Robot obstacle detection method and system in smart factory environment

Abstract

The invention provides a robot obstacle detection method and system in a smart factory environment, and relates to the technical field of obstacles, and the method comprises the steps: determining a strong light region and a high temperature region of a factory according to illumination intensity data and temperature distribution data; taking an overlapped area of the strong light area and the high temperature area as a sensing blind area, and taking the rest area as a non-sensing blind area; according to the metal dust concentration data, the sensing ability grade of each robot is evaluated, and the robot with the sensing ability grade larger than a preset grade and located in the non-sensing blind area serves as a collaborative robot; determining the position and the motion state of an obstacle in the sensing blind area by combining the environment data sent by the cooperative robot and the robot for sensing the blind area; and according to the position and the motion state of the obstacle, constructing an obstacle avoidance map, and according to the obstacle avoidance map, planning an obstacle avoidance path for the cargo robot to pass through the sensing blind area. The robot has the technical effects that the position of the obstacle is accurately detected, and the collision risk of the robot is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of obstacle detection, and specifically to a robot obstacle detection method and system in a smart factory environment. Background Art

[0002] With the rapid development of smart factories, robots are increasingly used in production environments. In a smart factory environment, multiple robots work together to improve production efficiency and flexibility. However, due to the complex factory environment, there are various obstacles, such as raw materials, semi-finished products, and finished products, which interfere with the movement of robots and affect production efficiency and safety. Therefore, how to accurately detect the location of obstacles and plan a reasonable obstacle avoidance path has become a problem faced by robot motion control in a smart factory environment.

[0003] At present, the commonly used robot obstacle avoidance method is usually to equip the robot with devices such as laser radar and visual sensors to sense the surrounding environment and avoid obstacles. However, in harsh environments such as strong light and high temperature, the robot's perception equipment is easily disturbed and fails, resulting in the robot's obstacle avoidance system being unable to accurately detect the location of obstacles, increasing the risk of collision between the robot and the person. Summary of the invention

[0004] The present application provides a robot obstacle detection method, system, device and storage medium in a smart factory environment, which are used to accurately detect the position of obstacles and reduce the risk of robot collision.

[0005] In the first aspect, the present application provides a robot obstacle detection method in a smart factory environment, the method comprising: obtaining temperature distribution data, metal dust concentration data and light intensity data sent by multiple robots in the factory; determining the strong light area of ​​the factory according to the light intensity data, and determining the high temperature area of ​​the factory according to the temperature distribution data; using the overlapping area of ​​the strong light area and the high temperature area as a perception blind area, and using the remaining area as a non-perception blind area; evaluating the perception ability level of each of the robots according to the metal dust concentration data, and using the robots whose perception ability level is greater than a preset level and located in the non-perception blind area as collaborative robots; determining the obstacle position and motion status within the perception blind area by combining the first environmental perception data sent by the collaborative robot and the second environmental perception data sent by the robot in the perception blind area; constructing an obstacle avoidance map according to the obstacle position and the motion status, and planning an obstacle avoidance path for the cargo robot to cross the perception blind area according to the obstacle avoidance map.

[0006] By adopting the above technical solution, by obtaining the temperature distribution, metal dust concentration and light intensity data of multiple robots in the factory, the overlapping area of ​​the strong light area and the high temperature area is determined as the perception blind spot, and the perception ability level of each robot is evaluated. The robots in the non-perception blind spot with strong perception ability are selected as collaborative robots. By combining the first environmental perception data of the collaborative robot and the second environmental perception data of the perception blind spot robot, the position and motion state of obstacles in the perception blind spot can be accurately obtained, thereby constructing an obstacle avoidance map and planning a reasonable obstacle avoidance path, accurately detecting the position of obstacles, and reducing the risk of robot collision.

[0007] Optionally, determining the strong light area of ​​the factory based on the light intensity data includes: performing time domain filtering on the light intensity data to obtain target light intensity data; establishing a light intensity distribution matrix based on the target light intensity data; dividing each area in the factory into different light levels based on the light intensity distribution matrix; and determining the area where the light level is greater than a preset level as a strong light area.

[0008] By adopting the above technical solution, the target light intensity data is obtained by time-domain filtering the light intensity data, and a light intensity distribution matrix is ​​established. The various areas in the factory are divided into different light levels, and the areas with light levels greater than the preset level are determined as strong light areas. This can effectively eliminate noise interference in the light intensity data and improve the accuracy of strong light area identification.

[0009] Optionally, determining the high temperature area of ​​the factory based on the temperature distribution data includes: performing spatial interpolation on the temperature distribution data to obtain a temperature distribution thermogram of the factory area; and determining, based on the temperature distribution thermogram, an area having a temperature higher than a preset temperature threshold and a temperature gradient greater than a preset gradient threshold as a high temperature area.

[0010] By adopting the above technical solution, the temperature distribution thermodynamic map of the factory area is obtained by spatially interpolating the temperature distribution data, and the area with a temperature higher than a preset temperature threshold and a temperature gradient greater than a preset gradient threshold is determined as a high-temperature area according to the temperature distribution thermodynamic map. This can achieve a continuous expression of the temperature distribution of the factory area and improve the accuracy of high-temperature area identification.

[0011] Optionally, evaluating the perception ability level of each of the robots based on the metal dust concentration data includes: determining the dust concentration at the location of each of the robots based on the metal dust concentration data; determining the perception ability level of each of the robots based on the dust concentration, wherein the perception ability level is inversely proportional to the dust concentration.

[0012] By adopting the above technical solution, by determining the dust concentration at each robot's location based on the metal dust concentration data and establishing an inverse relationship between the perception ability level and the dust concentration, the impact of metal dust on the robot's perception ability can be accurately evaluated, thereby more reasonably selecting a collaborative robot with stronger perception ability.

