Simulation experiment method and system based on unmanned sweeper simulation

Abstract

The invention discloses a simulation experiment method and system based on unmanned motor sweeper simulation, and relates to the technical field of vehicle simulation testing, and the method comprises the steps: obtaining the working data of an unmanned motor sweeper, obtaining the working mode information according to the working data of the unmanned motor sweeper, classifying the working data of the unmanned motor sweeper with a working mode as a reference, and obtaining the working mode information of the unmanned motor sweeper; and obtaining work data classification information. The working data of different working modes are classified, the data analysis efficiency is improved, the subsequent data processing step is facilitated, the driving conditions of the unmanned sweeper under different road conditions are accurately analyzed through the working sub-data sets in the moving mode, and the working efficiency of the unmanned sweeper is improved. According to the method, a reference is provided for the analysis of the working condition of the unmanned sweeper in other subsequent modes, a data basis is provided for the simulation of the unmanned sweeper through the mode characteristic data corresponding to each working mode, the simulation efficiency of the unmanned sweeper is improved, and the stability and reliability of the operation of the unmanned sweeper are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle simulation testing, and specifically relates to a simulation experiment method and system based on the simulation of a driverless sweeper vehicle. Background Art

[0002] At present, the application of autonomous driving technology in ground vehicles has gradually matured. Autonomous driving technology has the characteristics of high efficiency, safety, and can extend the service life of vehicles. Applying autonomous driving technology to sweeper vehicles can replace drivers, greatly increasing the working hours of sweeper vehicles and ensuring that the sweeper vehicles can continuously maintain the cleanliness of the regional environment. Therefore, in the current process of urban environment maintenance and intelligent transportation development, the application of driverless sweeper vehicles has gradually become popular. With the continuous improvement of technology maturity, driverless sweeper vehicles integrated with advanced technologies such as high-definition cameras, lidar, and ultrasonic sensors have achieved high-precision positioning and perception of obstacle avoidance, and their performance is more stable. Therefore, driverless sweeper vehicles have been widely used in scenarios such as municipal roads, campuses, communities, parks, and scenic spots. To avoid resource waste during the R & D of driverless sweeper vehicles, simulation experiments are often carried out on driverless sweeper vehicles during the R & D process.

[0003] Currently, there are still problems in the simulation experiment of driverless sweeper vehicle simulation, such as the inability to accurately evaluate the daily working data of driverless sweeper vehicles, and the inability to construct a simulation scenario based on the working data that can accurately test the performance of driverless sweeper vehicles. Traditional testing methods mainly rely on on-road testing, but on-road testing is limited by environmental conditions, high costs, and it is difficult to comprehensively cover various working conditions. In the vehicle design stage, there is a lack of efficient virtual verification means, making it difficult to quickly evaluate and optimize different design schemes. However, if a virtual scenario is directly established based on the working data, not only is the data processing volume large, but the test data during the simulation experiment is also relatively large, and it is impossible to quickly identify the data representing the performance of the driverless sweeper vehicle, reducing the R & D efficiency and operational reliability of the driverless sweeper vehicle. Summary of the Invention

[0004] To solve the above technical problems, a simulation experiment method and system based on the simulation of a driverless sweeper vehicle are provided. This technical solution solves the problems mentioned in the above background art, such as the inability to accurately evaluate the daily working data of driverless sweeper vehicles, the inability to construct a simulation scenario based on the working data that can accurately test the performance of driverless sweeper vehicles. Traditional testing methods mainly rely on on-road testing, but on-road testing is limited by environmental conditions, high costs, and it is difficult to comprehensively cover various working conditions. In the vehicle design stage, there is a lack of efficient virtual verification means, making it difficult to quickly evaluate and optimize different design schemes. However, if a virtual scenario is directly established based on the working data, not only is the data processing volume large, but the test data during the simulation experiment is also relatively large, and it is impossible to quickly identify the data representing the performance of the driverless sweeper vehicle, reducing the R & D efficiency and operational reliability of the driverless sweeper vehicle.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows: A simulation experiment method based on the simulation of an unmanned cleaning vehicle, comprising: Obtaining the working data of the unmanned cleaning vehicle, where the working data of the unmanned cleaning vehicle includes environmental landscape data, cleaning vehicle working parameters, and map data; According to the working data of the unmanned cleaning vehicle, obtaining working mode information, where the working modes include a cleaning mode, an obstacle avoidance mode, and a moving mode; Taking the working mode as a reference, classifying the working data of the unmanned cleaning vehicle to obtain working data classification information; According to the working mode information and the working data classification information, obtaining the mode feature data corresponding to each working mode; According to the mode feature data, obtaining the corresponding environmental landscape data and map data; Taking the environmental landscape data and the map data as a reference, constructing a three-dimensional scene to obtain simulation experiment scene information; Taking the simulation experiment scene as a reference, conducting a simulation experiment on the unmanned cleaning vehicle.

[0006] Preferably, the obtaining the mode feature data corresponding to each working mode according to the working mode information and the working data classification information specifically includes: According to the working data classification information, dividing the working data of the unmanned cleaning vehicle corresponding to the same working mode into the same data group to obtain the mode working data group corresponding to each working mode; Obtaining the moving mode working data group, where the moving mode working data group represents the mode working data corresponding to the unmanned cleaning vehicle in the moving mode; Taking the road type corresponding to each data in the moving mode working data group as a reference, further dividing the moving mode working data group to obtain the moving mode working sub-data group, where the road types include flat roads, slope roads, and curved roads; According to the moving mode working sub-data group, obtaining the moving mode feature data; Based on the cleaning mode working data group, obtaining the cleaning mode feature data, where the cleaning mode working data group represents the mode working data corresponding to the unmanned cleaning vehicle in the cleaning mode; According to the obstacle avoidance mode working data group, obtaining the obstacle avoidance path information corresponding to each mode working data; Taking the obstacle avoidance path information as a basis, obtaining the obstacle avoidance mode feature data; According to the moving mode feature data, the cleaning mode feature data, and the obstacle avoidance mode feature data, obtaining the mode feature data.

