacle avoidance system for an explosion-proof floor cleaning robot, employing the multi-sensor fusion obstacle avoidance method for an explosion-proof floor cleaning robot as described in any one of claims 1-9, characterized in that, The system includes: The data sensing module is used to deploy a multi-sensor fusion array on the explosion-proof floor cleaning robot to collect multi-source sensing data of the explosion-proof floor cleaning robot. The multi-sensor fusion array includes an intrinsically safe lidar, an ultrasonic sensor, a multispectral sensor, an electrostatic potential sensor, and a dust concentration sensor. The safety risk identification module is used to determine the material properties and potential ignition risk level of obstacles in the environment where the explosion-proof floor cleaning robot is located through the multi-source sensing data, and to define the safe distance threshold between the explosion-proof floor cleaning robot and the current obstacle. The status monitoring module is used to monitor the electrostatic potential value of the explosion-proof floor cleaning robot in real time, and to obtain the relative distance between the explosion-proof floor cleaning robot and the obstacle in real time as the explosion-proof floor cleaning robot approaches the obstacle. The instruction generation module is used to generate a zero-collision obstacle avoidance instruction for the explosion-proof floor cleaning robot when the relative distance is less than the safe distance threshold, by combining the electrostatic potential monitoring value, the material properties and the potential ignition risk level. The control execution module is used to construct the obstacle avoidance action constraint space of the explosion-proof floor cleaning robot based on the zero-collision obstacle avoidance command, and to perform differentiated obstacle avoidance processing of the explosion-proof floor cleaning robot within the obstacle avoidance action constraint space.

Images