[0013] Optionally, the first environmental perception data sent by the collaborative robot and the second environmental perception data sent by the robot in the perception blind spot are combined to determine the position and motion state of the obstacle in the perception blind spot, including: taking the first environmental perception data as primary perception data and taking the second environmental perception data as auxiliary perception data; determining the initial position and initial motion state of the obstacle in the perception blind spot based on the primary perception data; correcting the initial position and the initial motion state based on the auxiliary perception data to obtain the corrected target obstacle position and target motion state; and taking the target obstacle position and the target motion state as the obstacle position and motion state in the perception blind spot.

[0014] By adopting the above technical solution, the first environmental perception data of the collaborative robot is used as the main perception data, and the second environmental perception data of the blind spot perception robot is used as the auxiliary perception data to determine the initial position and initial motion state of the obstacle, and the auxiliary perception data is used to correct the target obstacle position and target motion state, thereby realizing multi-source data fusion perception of obstacles in the perception blind spot and improving the reliability of obstacle position and motion state recognition.

[0015] Optionally, constructing an obstacle avoidance map based on the obstacle position and the motion state includes: predicting the motion trajectory of the obstacle within a preset time period based on the obstacle position and the motion state; mapping the motion trajectory to the regional coordinate system of the factory to obtain an obstacle impact area; determining the risk level of each area in the factory based on the obstacle impact area and the distribution positions of multiple devices in the factory; and generating an obstacle avoidance map based on the risk levels.

[0016] By adopting the above technical solution, the movement trajectory of obstacles within a preset time period is predicted and mapped to the factory area coordinate system to obtain the obstacle impact area. The risk level of each area is determined in combination with the distribution location of factory equipment and an obstacle avoidance map is generated. This achieves accurate grasp of the dynamic characteristics of obstacles and reasonable division of risk areas, thereby improving the timeliness and practicality of the obstacle avoidance map.

[0017] Optionally, after planning an obstacle avoidance path for the cargo robot to cross the perception blind spot according to the obstacle avoidance map, the method further includes: establishing a communication network among multiple cargo robots in the perception blind spot; and allocating a time window for crossing the perception blind spot to each cargo robot according to the task priority of each cargo robot.

[0018] By adopting the above technical solution, a communication network is established between multiple cargo robots in the perception blind spot, and a time window for crossing the perception blind spot is allocated according to the task priority of each cargo robot. This achieves orderly scheduling of cargo robots in the perception blind spot, avoiding the congestion and collision risks that may be caused by multiple robots crossing the perception blind spot at the same time.

[0019] In a second aspect, the present application provides a robot obstacle detection system in a smart factory environment, the system comprising: an acquisition module, a determination module, an output module, an evaluation module, a combination module and a generation module; wherein, The acquisition module is used to acquire temperature distribution data, metal dust concentration data and light intensity data sent by multiple robots in the factory; the determination module is used to determine the strong light area of ​​the factory according to the light intensity data, and to determine the high temperature area of ​​the factory according to the temperature distribution data; the output module is used to use the overlapping area of ​​the strong light area and the high temperature area as a perception blind area, and the remaining area as a non-perception blind area; the evaluation module is used to evaluate the perception ability level of each robot according to the metal dust concentration data, and use the robot whose perception ability level is greater than the preset level and is located in the non-perception blind area as a collaborative robot; the combination module is used to combine the first environmental perception data sent by the collaborative robot and the second environmental perception data sent by the robot in the perception blind area to determine the obstacle position and motion state in the perception blind area; the generation module is used to construct an obstacle avoidance map according to the obstacle position and the motion state, and plan an obstacle avoidance path for the cargo robot to cross the perception blind area according to the obstacle avoidance map.

[0020] In a third aspect, the present application provides an electronic device that adopts the following technical solution: it includes a processor, a memory, a user interface, and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a computer program such as any of the above-mentioned robot obstacle detection methods in a smart factory environment.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: storing a computer program that can be loaded by a processor and execute any of the above-mentioned robot obstacle detection methods in a smart factory environment.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: By obtaining the temperature distribution, metal dust concentration and light intensity data of multiple robots in the factory, the overlapping areas of strong light areas and high temperature areas are determined as perception blind spots, and the perception ability level of each robot is evaluated. Robots in non-perception blind spots with strong perception abilities are selected as collaborative robots. By combining the first environmental perception data of the collaborative robot and the second environmental perception data of the perception blind spot robot, the position and motion status of obstacles in the perception blind spot can be accurately obtained, thereby constructing an obstacle avoidance map and planning a reasonable obstacle avoidance path, accurately detecting the position of obstacles, and reducing the risk of robot collision. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of a robot obstacle detection method in a smart factory environment provided by an embodiment of the present application; Figure 2 It is a structural schematic diagram of a robot obstacle detection system in a smart factory environment provided by an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0024] Description of reference numerals: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0026] In the description of the embodiments of the present application, words such as "illustrative", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "illustrative", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "illustrative", "for example" or "for example" is intended to present related concepts in a concrete way.

[0027] Figure 1 FIG. 1 is a flow chart of a robot obstacle detection method in a smart factory environment provided by an embodiment of the present application. Figure 1 As shown, the method includes S101-S106: S101, obtaining temperature distribution data, metal dust concentration data, and light intensity data sent by multiple robots in the factory.

[0028] In a smart factory environment, interference factors such as high temperature, strong light, and metal dust are generated during the production process, which will affect the sensor performance of the robot and reduce the obstacle detection accuracy. In order to accurately identify the perception blind spots in the factory environment and improve the reliability of obstacle detection, this embodiment first obtains the environmental perception data sent by multiple robots in the factory.