[0007] Preferably, obtaining the mobile mode feature data according to the mobile mode working sub-data group specifically includes: Obtain the performance design parameters of the unmanned sweeper, where the performance design parameters of the unmanned sweeper include standard speed information, standard energy consumption information, and standard cleaning coverage rate; Based on the performance design parameters of the unmanned sweeper, obtain the standard energy consumption ratio coefficient, where the standard energy consumption ratio represents the proportional coefficient of the speed to the energy consumption of the unmanned sweeper; Taking the standard energy consumption ratio coefficient as a benchmark, obtain the weight coefficients of the speed and energy consumption of the unmanned sweeper; According to the mobile mode working sub-data group corresponding to the flat road, take the product of the speed of the unmanned sweeper and the corresponding weight coefficient as the speed quantity of the unmanned sweeper, and take the product of the energy consumption of the unmanned sweeper and the corresponding weight coefficient as the energy consumption quantity of the unmanned sweeper; Take the ratio of the speed quantity of the unmanned sweeper to the energy consumption quantity of the unmanned sweeper as the calibration coefficient of the flat road; Take the mobile mode working sub-data group corresponding to the maximum value of the calibration coefficient of the flat road in the mobile mode working sub-data group corresponding to the flat road as the flat road feature data; Based on the mobile mode working sub-data group corresponding to the flat road, obtain the slope road feature data and the curved road feature data; According to the flat road feature data, slope road feature data, and curved road feature data, obtain the mobile mode feature data.

[0008] Preferably, obtaining the slope road feature data and the curved road feature data based on the mobile mode working sub-data group corresponding to the flat road specifically includes: Based on the mobile mode working sub-data group corresponding to the flat road, obtain the maximum and minimum speeds of the unmanned sweeper on the flat road; Take the maximum and minimum speeds of the unmanned sweeper on the flat road as the benchmark speed threshold of the unmanned sweeper; Remove the data in the mobile mode working sub-data groups corresponding to the slope road and the curved road where the speed of the unmanned sweeper does not exceed the benchmark speed threshold of the unmanned sweeper, and obtain the mobile mode feature data group; Taking the mobile mode feature data group corresponding to the slope road as a benchmark, obtain the speed quantity of the slope unmanned sweeper and the energy consumption quantity of the slope unmanned sweeper; Take the sum of the speed quantity of the slope unmanned sweeper and the energy consumption quantity of the slope unmanned sweeper as the calibration coefficient of the slope road; Take the mobile mode working sub-data group corresponding to the maximum value of the calibration coefficient of the slope road in the mobile mode working sub-data group corresponding to the slope road as the slope road feature data; Based on the flat road feature data, the speed of the unmanned sweeper corresponding to the flat road feature data is used as the characteristic speed of the unmanned sweeper; Based on the mobile mode feature data group corresponding to the curved road, the speed change information of the unmanned sweeper corresponding to each data is obtained, and the speed change information of the unmanned sweeper represents the speed change condition of the unmanned sweeper when passing through the curved road; According to the speed change information of the unmanned sweeper, the maximum and minimum speeds of the unmanned sweeper corresponding to each data in the mobile mode feature data group are obtained; The sum of the differences between the maximum and minimum speeds of the unmanned sweeper and the characteristic speed of the unmanned sweeper respectively is used as the calibration coefficient of the curved road; The mobile mode working sub-data group corresponding to the maximum calibration coefficient of the curved road in the mobile mode working sub-data group corresponding to the curved road is used as the curved road feature data.

[0009] Preferably, obtaining the cleaning mode feature data based on the cleaning mode working data group specifically includes: Based on the cleaning mode working data group, the cleaning coverage rate corresponding to each mode working data is obtained; According to the mobile mode feature data, based on the proportional relationship between the speed and energy consumption of the unmanned sweeper, the mobile energy consumption ratio coefficient corresponding to each mobile mode feature data is obtained; According to the performance design parameters of the unmanned sweeper, the standard cleaning energy consumption information of the unmanned sweeper is obtained; The standard energy consumption ratio coefficient is obtained, and the ratio of the mobile energy consumption ratio coefficient to the standard energy consumption ratio coefficient is used as the energy consumption difference coefficient; The average value of the energy consumption difference coefficients corresponding to the mobile mode feature data is used as the coefficient difference reference value; The ratio of the cleaning coverage rate corresponding to each mode working data in the cleaning mode working data group to the standard cleaning coverage rate is used as the cleaning difference coefficient; According to the cleaning mode working data group, the characteristic energy consumption ratio coefficient corresponding to each mode working data is obtained, and the characteristic energy consumption ratio represents the proportional coefficient of the speed and energy consumption of the unmanned sweeper in the cleaning mode working data group; The ratio of the characteristic energy consumption ratio coefficient to the coefficient difference reference value is used as the energy consumption difference coefficient; The product of the energy consumption difference coefficient and the cleaning difference coefficient is used as the cleaning characteristic coefficient; The mode working data corresponding to the minimum cleaning characteristic coefficient in the cleaning mode working data group is used as the cleaning mode feature data.

[0010] Preferably, obtaining the obstacle avoidance mode feature data based on the obstacle avoidance path information specifically includes: Obtain the obstacle avoidance planning path information of the unmanned sweeper corresponding to the working data of each mode according to the obstacle avoidance mode working data group; Match the obstacle avoidance planning path information of the unmanned sweeper with the obstacle avoidance path information to obtain the obstacle avoidance path comparison information; According to the obstacle avoidance path comparison information, obtain the starting point and ending point of the obstacle avoidance planning path and the starting point and ending point of the obstacle avoidance path; Take the sum of the distance between the starting point of the obstacle avoidance planning path and the starting point of the obstacle avoidance path and the distance between the ending point of the obstacle avoidance planning path and the ending point of the obstacle avoidance path as the reference offset; Obtain the obstacle avoidance planning path length information and the obstacle avoidance path length information; Take the ratio of the reference offset to the obstacle avoidance planning path length as the path basic offset coefficient; Take the ratio of the obstacle avoidance path length to the obstacle avoidance planning path length as the obstacle avoidance path comparison coefficient; Take the product of the path basic offset coefficient and the obstacle avoidance path comparison coefficient as the obstacle avoidance feature coefficient; Take the mode working data corresponding to the largest obstacle avoidance feature coefficient in the obstacle avoidance mode working data group as the obstacle avoidance mode feature data.