[0029] Specifically, each robot in the factory is equipped with a temperature sensor, a metal dust concentration sensor and a light intensity sensor. The temperature sensor uses an infrared array temperature sensor with a measurement range of -40°C to 150°C and a measurement accuracy of ±0.5°C; the metal dust concentration sensor uses a laser scattering dust concentration sensor with a detection range of 0-1000mg / m³ and a resolution of 0.1mg / m³; the light intensity sensor uses a digital light sensor with a measurement range of 1-65535lux and a response time of less than 1ms.

[0030] Each robot sends the collected environmental perception data to the central control system in real time through the wireless communication network. To ensure the real-time and reliability of data transmission, the industrial Internet of Things communication protocol based on the 5G network is adopted, with a data transmission delay of less than 10ms and a packet loss rate of less than 0.01%. During the data transmission process, the collected raw data is timestamped and marked with device ID for subsequent data processing and analysis.

[0031] The frequency of collecting environmental perception data is dynamically adjusted according to the factory production conditions. Under normal conditions, the data collection frequency is 10Hz; when a sudden change in environmental parameters is detected, the collection frequency is automatically increased to 50Hz to capture the detailed characteristics of environmental changes. At the same time, in order to reduce the burden of data storage and transmission, a data preprocessing mechanism is used to reduce noise and compress the original data, retaining only valid data for transmission.

[0032] By acquiring these environmental perception data, we can fully understand the temperature distribution, metal dust concentration distribution and light intensity distribution in the factory, laying a data foundation for the subsequent identification of perception blind spots, evaluation of robot perception capabilities and planning of obstacle avoidance paths. This multi-dimensional environmental perception data collection method can effectively improve the system's perception capabilities of the factory environment and provide a guarantee for efficient and reliable robot obstacle detection.

[0033] S102, determining the strong light area of ​​the factory according to the light intensity data, and determining the high temperature area of ​​the factory according to the temperature distribution data.

[0034] In factory environments, areas of strong light and high temperature can significantly affect the performance of perception devices such as robot vision sensors and lidar. For example, strong light can cause image overexposure and abnormal laser reflection, and high temperature can cause thermal disturbances and range errors. Therefore, accurate identification of these areas is crucial for subsequent obstacle detection.

[0035] First, the acquired light intensity data is filtered in the time domain. Specifically, a bandpass filter is used with a cutoff frequency set to 0.1Hz to 10Hz to filter out the effects of ambient light flicker and sensor noise. The target light intensity data obtained after filtering can more accurately reflect the steady-state light distribution of the factory environment. Based on the target light intensity data, an MxN-dimensional light intensity distribution matrix is ​​established, where M and N correspond to the number of grid divisions in the factory area in the X-axis and Y-axis directions, respectively, and the size of each grid is 0.5mx0.5m.

[0036] Based on the light intensity distribution matrix, the factory area is divided into four light levels: low illumination area (0-1000 lux), normal illumination area (1000-3000 lux), high illumination area (3000-5000 lux) and strong light area (>5000 lux). When the light level of a certain area is greater than the preset level (set as a high illumination area in this embodiment), it is marked as a strong light area. In order to improve the accuracy of area division, a bilinear interpolation algorithm is used at the grid boundary to perform a smooth transition of light intensity.

[0037] At the same time, the temperature distribution data is spatially interpolated, and the Kriging interpolation algorithm is used to construct the temperature distribution heat map of the factory area. This algorithm takes into account the spatial correlation of the temperature data and can generate continuous temperature distribution estimates between sampling points. The spatial resolution of the temperature distribution heat map is consistent with the light intensity distribution matrix, both of which are 0.5mx0.5m.

[0038] Based on the temperature distribution thermodynamic map, the temperature threshold is set to 45°C and the temperature gradient threshold is set to 5°C / m. When the temperature of a certain area is higher than the temperature threshold and the temperature gradient is greater than the gradient threshold, it is marked as a high temperature area. The temperature gradient is calculated using the central difference method to capture areas with sharp temperature changes. These areas are usually adjacent to high-temperature industrial equipment such as thermal processing equipment and smelting equipment.

[0039] Based on the above embodiment, as an optional implementation, in S102, determining the strong light area of ​​the factory according to the light intensity data specifically includes S21-S24: S21, performing time domain filtering on the light intensity data to obtain target light intensity data.

[0040] In a factory environment, the temporal and spatial distribution of light intensity directly affects the robot's environmental perception performance. In order to accurately identify the strong light areas that affect the normal operation of the robot, the collected light intensity data needs to be systematically processed and analyzed. Since the lighting conditions inside the factory are affected by many factors, such as natural light, artificial lighting, equipment reflections, etc., the original light intensity data often contains noise and instantaneous fluctuations, and it is necessary to obtain stable and reliable light intensity characteristics through time domain filtering.

[0041] In the time domain filtering stage, a sliding median filter is used to process the original light intensity data. The sliding window size is set to 10 sampling points and the sampling frequency is 10Hz, which can effectively suppress the interference caused by sudden light changes and maintain the long-term change trend of light intensity. The target light intensity data obtained after filtering can more accurately reflect the actual light conditions in various areas of the factory.

[0042] S22, establishing a light intensity distribution matrix according to the target light intensity data.

[0043] Based on the target light intensity data, the light intensity distribution matrix of the factory environment is established. The factory space is divided into several grid cells, each of which is 0.5 m × 0.5 m in size. For each grid cell, the average light intensity value of its corresponding position is calculated and stored in the light intensity distribution matrix. This matrix representation method is not only convenient for subsequent data processing, but also can intuitively display the light distribution characteristics of the factory space.

[0044] S23, dividing various areas in the factory into different light levels according to the light intensity distribution matrix.

[0045] S24, determining the area where the light level is greater than the preset level as a strong light area.

[0046] In order to achieve accurate division of the lighting area, the factory environment is divided into different lighting levels according to the lighting intensity distribution matrix. Specifically, the multi-threshold segmentation method is used to divide the lighting intensity into five levels: low lighting area, normal lighting area, medium-intensity light area, high-intensity light area and extremely strong light area. The division thresholds of each level are determined based on the actual measured data of the industrial site and the performance indicators of the robot vision system to ensure that the classification results match the actual working needs of the robot.

[0047] Finally, the area with a light level higher than the preset level is determined as a strong light area. The preset level is set as a medium strong light area, that is, the high-intensity light area and the extremely strong light area are uniformly marked as a strong light area. This division method fully considers the dynamic range and anti-interference ability of the robot vision system, and can effectively identify areas that may cause the robot's perception performance to deteriorate.

[0048] Based on the above embodiment, as an optional implementation, in S102, determining the high temperature area of ​​the factory according to the temperature distribution data specifically includes S31-S32: S31, performing spatial interpolation on the temperature distribution data to obtain a temperature distribution thermodynamic map of the factory area.

[0049] S32, according to the temperature distribution thermodynamic map, determining a region where the temperature is higher than a preset temperature threshold and the temperature gradient is greater than a preset gradient threshold as a high temperature region.

[0050] In a factory environment, the distribution of high-temperature equipment and heat sources can affect the normal operation and safety of robots. Due to the limited deployment locations of temperature sensors, it is impossible to directly obtain the continuous temperature distribution of the entire factory space. It is necessary to construct a complete temperature distribution thermal map through spatial interpolation methods and identify potential hazardous areas based on temperature values ​​and temperature gradient characteristics.

[0051] In the spatial interpolation stage, the Kriging interpolation method is used to process discrete temperature distribution data. This method comprehensively considers the correlation of spatial positions and the weight distribution of measurement points, and can reflect the spatial continuity characteristics of the temperature field while ensuring the interpolation accuracy. In specific implementation, the spatial variation function model of temperature data is first established to describe the law of temperature value change with spatial distance, and then the optimal linear unbiased estimate of the temperature value of the unmeasured point in the factory space is made based on the model. The resolution of the interpolation grid is set to 0.2 meters, which not only ensures the expression of temperature distribution details, but also meets the needs of real-time calculation.

[0052] The temperature distribution heat map generated based on the interpolation results uses a pseudo-color display method, with different temperature ranges corresponding to different colors, which is convenient for intuitively identifying temperature anomaly areas. The color mapping of the heat map adopts a gradient scheme from blue (low temperature) to red (high temperature), and the color depth of each grid point is linearly corresponding to its temperature value.

[0053] The identification of high temperature areas adopts a dual threshold judgment method, taking into account both the absolute value of temperature and the temperature gradient. The preset temperature threshold is determined according to the temperature resistance level of the robot components and is usually set to 45°C; the preset temperature gradient threshold is determined based on the thermal damage risk assessment and is used to identify areas with drastic temperature changes. When the temperature value of a certain area exceeds the preset temperature threshold and the temperature gradient of the area (i.e., the temperature change rate per unit distance) exceeds the preset gradient threshold, it is marked as a high temperature area.

[0054] S103: The overlapping area of ​​the strong light area and the high temperature area is used as a perception blind area, and the remaining area is used as a non-perception blind area.

[0055] In a factory environment, when strong light and high temperature exist at the same time, a superposition effect will occur, significantly reducing the robot's perception ability. For example, strong light will cause the visual sensor image to be overexposed, while the high temperature environment will cause the air refractive index to change, resulting in a deviation in the LiDAR ranging. When these two interference factors exist at the same time, the traditional single environmental compensation method will fail, forming an area with severely limited perception ability. Therefore, it is necessary to identify these overlapping areas and define them as perception blind spots so that special perception strategies can be adopted.

[0056] In the specific implementation, the spatial distribution data of the strong light area and the high temperature area obtained in the above steps are first processed in a unified data format. Since both data are represented by a 0.5mx0.5m grid, spatial overlap analysis can be performed directly. In a unified factory coordinate system, binary matrices A and B are established, where matrix A represents the distribution of the strong light area (strong light area is recorded as 1, and non-strong light area is recorded as 0), and matrix B represents the distribution of the high temperature area (high temperature area is recorded as 1, and non-high temperature area is recorded as 0).

[0057] The overlapping area matrix C is obtained by matrix operation C=A⊙B (where ⊙ represents the multiplication of corresponding elements of the matrix). When the value of an element in the C matrix is ​​1, it means that there is strong light and high temperature interference at the grid location at the same time, and it is marked as a perception blind area. In order to avoid the jump of the perception blind area boundary, the morphological processing method is used to smooth the perception blind area. Specifically, the structural element with a radius of 1m is used for expansion operation to ensure the continuity and safety margin of the perception blind area.

[0058] For areas where the element value in the C matrix is ​​0, that is, areas where there is no overlap of strong light and high temperature, they are marked as non-perception blind areas. Although these areas may have strong light or high temperature interference alone, the robot can still guarantee basic perception capabilities through a single environmental compensation strategy. For the convenience of subsequent processing, the factory environment is divided into three types of areas: perception blind areas (areas where strong light and high temperature overlap), partially restricted areas (areas where only strong light or high temperature exists), and normal perception areas (areas where there is neither strong light nor high temperature).

[0059] S104, evaluating the perception ability level of each robot based on the metal dust concentration data, and treating robots whose perception ability level is greater than a preset level and located in a non-perception blind spot as collaborative robots.

[0060] Metal dust in the factory environment can block and scatter the robot's visual sensors, lidar and other sensing devices, reducing the perception accuracy. The higher the metal dust concentration, the greater the impact on the sensing devices. Therefore, it is necessary to evaluate the perception capabilities of each robot based on the metal dust concentration data in order to select the appropriate collaborative robot to participate in the obstacle detection task.