[0011] Furthermore, a simulation experiment system based on the unmanned sweeper simulation is proposed for implementing the simulation experiment method as described above, including: The main control module is used to obtain the cleaning mode feature data based on the cleaning mode working data group, obtain the obstacle avoidance path information corresponding to each mode working data according to the obstacle avoidance mode working data group, obtain the obstacle avoidance mode feature data based on the obstacle avoidance path information, obtain the corresponding environmental landscape data and map data according to the mode feature data, and perform three-dimensional scene construction based on the environmental landscape data and map data to obtain the simulation experiment scene information, and perform simulation experiments on the unmanned sweeper with the simulation experiment scene; The information acquisition module is used to acquire the working data of the unmanned sweeper. The working data of the unmanned sweeper includes environmental landscape data, sweeper working parameters, and map data. According to the working data of the unmanned sweeper, obtain the working mode information, obtain the performance design parameters of the unmanned sweeper. The performance design parameters of the unmanned sweeper include standard speed information, standard energy consumption information, and standard cleaning coverage rate. Based on the performance design parameters of the unmanned sweeper, obtain the standard energy consumption ratio coefficient; A data recognition module, which is used to divide the unmanned sweeper working data corresponding to the same working mode into the same data group according to the working data classification information, obtain the mode working data group corresponding to each working mode, further divide the mobile mode working data group based on the road type corresponding to each data in the mobile mode working data group to obtain the mobile mode working sub-data group, obtain the weight coefficient of the unmanned sweeper speed and energy consumption based on the standard energy consumption ratio coefficient, obtain the flat road characteristic data according to the weight coefficient of the unmanned sweeper speed and energy consumption, and obtain the slope road characteristic data and the curved road characteristic data based on the mobile mode working sub-data group corresponding to the flat road. A display module, which interacts with the main control module and is used to output and display the working data classification information, the mobile mode characteristic data, the cleaning mode characteristic data, the obstacle avoidance mode characteristic data, and the simulation experiment scenario information.

[0012] Optionally, the main control module specifically includes: A control unit, which is used to obtain the corresponding environmental landscape data and map data according to the mode characteristic data, construct a three-dimensional scene based on the environmental landscape data and map data to obtain the simulation experiment scenario information, and perform a simulation experiment on the unmanned sweeper with the simulation experiment scenario. An information receiving unit, which interacts with the information acquisition module and the data recognition module and is used to receive data and transmit it to the data processing unit. A data processing unit, which is used to obtain the cleaning mode characteristic data based on the cleaning mode working data group, obtain the obstacle avoidance path information corresponding to each mode working data according to the obstacle avoidance mode working data group, and obtain the obstacle avoidance mode characteristic data based on the obstacle avoidance path information.

[0013] Optionally, the information acquisition module specifically includes: A first acquisition unit, which is used to acquire the unmanned sweeper working data, where the unmanned sweeper working data includes environmental landscape data, sweeper working parameters, and map data, and obtain the working mode information according to the unmanned sweeper working data. A second acquisition unit, which is used to acquire the unmanned sweeper performance design parameters, where the unmanned sweeper performance design parameters include standard speed information, standard energy consumption information, and standard cleaning coverage rate, and obtain the standard energy consumption ratio coefficient based on the unmanned sweeper performance design parameters.

[0014] Optionally, the data recognition module specifically includes: The first recognition unit is configured to divide the work data of the unmanned sweeper corresponding to the same work mode into the same data group according to the work data classification information, obtain the mode work data group corresponding to each work mode, and further divide the mobile mode work data group based on the road type corresponding to each data in the mobile mode work data group to obtain the mobile mode work sub-data group. The second recognition unit is configured to obtain the weight coefficient of the speed and energy consumption of the unmanned sweeper based on the standard energy consumption ratio coefficient, obtain the flat road characteristic data according to the weight coefficient of the speed and energy consumption of the unmanned sweeper, and obtain the slope road characteristic data and the curved road characteristic data based on the mobile mode work sub-data group corresponding to the flat road.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a simulation experiment method and system based on unmanned sweeper simulation. By classifying the work data of different work modes, the data analysis efficiency is improved, which is convenient for subsequent data processing steps. By analyzing the mobile mode work sub-data group, the driving conditions of the unmanned sweeper under different road conditions are accurately analyzed, providing a benchmark for the analysis of the work conditions of the unmanned sweeper in other subsequent modes. Based on the mode characteristic data corresponding to each work mode, a data basis is provided for the simulation of the unmanned sweeper, improving the simulation efficiency of the unmanned sweeper and ensuring the stability and reliability of the operation of the unmanned sweeper. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of a simulation experiment method based on unmanned sweeper simulation proposed by the present invention; Figure 2 It is a flowchart of obtaining mode characteristic data in the present invention; Figure 3 It is a flowchart of obtaining mobile mode characteristic data in the present invention; Figure 4 It is a flowchart of obtaining cleaning mode characteristic data in the present invention; Figure 5 It is a structural block diagram of a simulation experiment system based on unmanned sweeper simulation proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations.

[0018] Referring to Figure 1 - Figure 4 As shown, a simulation experiment method based on unmanned sweeper simulation in an embodiment of the present invention includes: Obtain the working data of the unmanned sweeper, where the working data of the unmanned sweeper includes environmental landscape data, sweeper working parameters, and map data; Obtain the working mode information according to the working data of the unmanned sweeper, where the working modes include a cleaning mode, an obstacle avoidance mode, and a moving mode; Classify the working data of the unmanned sweeper based on the working mode to obtain the classified information of the working data; Obtain the mode feature data corresponding to each working mode according to the working mode information and the classified information of the working data; Specifically, obtaining the mode feature data corresponding to each working mode according to the working mode information and the classified information of the working data specifically includes: According to the classified information of the working data, divide the working data of the unmanned sweeper corresponding to the same working mode into the same data group to obtain the mode working data group corresponding to each working mode; Obtain the moving mode working data group, where the moving mode working data group represents the mode working data corresponding to the unmanned sweeper in the moving mode; Based on the road type corresponding to each data in the moving mode working data group, further divide the moving mode working data group to obtain the moving mode working sub-data group, where the road types include flat roads, slope roads, and curved roads; Obtain the moving mode feature data according to the moving mode working sub-data group; Based on the cleaning mode working data group, obtain the cleaning mode feature data, where the cleaning mode working data group represents the mode working data corresponding to the unmanned sweeper in the cleaning mode; According to the obstacle avoidance mode working data group, obtain the obstacle avoidance path information corresponding to each mode working data; Based on the obstacle avoidance path information, obtain the obstacle avoidance mode feature data; Obtain the mode feature data according to the moving mode feature data, the cleaning mode feature data, and the obstacle avoidance mode feature data.

[0019] In this solution, the working data of the unmanned sweeper corresponding to the same working mode is divided into the same data group, and the mode working data group corresponding to each working mode is obtained. Based on the road type corresponding to each data in the mobile mode working data group, the mobile mode working data group is further divided to obtain the mobile mode sub-working data group. According to the mobile mode sub-working data group, the mobile mode characteristic data is obtained. Based on the sweeping mode working data group, the sweeping mode characteristic data is obtained. Based on the obstacle avoidance path information, the obstacle avoidance mode characteristic data is obtained. For the operation parameters, the obstacle avoidance mode focuses on the sensor response time and the change of path curvature. The mobile mode separates data such as motor torque and driving speed according to the road type (flat / slope / curved), avoiding simulation errors caused by the mixing of multi-mode data. For example, in a curved road scenario, the smoothness of the steering algorithm can be evaluated separately, excluding the interference of the sweeping operation on the mobile performance.

[0020] It can be understood that the daily working data of the unmanned sweeper is often a variety of data under different working modes, different road conditions and different weather types, and it is impossible to directly analyze the working conditions of the unmanned sweeper accurately with a fixed standard or value. For example, when the unmanned sweeper is in the sweeping mode on a rainy day, the working parameters of the unmanned sweeper are related to too many variables (road conditions, weather, etc.), and it is impossible to accurately analyze the influence degree of each variable on the unmanned sweeper. Therefore, based on the mobile mode data of the unmanned sweeper on a flat road, a standard for the working parameters of the unmanned sweeper is established, providing a basis for the data analysis of the subsequent remaining modes.

[0021] Specifically, according to the mobile mode sub-working data group, the mobile mode characteristic data is obtained, which specifically includes: Obtain the performance design parameters of the unmanned sweeper, where the performance design parameters of the unmanned sweeper include standard speed information, standard energy consumption information, and standard cleaning coverage rate; Based on the performance design parameters of the unmanned sweeper, obtain the standard energy consumption ratio coefficient, where the standard energy consumption ratio represents the proportional coefficient of the speed and energy consumption of the unmanned sweeper; Based on the standard energy consumption ratio coefficient, obtain the weight coefficient of the speed and energy consumption of the unmanned sweeper; According to the mobile mode sub-working data group corresponding to the flat road, take the product of the speed of the unmanned sweeper and the corresponding weight coefficient as the speed quantity of the unmanned sweeper, and take the product of the energy consumption of the unmanned sweeper and the corresponding weight coefficient as the energy consumption quantity of the unmanned sweeper; Take the ratio of the speed quantity of the unmanned sweeper to the energy consumption quantity of the unmanned sweeper as the calibration coefficient for the flat road; Take the mobile mode sub-working data group corresponding to the maximum value of the calibration coefficient for the flat road in the mobile mode sub-working data group corresponding to the flat road as the flat road characteristic data; Based on the mobile mode working sub-data group corresponding to the flat road, obtain the ramp road feature data and the curved road feature data; According to the flat road feature data, the ramp road feature data and the curved road feature data, obtain the mobile mode feature data.

[0022] In this solution, through standardized parameter modeling, dynamic weight allocation, and multi-road condition feature extraction, accurate quantification of performance evaluation and targeted design optimization are achieved in the simulation experiment of the unmanned sweeper. By setting the weight coefficient of the speed and energy consumption of the unmanned sweeper through the standard energy consumption ratio coefficient (the ratio of speed to energy consumption), the speed and energy consumption are separated from the mixed influencing factors. By dynamically adjusting the evaluation focus through the weight coefficient, the fuzzy evaluation of "the increase in speed is accompanied by a sharp increase in energy consumption" is avoided. For example, if the ratio coefficient of the speed and energy consumption of the unmanned sweeper is 1.5, the weight coefficient of the speed of the unmanned sweeper is 0.6, and the weight coefficient of the energy consumption of the unmanned sweeper is 0.4. As the core index, the standard energy consumption ratio can be directly mapped to the hardware selection (such as motor power, battery capacity). For example, the standard energy consumption ratio of a certain model of sweeper is 0.8 km / kWh. By simulating and verifying the deviation between the actual ratio and the standard value under different road conditions, the inefficient links are quickly located. By locking the maximum value of the calibration coefficient, the "limit working point" under each road condition is determined (such as the maximum speed - energy consumption ratio of the flat road corresponding to the fully loaded and uniform speed working condition, and the ramp road corresponding to the maximum climbing working condition). The simulation can specifically test the performance boundary under extreme conditions (such as motor overload protection, battery endurance limit), and expose design defects in advance (such as insufficient battery capacity leading to operation interruption under the ramp working condition). The mobile performance evaluation of the unmanned sweeper is upgraded from experience-driven to data-driven, significantly improving the accuracy and R & D efficiency of the simulation experiment. Especially in complex urban road conditions, its quantitative analysis ability for multi-dimensional performance indicators provides key technical support for the hardware selection, algorithm optimization, and productization of the unmanned sweeper.

[0023] Specifically, based on the mobile mode working sub-data group corresponding to the flat road, obtain the ramp road feature data and the curved road feature data, which specifically includes: Based on the mobile mode working sub-data group corresponding to the flat road, obtain the maximum and minimum speeds of the unmanned sweeper on the flat road; Take the maximum and minimum speeds of the unmanned sweeper on the flat road as the reference speed threshold of the unmanned sweeper; Remove the data in the mobile mode working sub-data groups corresponding to the ramp road and the curved road where the speed of the unmanned sweeper does not exceed the reference speed threshold of the unmanned sweeper, and obtain the mobile mode feature data group; Taking the mobile mode feature data group corresponding to the ramp road as the reference, obtain the ramp unmanned sweeper speed and the ramp unmanned sweeper energy consumption; Take the sum of the speed of the slope unmanned sweeper and the energy consumption of the slope unmanned sweeper as the slope road calibration coefficient; Take the mobile mode working sub-data group corresponding to the maximum value of the slope road calibration coefficient in the mobile mode working sub-data group corresponding to the slope road as the slope road characteristic data; Based on the flat road characteristic data, take the speed of the unmanned sweeper corresponding to the flat road characteristic data as the characteristic speed of the unmanned sweeper; Taking the mobile mode characteristic data group corresponding to the curved road as the benchmark, obtain the speed change information of the unmanned sweeper corresponding to each data, and the speed change information of the unmanned sweeper represents the speed change condition of the unmanned sweeper when passing through the curved road; According to the speed change information of the unmanned sweeper, obtain the maximum and minimum speeds of the unmanned sweeper corresponding to each data in the mobile mode characteristic data group; Take the sum of the differences between the maximum and minimum speeds of the unmanned sweeper and the characteristic speed of the unmanned sweeper respectively as the curved road calibration coefficient; Take the mobile mode working sub-data group corresponding to the maximum value of the curved road calibration coefficient in the mobile mode working sub-data group corresponding to the curved road as the curved road characteristic data.