[0061] First, the metal dust concentration data at each robot's location is analyzed in a time window. The time window length is set to 10s, and the statistical characteristics of the dust concentration data within the window are calculated, including the mean μ, standard deviation σ, and coefficient of variation CV (CV=σ / μ). These statistical characteristics reflect the degree of dust pollution and its stability in the robot's environment.

[0062] Based on these statistical characteristics, a robot perception ability evaluation formula is established. The formula adopts a weighted scoring method, and the specific calculation formula is: Perception ability score S = w1×(1-μ / μmax)+w2×(1-σ / σmax)+w3×(1-CV / CVmax); where w1, w2, and w3 are weight coefficients, which are set to 0.5, 0.3, and 0.2 after experimental optimization; μmax, σmax, and CVmax are the maximum values ​​in historical data. The closer the environmental parameters are to the ideal state (that is, the smaller the indicators are), the higher the score.

[0063] According to the perception ability score S, the robot's perception ability is divided into four levels: excellent level (S≥0.8): the performance of the perception device is almost unaffected; good level (0.6≤S<0.8): the performance of the perception device is slightly affected; general level (0.4≤S<0.6): the performance of the perception device is obviously affected; poor level (S<0.4): the performance of the perception device is seriously affected.

[0064] In this embodiment, the preset level is set to the good level, that is, the perception ability score of the collaborative robot is required to be no less than 0.6. At the same time, combined with the perception blind area distribution map obtained in the previous step, the robots that meet the following conditions are selected as collaborative robots: the perception ability level is greater than or equal to the good level (S≥0.6), located in the non-perception blind area (including some restricted areas and normal perception areas), and currently not occupied by other tasks.

[0065] In order to ensure the real-time and reliability of collaborative perception, the system updates the robot's perception ability evaluation results every 1 second and dynamically adjusts the selection of collaborative robots. When the perception ability level of a collaborative robot decreases or enters a perception blind spot, the system will automatically select other qualified robots to replace it.

[0066] Based on the above embodiment, as an optional implementation, in S104, evaluating the perception ability level of each robot according to the metal dust concentration data specifically includes S41-S42: S41, determining the dust concentration at the location of each robot according to the metal dust concentration data.

[0067] S42, determining the perception ability level of each robot according to the dust concentration, wherein the perception ability level is inversely proportional to the dust concentration.

[0068] In a factory environment, metal dust is an important environmental factor that affects the perception performance of robots. Metal dust not only interferes with the ranging accuracy of the lidar, but also reduces the imaging quality of the visual sensor. Therefore, it is necessary to dynamically evaluate the perception ability of the robot based on the dust concentration at the robot's location, so as to reasonably allocate perception tasks in the subsequent collaborative perception process.

[0069] When determining the dust concentration at the robot's location, the nearest neighbor interpolation method is used to process the dust concentration data. First, the measurement values ​​of several dust sensors closest to the robot are obtained, and then the dust concentration at the robot's location is calculated based on the spatial distance relationship between the sensor position and the robot position. To improve the accuracy of the evaluation, a distance weight factor is introduced in the calculation process so that the measurement values ​​of closer sensors have a greater influence weight.

[0070] Based on the obtained dust concentration values, a perception capability level evaluation model is established. The model divides the robot's perception capability into five levels: excellent, good, general, poor, and extremely poor. The specific grading standards are as follows: when the dust concentration is lower than 0.1 mg / m³, the perception capability level is excellent; when the dust concentration is in the range of 0.1-0.5 mg / m³, it is good; when the dust concentration is in the range of 0.5-1.0 mg / m³, it is general; when the dust concentration is in the range of 1.0-2.0 mg / m³, it is poor; when it exceeds 2.0 mg / m³, it is extremely poor. This grading method fully considers the sensitivity of different sensors to dust interference, ensuring that the evaluation results can accurately reflect the actual perception performance.

[0071] Since the perception level is inversely proportional to the dust concentration, the evaluation model uses an exponential decay function to describe this relationship. Specifically, the perception level score S can be expressed as: S=A×e^(-k×C), where A is the full score coefficient (set to 100), k is the decay coefficient (determined by experimental calibration), and C is the dust concentration value. This mathematical model not only reflects the basic law that the perception ability decreases with the increase of dust concentration, but also reflects the rapid degradation of the perception ability in the high concentration range.

[0072] S105, combining the first environment perception data sent by the collaborative robot and the second environment perception data sent by the robot in the perception blind spot, determining the position and movement state of the obstacle in the perception blind spot.

[0073] In a factory environment, since robots in the blind spot are subject to dual interference from strong light and high temperature, their environmental perception data has great uncertainty. In order to accurately detect obstacles in the blind spot, it is necessary to integrate and analyze the environmental perception data of the collaborative robot and the robot in the blind spot, making full use of the complementary advantages of different perspectives and different sensors to improve the reliability of obstacle detection.

[0074] First, the first environmental perception data sent by the collaborative robot is preprocessed. The first environmental perception data includes lidar point cloud data (scanning frequency 10Hz, angular resolution 0.25°) and visual image data (resolution 1920×1080, frame rate 30fps). The point cloud data is spatially filtered and downsampled to remove outliers and reduce data redundancy; the visual image is distorted and compensated for illumination to improve image quality.

[0075] At the same time, the second environment perception data sent by the perception blind spot robot is processed. Although the second environment perception data is greatly affected by environmental interference, it still contains valuable information, mainly including degraded point cloud data and blurred visual images. Adaptive threshold processing method is used for these data to extract key information that may contain obstacle features.

[0076] In order to achieve the spatiotemporal alignment of multi-source data, a unified spatiotemporal reference system is established. In the time dimension, the timestamp alignment technology is used to synchronize the data of different sensors to a unified time reference; in the spatial dimension, all perception data are converted to the factory global coordinate system through robot pose estimation and coordinate transformation.