[0024] In this solution, the invalid data of the slope and curved roads (such as abnormal values beyond the flat road speed range) are filtered by the flat road reference speed threshold, avoiding the reduction of efficiency caused by analyzing each data. Taking the slope road calibration coefficient as the benchmark to identify the characteristic data in the slope road, through the sum value of "speed + energy consumption" (slope calibration coefficient), considering the climbing ability and energy consumption efficiency simultaneously, so that the characteristic data group only contains valid samples that meet the design constraints, making the simulation more targeted. Taking the flat road characteristic speed as the anchor point (such as the standard speed of 5 km / h), the speed change (acceleration / deceleration amplitude) of the curved road can be quantitatively evaluated, and the speed stability of the steering process is quantified by the "sum of the differences between the speed extreme values and the characteristic speed" (curved calibration coefficient), effectively identifying the defects of the steering algorithm (such as the speed drops suddenly by more than 30% during a sharp turn, resulting in fluctuations in the cleaning efficiency), providing a key basis for optimizing the path planning algorithm, solving the ambiguity and inefficiency problems of the performance evaluation of unmanned sweepers under complex road conditions, and providing a feasible quantitative solution for hardware selection and algorithm optimization.

[0025] Specifically, based on the cleaning mode working data group, obtain the cleaning mode characteristic data, specifically including: Based on the cleaning mode working data group, obtain the cleaning coverage rate corresponding to each mode working data; According to the mobile mode characteristic data, take the proportional relationship between the speed and energy consumption of the unmanned sweeper as the benchmark, and obtain the mobile energy consumption ratio coefficient corresponding to each mobile mode characteristic data; Obtain the standard cleaning energy consumption information of the driverless sweeper according to the performance design parameters of the driverless sweeper; Obtain the standard energy consumption ratio coefficient, and use the ratio of the mobile energy consumption ratio coefficient to the standard energy consumption ratio coefficient as the energy consumption difference coefficient; Use the mean value of the energy consumption difference coefficients corresponding to the mobile mode characteristic data as the coefficient difference reference value; Use the ratio of the cleaning coverage rate corresponding to each mode working data in the cleaning mode working data group to the standard cleaning coverage rate as the cleaning difference coefficient; According to the cleaning mode working data group, obtain the characteristic energy consumption ratio coefficient corresponding to each mode working data, where the characteristic energy consumption ratio represents the proportional coefficient of the speed and energy consumption of the driverless sweeper in the cleaning mode working data group; Use the ratio of the characteristic energy consumption ratio coefficient to the coefficient difference reference value as the energy consumption difference coefficient; Use the product of the energy consumption difference coefficient and the cleaning difference coefficient as the cleaning characteristic coefficient; Use the mode working data corresponding to the smallest cleaning characteristic coefficient in the cleaning mode working data group as the cleaning mode characteristic data.

[0026] In this solution, through the product (cleaning characteristic coefficient) of the cleaning difference coefficient (coverage rate) and the energy consumption difference coefficient (energy consumption efficiency), a two-way constraint evaluation of "operation effect - energy consumption" is realized, avoiding the one-sidedness of traditional simulation that only focuses on the cleaning coverage rate (such as reaching 95% but the energy consumption exceeding the standard by 30%) or simply pursuing low energy consumption (such as the energy consumption meeting the standard but the coverage rate being less than 80%). By forcing the selection of the "double-optimal" working mode through the coefficient product, the practicability of the design scheme is ensured.

[0027] It can be understood that for the cleaning operation of the driverless sweeper, the impacts of different road environments and weather environments on the working parameters of the driverless sweeper are very different. If each data is analyzed one by one, evaluating the working condition of the driverless sweeper during cleaning not only involves a large amount of data processing but also has a low analysis efficiency, and it is impossible to accurately identify the cleaning operation condition of the driverless sweeper. Therefore, by using the ratio of the characteristic energy consumption ratio coefficient to the coefficient difference reference value as the energy consumption difference coefficient, the smaller the energy consumption difference coefficient, the greater the difference between the energy consumption of the driverless sweeper and the energy consumption during movement. At this time, use the ratio of the cleaning coverage rate corresponding to each mode working data in the cleaning mode working data group to the standard cleaning coverage rate as the cleaning difference coefficient. Then, under normal conditions, the cleaning difference coefficient will also increase with the increase in energy consumption. Therefore, use the mode working data corresponding to the smallest cleaning characteristic coefficient in the cleaning mode working data group as the cleaning mode characteristic data to accurately identify the characteristic data during the cleaning operation.

[0028] Specifically, based on the obstacle avoidance path information, obtain the obstacle avoidance mode characteristic data, specifically including: Obtain the obstacle avoidance planning path information of the unmanned sweeper corresponding to the working data of each mode according to the obstacle avoidance mode working data group; Match the obstacle avoidance planning path information of the unmanned sweeper with the obstacle avoidance path information to obtain the obstacle avoidance path comparison information; Obtain the starting point and ending point of the obstacle avoidance planning path and the starting point and ending point of the obstacle avoidance path according to the obstacle avoidance path comparison information; Take the sum of the distance between the starting point of the obstacle avoidance planning path and the starting point of the obstacle avoidance path and the distance between the ending point of the obstacle avoidance planning path and the ending point of the obstacle avoidance path as the reference offset; Obtain the obstacle avoidance planning path length information and the obstacle avoidance path length information; Take the ratio of the reference offset to the obstacle avoidance planning path length as the path basic offset coefficient; Take the ratio of the obstacle avoidance path length to the obstacle avoidance planning path length as the obstacle avoidance path comparison coefficient; Take the product of the path basic offset coefficient and the obstacle avoidance path comparison coefficient as the obstacle avoidance feature coefficient; Take the mode working data corresponding to the largest obstacle avoidance feature coefficient in the obstacle avoidance mode working data group as the obstacle avoidance mode feature data.

[0029] In this solution, the starting point / ending point positioning accuracy of the obstacle avoidance path is directly reflected by the reference offset, which can quickly identify the coordinate calibration problem of the sensor fusion algorithm. The obstacle avoidance path comparison coefficient can expose the redundant detour problem of the planning algorithm, providing a clear direction for path optimization, and solving the problems of "rough evaluation" and "vague defect positioning" in traditional obstacle avoidance simulation. Especially in a dynamic and complex environment, its in-depth analysis ability for the position accuracy and detour efficiency of the obstacle avoidance path provides key technical support for the safety and reliability design of the unmanned sweeper.

[0030] Obtain the corresponding environmental landscape data and map data according to the mode feature data; Build a three-dimensional scene based on the environmental landscape data and map data to obtain the simulated experimental scene information; Specifically, for the environmental landscape data and map data corresponding to the mode feature data, the laser point cloud data and high-precision map data in different coordinate systems are fused through a coordinate transformation algorithm so that they can accurately reflect the spatial information of the real environment. A digital twin three-dimensional scene is built using professional three-dimensional modeling software (such as Blender or Maya). According to the elements such as terrain, buildings, and road facilities in the real environment, the corresponding three-dimensional models are accurately created, and their materials, textures, and physical properties are set. The road environment, obstacle environment, etc. in the unmanned sweeper simulation experiment are configured through the mode feature data, and different weather conditions and traffic scenarios are set to comprehensively test and analyze the running stability and cleaning effect of the unmanned sweeper.

[0031] Taking the simulated experimental scenario as a benchmark, a simulation experiment is carried out on the unmanned cleaning vehicle.

[0032] Referring to Figure 5 As shown, further, in combination with the above-mentioned simulation experiment method based on the simulation of the unmanned cleaning vehicle, a simulation experiment system based on the simulation of the unmanned cleaning vehicle is proposed, including: The main control module, which is used to obtain the cleaning mode feature data based on the cleaning mode working data group, obtain the obstacle avoidance path information corresponding to each mode working data according to the obstacle avoidance mode working data group, obtain the obstacle avoidance mode feature data based on the obstacle avoidance path information, obtain the corresponding environmental landscape data and map data according to the mode feature data, and carry out three-dimensional scene construction based on the environmental landscape data and map data to obtain the simulated experimental scene information, and carry out a simulation experiment on the unmanned cleaning vehicle with the simulated experimental scene; The information acquisition module, which is used to acquire the working data of the unmanned cleaning vehicle. The working data of the unmanned cleaning vehicle includes environmental landscape data, cleaning vehicle working parameters and map data. According to the working data of the unmanned cleaning vehicle, obtain the working mode information, obtain the performance design parameters of the unmanned cleaning vehicle. The performance design parameters of the unmanned cleaning vehicle include standard speed information, standard energy consumption information and standard cleaning coverage rate, and obtain the standard energy consumption ratio coefficient based on the performance design parameters of the unmanned cleaning vehicle; The data identification module, which is used to divide the working data of the unmanned cleaning vehicle corresponding to the same working mode into the same data group according to the working data classification information, obtain the mode working data group corresponding to each working mode. Based on the road type corresponding to each data in the moving mode working data group, further divide the moving mode working data group to obtain the moving mode working sub-data group. Based on the standard energy consumption ratio coefficient, obtain the weight coefficient of the speed and energy consumption of the unmanned cleaning vehicle, and obtain the flat road feature data according to the weight coefficient of the speed and energy consumption of the unmanned cleaning vehicle. Based on the moving mode working sub-data group corresponding to the flat road, obtain the slope road feature data and the curved road feature data; The display module, which interacts with the main control module and is used to output and display the working data classification information, moving mode feature data, cleaning mode feature data, obstacle avoidance mode feature data and simulated experimental scene information.

[0033] The main control module specifically includes: The control unit, which is used to obtain the corresponding environmental landscape data and map data according to the mode feature data, carry out three-dimensional scene construction based on the environmental landscape data and map data to obtain the simulated experimental scene information, and carry out a simulation experiment on the unmanned cleaning vehicle with the simulated experimental scene; An information receiving unit, which interacts with an information acquisition module and a data recognition module, is configured to receive data and transmit it to a data processing unit; A data processing unit, which is configured to obtain cleaning mode characteristic data based on a cleaning mode working data group, and obtain obstacle avoidance path information corresponding to each mode of working data according to an obstacle avoidance mode working data group, and obtain obstacle avoidance mode characteristic data based on the obstacle avoidance path information.

[0034] The information acquisition module specifically includes: A first acquisition unit, which is configured to acquire unmanned sweeper working data. The unmanned sweeper working data includes environmental landscape data, sweeper working parameters, and map data, and obtain working mode information according to the unmanned sweeper working data; A second acquisition unit, which is configured to acquire unmanned sweeper performance design parameters. The unmanned sweeper performance design parameters include standard speed information, standard energy consumption information, and standard cleaning coverage rate, and obtain a standard energy consumption ratio coefficient based on the unmanned sweeper performance design parameters.

[0035] The data recognition module specifically includes: A first recognition unit, which is configured to divide the unmanned sweeper working data corresponding to the same working mode into the same data group according to working data classification information, obtain a mode working data group corresponding to each working mode, and further divide the mobile mode working data group based on the road type corresponding to each data in the mobile mode working data group to obtain a mobile mode working sub-data group; A second recognition unit, which is configured to obtain a weight coefficient of the unmanned sweeper speed and energy consumption based on the standard energy consumption ratio coefficient, obtain flat road characteristic data according to the weight coefficient of the unmanned sweeper speed and energy consumption, and obtain slope road characteristic data and curved road characteristic data based on the mobile mode working sub-data group corresponding to the flat road.

[0036] In summary, the advantages of the present invention are as follows: By using working data classification information, the working data of different working modes are classified, which improves the data analysis efficiency and facilitates subsequent data processing steps. By further dividing the mobile mode working data group, a mobile mode working sub-data group is obtained, which accurately analyzes the driving conditions of the unmanned sweeper under different road conditions and provides a basis for analyzing the working conditions of the unmanned sweeper in other subsequent modes. Through the mode characteristic data corresponding to each working mode, a three-dimensional scene is constructed based on environmental landscape data and map data, which provides a data basis for the simulation of the unmanned sweeper, improves the simulation efficiency of the unmanned sweeper, and ensures the stability and reliability of the operation of the unmanned sweeper.

[0037] The basic principles, main features and advantages of the present invention have been shown and described above. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and what is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, various changes and improvements will occur to the present invention, and these changes and improvements fall within the scope of the present invention claimed. The scope of protection required by the present invention is defined by the appended claims and their equivalents.