[0077] In the data fusion stage, an improved probability hypothesis density (PHD) filtering algorithm is used for multi-sensor data fusion. This algorithm can simultaneously handle multiple sources of uncertainty, including perception noise, detection probability changes, and false alarms. The specific fusion process includes the following steps: Feature extraction: Extract the geometric features (size, shape) and motion features (speed, acceleration) of obstacles from the first environment perception data as observations with higher reliability.

[0078] State estimation: Combine the fuzzy features extracted from the second environment perception data to establish an obstacle state estimation model. The state vector includes position coordinates (x, y), velocity components (vx, vy) and acceleration components (ax, ay).

[0079] Dynamic update: Use the PHD filter to recursively update the obstacle state estimation. The filter's measurement update weight is dynamically adjusted according to the data reliability, where the weight of the first environment perception data is higher (usually 0.7-0.9) and the weight of the second environment perception data is lower (usually 0.1-0.3).

[0080] To improve real-time performance, a parallel computing architecture is used to implement the data fusion algorithm. Feature extraction and state estimation tasks are assigned to multiple processing cores, and GPU is used to accelerate matrix operations to control the single fusion processing delay within 50ms.

[0081] Based on the above embodiment, as an optional implementation, in S105, combining the first environment perception data sent by the collaborative robot and the second environment perception data sent by the robot in the perception blind spot, determining the position and motion state of the obstacle in the perception blind spot specifically includes S51-S54: S51: Use the first environmental perception data as primary perception data and use the second environmental perception data as auxiliary perception data.

[0082] S52: Determine the initial position and initial motion state of the obstacle in the perception blind spot based on the main perception data.

[0083] S53, correcting the initial position and the initial motion state according to the auxiliary perception data to obtain a corrected target obstacle position and target motion state.

[0084] S54: taking the target obstacle position and the target motion state as the obstacle position and motion state in the perception blind area.

[0085] In a factory where multiple robots work together, due to the influence of strong light, high temperature, metal dust and other factors, a single robot often has a blind spot in perception and cannot accurately perceive obstacles in the environment. In order to ensure the safety and reliability of the robot system, it is necessary to use the perception data of different robots through multi-robot collaborative perception to achieve accurate positioning and motion state estimation of obstacles in the blind spot.

[0086] During data processing, the first environmental perception data sent by the collaborative robot is used as the main perception data. This is because the collaborative robot is in an area with better environmental conditions, and its perception data has higher accuracy and reliability. The second environmental perception data sent by the robot in the perception blind spot is used as auxiliary perception data. Although its perception ability is limited, this data still contains valuable environmental information and can be used to verify and supplement the observation results of the main perception data.

[0087] When determining the initial position and initial motion state of the obstacle based on the main perception data, the Kalman filter algorithm is used for target tracking. Through the two stages of prediction and update, this algorithm can effectively process the noise in the perception data and provide the optimal estimate of the obstacle position and velocity. In specific implementation, the motion state equation and observation equation of the obstacle are established, where the state vector contains the two-dimensional coordinate position and velocity components of the obstacle. The initial position coordinates (x 0 ,y 0 ) and the initial velocity vector (vx 0 ,vy 0 ).

[0088] When using auxiliary perception data for correction, a confidence-based data verification method is used. First, the difference between the two sets of perception data is calculated. When the difference exceeds the preset threshold, the anomaly detection mechanism is triggered. The reliability of the data is judged by analyzing the temporal consistency, spatial continuity, and conformity with historical data of the two sets of data. If the main perception data is judged to be reliable, its results are directly used; if an anomaly is found, it is necessary to conduct in-depth analysis in combination with the auxiliary perception data, and re-evaluate the position and motion state of the obstacle through the state estimator.

[0089] S106, constructing an obstacle avoidance map according to the position and motion state of the obstacle, and planning an obstacle avoidance path for the cargo robot to cross the perception blind spot according to the obstacle avoidance map.

[0090] In a factory environment, cargo robots need to safely and efficiently cross blind spots, which requires building a dynamic obstacle avoidance map based on the obstacle information obtained in the previous steps and planning a suitable obstacle avoidance path accordingly. Since obstacles in blind spots may be in motion, traditional static map planning methods are difficult to ensure the safety and executability of the planned path.

[0091] First, a dynamic obstacle avoidance map based on probability grids is constructed. The factory environment is divided into uniform grids, each of which contains two attributes: occupancy probability value and dynamic risk value. The occupancy probability value reflects the possibility that the grid is occupied by an obstacle, and the value range is [0,1]; the dynamic risk value represents the comprehensive risk level after considering the movement state of the obstacle. This calculation method ensures that the obstacle area with faster movement speed or greater acceleration has a higher risk value.

[0092] In order to deal with the uncertainty of obstacle movement, a spatiotemporal probability prediction method is used to update the obstacle avoidance map. Based on the current movement state of the obstacle, an improved Kalman filter is used to predict the possible position distribution in the future. The prediction results are mapped to the grid map through a Gaussian probability model to form a time-varying risk distribution. Considering that the uncertainty of the prediction increases with time, a time decay factor is introduced to attenuate the impact of the long-term prediction results.

[0093] Based on the obstacle avoidance map, the improved spatiotemporal RRT* (Rapidly-exploring Random Tree*) algorithm is used for path planning. This algorithm adds the time dimension to the traditional RRT*, so that the planned path can actively avoid high-risk areas. A safe movement path is constructed through three main steps: random sampling, extended tree growth, and path optimization. Among them, the cost function comprehensively considers the path length, dynamic risk accumulation value, and time penalty term, and determines the optimal path through a multi-objective optimization method.

[0094] To improve planning efficiency, an adaptive sampling strategy is adopted. In the initial planning stage, a larger sampling step size is used to quickly find a feasible solution, and then a smaller sampling step size is used in key areas (such as turning points and crossing points) to refine the path. At the same time, parallel computing technology is used to accelerate the path search process and ensure the real-time planning.