Claims

1. A simulation experiment method based on the simulation of an unmanned sweeper, characterized in that, Including: Obtain the working data of the unmanned sweeper, where the working data of the unmanned sweeper includes environmental landscape data, sweeper working parameters, and map data; According to the working data of the unmanned sweeper, obtain the working mode information, where the working mode includes a cleaning mode, an obstacle avoidance mode, and a movement mode; Based on the working mode, classify the working data of the unmanned sweeper to obtain the classified working data information; According to the working mode information and the classified working data information, obtain the mode feature data corresponding to each working mode; According to the mode feature data, obtain the corresponding environmental landscape data and map data; Based on the environmental landscape data and the map data, construct a three-dimensional scene to obtain the simulated experimental scene information; Based on the simulated experimental scene, conduct a simulation experiment on the unmanned sweeper.

2. The simulation experiment method based on the unmanned sweeper simulation according to claim 1, characterized in that The step of obtaining the mode feature data corresponding to each working mode according to the working mode information and the classified working data information specifically includes: According to the classified working data information, divide the working data of the unmanned sweeper corresponding to the same working mode into the same data group to obtain the mode working data group corresponding to each working mode; Obtain the movement mode working data group, where the movement mode working data group represents the mode working data corresponding to the unmanned sweeper in the movement mode; Based on the road type corresponding to each data in the movement mode working data group, further divide the movement mode working data group to obtain the movement mode working sub-data group, where the road type includes flat roads, slope roads, and curved roads; According to the movement mode working sub-data group, obtain the movement mode feature data; Based on the cleaning mode working data group, obtain the cleaning mode feature data, where the cleaning mode working data group represents the mode working data corresponding to the unmanned sweeper in the cleaning mode; According to the obstacle avoidance mode working data group, obtain the obstacle avoidance path information corresponding to each mode working data; Based on the obstacle avoidance path information, obtain the obstacle avoidance mode feature data; According to the movement mode feature data, the cleaning mode feature data, and the obstacle avoidance mode feature data, obtain the mode feature data.

3. A simulation experiment method based on the simulation of an unmanned cleaning vehicle according to claim 2, characterized in that, The step of obtaining the movement mode feature data according to the movement mode working sub-data group specifically includes: Obtain the performance design parameters of the unmanned sweeper, where the performance design parameters of the unmanned sweeper include standard speed information, standard energy consumption information, and standard cleaning coverage rate; Based on the performance design parameters of the unmanned sweeper, obtain the standard energy consumption ratio coefficient, where the standard energy consumption ratio represents the proportional coefficient of the speed and energy consumption of the unmanned sweeper; Based on the standard energy consumption ratio coefficient, obtain the weight coefficient of the speed and energy consumption of the unmanned sweeper; According to the movement mode working sub-data group corresponding to the flat road, take the product of the speed of the unmanned sweeper and the corresponding weight coefficient as the speed quantity of the unmanned sweeper, and take the product of the energy consumption of the unmanned sweeper and the corresponding weight coefficient as the energy consumption quantity of the unmanned sweeper; Take the ratio of the speed quantity of the unmanned sweeper to the energy consumption quantity of the unmanned sweeper as the calibration coefficient of the flat road; Take the movement mode working sub-data group corresponding to the maximum calibration coefficient of the flat road in the movement mode working sub-data group corresponding to the flat road as the flat road feature data; Based on the mobile mode working sub-data group corresponding to flat roads, obtain slope road characteristic data and curved road characteristic data; Based on the flat road characteristic data, slope road characteristic data and curved road characteristic data, obtain mobile mode characteristic data.

4. A simulation experiment method based on the simulation of an unmanned sweeper, as described in claim 3, wherein, The obtaining of slope road characteristic data and curved road characteristic data based on the mobile mode working sub-data group corresponding to flat roads specifically includes: Based on the mobile mode working sub-data group corresponding to flat roads, obtain the maximum and minimum speeds of the unmanned sweeper on flat roads; Take the maximum and minimum speeds of the unmanned sweeper on flat roads as the benchmark speed thresholds of the unmanned sweeper; Remove the data in the mobile mode working sub-data groups corresponding to slope roads and curved roads where the speed of the unmanned sweeper does not exceed the benchmark speed threshold of the unmanned sweeper to obtain a mobile mode characteristic data group; Based on the mobile mode characteristic data group corresponding to slope roads, obtain the speed quantity of the slope unmanned sweeper and the energy consumption quantity of the slope unmanned sweeper; Take the sum of the speed quantity of the slope unmanned sweeper and the energy consumption quantity of the slope unmanned sweeper as the calibration coefficient of the slope road; Take the mobile mode working sub-data group corresponding to the maximum calibration coefficient of the slope road in the mobile mode working sub-data group corresponding to slope roads as the slope road characteristic data; Based on the flat road characteristic data, take the speed of the unmanned sweeper corresponding to the flat road characteristic data as the characteristic speed of the unmanned sweeper; Based on the mobile mode characteristic data group corresponding to curved roads, obtain the speed change information of the unmanned sweeper corresponding to each data, and the speed change information of the unmanned sweeper represents the speed change condition of the unmanned sweeper when passing through a curved road; According to the speed change information of the unmanned sweeper, obtain the maximum and minimum speeds of the unmanned sweeper corresponding to each data in the mobile mode characteristic data group; Take the sum of the differences between the maximum and minimum speeds of the unmanned sweeper and the characteristic speed of the unmanned sweeper respectively as the calibration coefficient of the curved road; Take the mobile mode working sub-data group corresponding to the maximum calibration coefficient of the curved road in the mobile mode working sub-data group corresponding to curved roads as the curved road characteristic data.

5. A simulation experiment method based on unmanned sweeper simulation according to claim 2, characterized in that, The obtaining of cleaning mode characteristic data based on the cleaning mode working data group specifically includes: Based on the cleaning mode working data group, obtain the cleaning coverage rate corresponding to each mode working data; According to the mobile mode characteristic data, based on the proportional relationship between the speed and energy consumption of the unmanned sweeper, obtain the mobile energy consumption ratio coefficient corresponding to each mobile mode characteristic data; According to the performance design parameters of the unmanned sweeper, obtain the standard cleaning energy consumption information of the unmanned sweeper; Obtain the standard energy consumption ratio coefficient, and take the ratio of the mobile energy consumption ratio coefficient to the standard energy consumption ratio coefficient as the energy consumption difference coefficient; Take the mean value of the energy consumption difference coefficients corresponding to the mobile mode characteristic data as the coefficient difference reference value; Take the ratio of the cleaning coverage rate corresponding to each mode working data in the cleaning mode working data group to the standard cleaning coverage rate as the cleaning difference coefficient; According to the cleaning mode working data group, obtain the characteristic energy consumption ratio coefficient corresponding to each mode working data, and the characteristic energy consumption ratio represents the proportional coefficient of the speed and energy consumption of the unmanned sweeper in the cleaning mode working data group; Take the ratio of the characteristic energy consumption ratio coefficient to the coefficient difference reference value as the energy consumption difference coefficient; Take the product of the energy consumption difference coefficient and the cleaning difference coefficient as the cleaning characteristic coefficient; Take the mode working data corresponding to the smallest cleaning characteristic coefficient in the cleaning mode working data group as the cleaning mode characteristic data.