[0095] Based on the above embodiment, as an optional implementation, in S106, constructing an obstacle avoidance map according to the position and motion state of the obstacle specifically includes S61-S64: S61, predicting the movement trajectory of the obstacle within a preset time period according to the position and movement state of the obstacle.

[0096] S62, mapping the motion trajectory to the regional coordinate system of the factory to obtain the obstacle impact area.

[0097] S63, determining the risk level of each area in the factory based on the obstacle impact area and the distribution locations of multiple devices in the factory.

[0098] S64: Generate an obstacle avoidance map according to the risk level.

[0099] First, based on the acquired obstacle position (x, y) and motion state (vx, vy), the kinematic model is used to predict the movement trajectory of the obstacle in the future time period. Considering the movement characteristics of obstacles (such as forklifts, workers, etc.) in the factory environment, the trajectory prediction is carried out by combining the uniform motion model and the steering constraint model. The prediction time period is set to 10 seconds, and the time step is 100 milliseconds for discretization. For each time step, the predicted position of the obstacle is calculated: x(t)=x+vx×t+0.5×ax×t², y(t)=y+vy×t+0.5×ay×t², where ax and ay are the acceleration components of the obstacle, which are estimated from historical data.

[0100] When mapping the predicted motion trajectory to the regional coordinate system of the factory, the actual size of the obstacle and the safety margin need to be considered. Based on the outer contour of the obstacle, the safety distance (usually set to 0.5 meters) is extended outward to form the obstacle impact area. This area is represented by a polygon, and its vertex coordinates are calculated by combining the obstacle trajectory points and the safety margin. To improve computational efficiency, the convex hull algorithm is used to simplify the geometric representation of the impact area.

[0101] When determining the risk level of each area in the factory, three key factors are considered comprehensively: the area affected by obstacles, the distribution location of factory equipment, and the functional attributes of the area. The risk level is divided into four levels: dangerous area, high-risk area, medium-risk area, and safe area. The area within the obstacle impact area is automatically classified as a dangerous area; the area adjacent to high-value equipment (such as precision processing equipment) is classified as a high-risk area; the channel area with frequent personnel flow is classified as a medium-risk area; and the rest of the area is a safe area. At the same time, considering the dynamic changes in the operating status of the equipment, the system will update the risk assessment results of each area in real time.

[0102] Based on the risk level information, the system generates a rasterized obstacle avoidance map. The factory plane is divided into grid cells of 0.1 m × 0.1 m in size, and each grid cell is assigned a corresponding risk cost value: the danger zone is infinite (indicating that passage is prohibited), the high-risk zone is 80, the medium-risk zone is 40, and the safe zone is 10. In order to make the obstacle avoidance map smoother, the Gaussian fuzzy algorithm is used to locally smooth the risk cost to avoid drastic changes in direction during robot path planning.

[0103] After planning an obstacle avoidance path for the cargo robot to cross the perception blind spot according to the obstacle avoidance map, it also includes: establishing a communication network among multiple cargo robots in the perception blind spot; and allocating a time window for crossing the perception blind spot to each cargo robot according to the task priority of each cargo robot.

[0104] When establishing a communication network in the blind spot, a distributed self-organizing network architecture is adopted. Each cargo robot is equipped with a wireless communication module and uses industrial-grade WiFi protocol for data transmission. The communication content includes key information such as the robot's real-time position, speed, task status, and planned path. To ensure the real-time and reliability of communication, time division multiple access (TDMA) is used for channel allocation, and each robot is allocated a fixed time segment for data broadcasting. At the same time, a communication redundancy mechanism is set up. When the communication module of a robot fails, the adjacent robot can act as a relay node to maintain the connectivity of the network.

[0105] When determining the task priority of cargo robots, multiple factors are considered: task urgency, cargo importance, energy consumption, and path length. Robots with urgent tasks (such as transporting perishables or key production materials) are given higher priority; robots carrying important cargo (such as valuable or fragile items) are given a lower priority; robots with low battery power are given a relatively higher priority to avoid running out of energy in their blind spots; robots with shorter planned paths are also given a higher priority to improve traffic efficiency. The system calculates a comprehensive priority score based on these factors, ranging from 0 to 100, with higher scores indicating higher priority.

[0106] Based on the calculated priority, the system adopts a dynamic time window allocation strategy. First, the process of crossing the perception blind area is divided into multiple time windows, and the duration of each window is determined by the length of the area and the standard driving speed of the robot. To avoid interference between robots, a safety interval (usually 2 seconds) is set between adjacent time windows. High-priority robots give priority to the earliest available time window, and the system will reserve some emergency time windows to handle emergencies. To improve traffic efficiency, robots with similar priorities and non-intersecting paths are allowed to pass at the same time.

[0107] Based on the above method, the present application also discloses a robot obstacle detection system in a smart factory environment, such as Figure 2 As shown, Figure 2 : is a schematic diagram of the structure of a robot obstacle detection system in a smart factory environment provided by an embodiment of the present application. The system includes: an acquisition module, a determination module, an output module, an evaluation module, a combination module and a generation module; wherein, An acquisition module is used to acquire temperature distribution data, metal dust concentration data and light intensity data sent by multiple robots in the factory; a determination module is used to determine the strong light area of ​​the factory based on the light intensity data, and to determine the high temperature area of ​​the factory based on the temperature distribution data; an output module is used to use the overlapping area of ​​the strong light area and the high temperature area as a perception blind area, and the remaining area as a non-perception blind area; an evaluation module is used to evaluate the perception ability level of each robot based on the metal dust concentration data, and to use the robot whose perception ability level is greater than the preset level and is located in the non-perception blind area as a collaborative robot; a combination module is used to combine the first environmental perception data sent by the collaborative robot and the second environmental perception data sent by the robot in the perception blind area to determine the position and motion status of obstacles in the perception blind area; a generation module is used to construct an obstacle avoidance map based on the obstacle position and motion status, and plan an obstacle avoidance path for the cargo robot to cross the perception blind area based on the obstacle avoidance map.