6. A simulation experiment method based on the simulation of an unmanned sweeper, characterized in that, Based on the obstacle avoidance path information, obtain the obstacle avoidance mode characteristic data, specifically including: According to the obstacle avoidance mode working data group, obtain the obstacle avoidance planning path information of the unmanned cleaning vehicle corresponding to each mode working data; Match the obstacle avoidance planning path information of the unmanned cleaning vehicle with the obstacle avoidance path information to obtain the obstacle avoidance path comparison information; According to the obstacle avoidance path comparison information, obtain the starting point and ending point of the obstacle avoidance planning path and the starting point and ending point of the obstacle avoidance path; Take the sum of the distance between the starting point of the obstacle avoidance planning path and the starting point of the obstacle avoidance path and the distance between the ending point of the obstacle avoidance planning path and the ending point of the obstacle avoidance path as the reference offset; Obtain the obstacle avoidance planning path length information and the obstacle avoidance path length information; Take the ratio of the reference offset to the obstacle avoidance planning path length as the path basic offset coefficient; Take the ratio of the obstacle avoidance path length to the obstacle avoidance planning path length as the obstacle avoidance path comparison coefficient; Take the product of the path basic offset coefficient and the obstacle avoidance path comparison coefficient as the obstacle avoidance characteristic coefficient; Take the mode working data corresponding to the largest obstacle avoidance characteristic coefficient in the obstacle avoidance mode working data group as the obstacle avoidance mode characteristic data.

7. A simulation experiment system based on the simulation of an unmanned sweeper vehicle, for implementing the simulation experiment method according to any one of claims 1-6, characterized in that, Include: The main control module is used to obtain the cleaning mode characteristic data based on the cleaning mode working data group, obtain the obstacle avoidance path information corresponding to each mode working data according to the obstacle avoidance mode working data group, obtain the obstacle avoidance mode characteristic data based on the obstacle avoidance path information, obtain the corresponding environmental landscape data and map data according to the mode characteristic data, and construct a three-dimensional scene based on the environmental landscape data and map data to obtain the simulation experiment scene information, and conduct a simulation experiment on the unmanned cleaning vehicle with the simulation experiment scene; The information acquisition module is used to acquire the working data of the unmanned cleaning vehicle. The working data of the unmanned cleaning vehicle includes environmental landscape data, cleaning vehicle working parameters, and map data. According to the working data of the unmanned cleaning vehicle, obtain the working mode information, obtain the performance design parameters of the unmanned cleaning vehicle. The performance design parameters of the unmanned cleaning vehicle include standard speed information, standard energy consumption information, and standard cleaning coverage rate. Based on the performance design parameters of the unmanned cleaning vehicle, obtain the standard energy consumption ratio coefficient; A data recognition module, which is used to divide the work data of the unmanned sweeper corresponding to the same working mode into the same data group according to the work data classification information, obtain the mode work data group corresponding to each working mode, further divide the mobile mode work data group based on the road type corresponding to each data in the mobile mode work data group, obtain the mobile mode work sub-data group, take the standard energy consumption ratio coefficient as the benchmark, obtain the weight coefficient of the unmanned sweeper speed and energy consumption, and obtain the flat road characteristic data according to the weight coefficient of the unmanned sweeper speed and energy consumption. Based on the mobile mode work sub-data group corresponding to the flat road, obtain the slope road characteristic data and the curved road characteristic data; A display module, which interacts with the main control module and is used to output and display the work data classification information, mobile mode characteristic data, cleaning mode characteristic data, obstacle avoidance mode characteristic data and simulation experiment scenario information.

8. An analog experimental system based on the simulation of an unmanned sweeper, characterized in that, The main control module specifically includes: A control unit, which is used to obtain the corresponding environmental landscape data and map data according to the mode characteristic data, construct a three-dimensional scene based on the environmental landscape data and map data, obtain the simulation experiment scenario information, and perform a simulation experiment on the unmanned sweeper with the simulation experiment scenario; An information receiving unit, which interacts with the information acquisition module and the data recognition module, and is used to receive data and transmit it to the data processing unit; A data processing unit, which is used to obtain the cleaning mode characteristic data based on the cleaning mode work data group, obtain the obstacle avoidance path information corresponding to each mode work data according to the obstacle avoidance mode work data group, and obtain the obstacle avoidance mode characteristic data based on the obstacle avoidance path information.

9. An analog experimental system based on the simulation of an unmanned sweeper, characterized in that, The information acquisition module specifically includes: A first acquisition unit, which is used to acquire the work data of the unmanned sweeper. The work data of the unmanned sweeper includes environmental landscape data, sweeper work parameters and map data, and obtain the working mode information according to the work data of the unmanned sweeper; A second acquisition unit, which is used to acquire the performance design parameters of the unmanned sweeper. The performance design parameters of the unmanned sweeper include standard speed information, standard energy consumption information and standard cleaning coverage rate, and obtain the standard energy consumption ratio coefficient based on the performance design parameters of the unmanned sweeper.

10. A simulation experiment system based on the simulation of an unmanned sweeper, characterized in that, The data recognition module specifically includes: A first recognition unit, which is used to divide the work data of the unmanned sweeper corresponding to the same working mode into the same data group according to the work data classification information, obtain the mode work data group corresponding to each working mode, and further divide the mobile mode work data group based on the road type corresponding to each data in the mobile mode work data group to obtain the mobile mode work sub-data group; A second recognition unit, which is used to obtain the weight coefficient of the speed and energy consumption of the unmanned sweeper based on the standard energy consumption ratio coefficient, obtain the flat road characteristic data according to the weight coefficient of the speed and energy consumption of the unmanned sweeper, and obtain the slope road characteristic data and the curved road characteristic data based on the working sub-data group corresponding to the mobile mode of the flat road.

Images