[0108] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0109] See also Figure 3 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0110] The communication bus 1002 is used to realize the connection and communication between these components.

[0111] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0112] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0113] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0114] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may optionally also be at least one storage device located away from the aforementioned processor 1001. As Figure 3 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a robot obstacle detection method in a smart factory environment.

[0115] exist Figure 3 In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 1001 can be used to call an application program stored in the memory 1005 for a robot obstacle detection method in a smart factory environment. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0116] An electronic device readable storage medium stores instructions, which, when executed by one or more processors, enable the electronic device to execute one or more of the methods described in the above embodiments.

[0117] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0118] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0119] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0120] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0122] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0123] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A robot obstacle detection method in a smart factory environment, characterized in that: The method comprises: Obtain temperature distribution data, metal dust concentration data, and light intensity data sent by multiple robots in the factory; Determine the strong light area of ​​the factory according to the light intensity data, and determine the high temperature area of ​​the factory according to the temperature distribution data; The overlapping area of ​​the strong light area and the high temperature area is used as a perception blind area, and the remaining area is used as a non-perception blind area; According to the metal dust concentration data, the perception ability level of each of the robots is evaluated, and the robots whose perception ability level is greater than a preset level and located in the non-perception blind area are regarded as collaborative robots; Determine the position and motion state of obstacles in the perception blind spot by combining the first environment perception data sent by the collaborative robot and the second environment perception data sent by the robot in the perception blind spot; An obstacle avoidance map is constructed according to the obstacle position and the motion state, and an obstacle avoidance path is planned for the cargo robot to cross the perception blind spot according to the obstacle avoidance map.

2. The robot obstacle detection method in a smart factory environment according to claim 1, characterized in that: Determining the strong light area of ​​the factory according to the light intensity data includes: Performing time-domain filtering on the light intensity data to obtain target light intensity data; According to the target light intensity data, a light intensity distribution matrix is ​​established; According to the light intensity distribution matrix, each area in the factory is divided into different light levels; The area where the light level is greater than the preset level is determined as a strong light area.

3. The robot obstacle detection method in a smart factory environment according to claim 1, characterized in that: Determining the high temperature area of ​​the factory according to the temperature distribution data includes: Performing spatial interpolation on the temperature distribution data to obtain a temperature distribution thermodynamic map of the factory area; According to the temperature distribution thermodynamic map, a region where the temperature is higher than a preset temperature threshold and the temperature gradient is greater than a preset gradient threshold is determined as a high temperature region.

4. The robot obstacle detection method in a smart factory environment according to claim 1, characterized in that: The step of evaluating the perception capability level of each robot according to the metal dust concentration data includes: Determining the dust concentration at the location of each of the robots according to the metal dust concentration data; The perception capability level of each of the robots is determined according to the dust concentration, wherein the perception capability level is inversely proportional to the dust concentration.

5. The robot obstacle detection method in a smart factory environment according to claim 1, characterized in that: The combining the first environment perception data sent by the collaborative robot and the second environment perception data sent by the robot in the perception blind zone to determine the position and motion state of the obstacle in the perception blind zone includes: Using the first environmental perception data as primary perception data and using the second environmental perception data as auxiliary perception data; Determining the initial position and initial motion state of the obstacle in the perception blind area according to the main perception data; Correcting the initial position and the initial motion state according to the auxiliary sensing data to obtain a corrected target obstacle position and target motion state; The target obstacle position and the target motion state are used as the obstacle position and motion state in the perception blind area.

6. The robot obstacle detection method in a smart factory environment according to claim 1, characterized in that: The step of constructing an obstacle avoidance map according to the obstacle position and the motion state includes: Predicting the movement trajectory of the obstacle within a preset time period according to the obstacle position and the movement state; Mapping the motion trajectory into the regional coordinate system of the factory to obtain the obstacle impact area; Determine the risk level of each area in the factory based on the obstacle impact area and the distribution locations of multiple devices in the factory; An obstacle avoidance map is generated according to the risk level.

7. The robot obstacle detection method in a smart factory environment according to claim 1, characterized in that: After planning an obstacle avoidance path for the cargo robot to cross the perception blind spot according to the obstacle avoidance map, the method further includes: Establishing a communication network among the multiple cargo robots in the perception blind area; According to the task priority of each cargo robot, a time window for crossing the perception blind area is allocated to each cargo robot.

8. A robot obstacle detection system in a smart factory environment, characterized in that: The system includes: an acquisition module, a determination module, an output module, an evaluation module, a combination module and a generation module; wherein, The acquisition module is used to acquire temperature distribution data, metal dust concentration data and light intensity data sent by multiple robots in the factory; The determination module is used to determine the strong light area of ​​the factory according to the light intensity data, and to determine the high temperature area of ​​the factory according to the temperature distribution data; The output module is used to use the overlapping area of ​​the strong light area and the high temperature area as a perception blind area, and the remaining area as a non-perception blind area; The evaluation module is used to evaluate the perception ability level of each of the robots according to the metal dust concentration data, and to select the robots whose perception ability level is greater than a preset level and located in the non-perception blind area as collaborative robots; The combining module is used to combine the first environment perception data sent by the collaborative robot and the second environment perception data sent by the robot in the perception blind zone to determine the position and motion state of the obstacle in the perception blind zone; The generation module is used to construct an obstacle avoidance map according to the obstacle position and the motion state, and plan an obstacle avoidance path for the cargo robot to cross the perception blind spot according to the obstacle avoidance map.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 7.

Images