Cleaning system of laser radar and vehicle

Abstract

The invention discloses a cleaning system of a laser radar. Comprising a dirt detection module, a cleaning execution module and a control module, the dirt detection module is used for detecting the surface of the laser radar optical window in real time or regularly to obtain dirt detection information; the control module is connected with the dirt detection module and the cleaning execution module and used for determining a cleaning mode according to the pollution detection information obtained from the pollution detection module; and the cleaning execution module is used for executing cleaning operation by adopting a corresponding cleaning mechanism according to the cleaning mode. The purpose of intelligent cleaning of the laser radar in the prior art is at least achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computer, in particular, to a cleaning system of a laser radar and a vehicle. BACKGROUND

[0002] In recent years, intelligent assisted driving technology is constantly updated, and the configuration rate of laser radar is also increasing. Some after-sales problems recently fed back are caused by dirt, which causes the laser radar to fail to work normally. However, there is no relevant technology to clean the laser radar in time, which causes users to have great complaints.

[0003] In view of the above problems, no effective solution has been proposed so far. SUMMARY

[0004] The embodiment of the present application provides a cleaning system of a laser radar, so as to at least solve the problem that the laser radar is intelligently cleaned in the prior art.

[0005] According to one aspect of the embodiment of the present application, a cleaning system of a laser radar is provided, comprising: a dirt detection module, a cleaning execution module and a control module; the dirt detection module is used for acquiring dirt detection information by detecting the surface of the optical window of the laser radar in real time or periodically; the control module is connected with the dirt detection module and the cleaning execution module, and is used for determining a cleaning mode according to the pollution detection information acquired from the pollution detection module; and the cleaning execution module is used for executing a cleaning operation by adopting a corresponding cleaning mechanism according to the cleaning mode.

[0006] Optionally, the pollution detection information comprises the type of the pollution on the surface of the optical window, the position of the pollution on the surface of the optical window and the pollution degree.

[0007] Optionally, the dirt detection module determines the type of the pollution based on a dirt detection algorithm of point cloud characteristics; and the specific algorithm process is as follows: whether the type of the pollution is a dead insect is determined by analyzing the intensity anomaly of the point cloud characteristics of the near distance reflection layer; and / or whether the type of the pollution is water stains or soil is determined by analyzing the signal attenuation of the point cloud characteristics of the near distance reflection layer; and / or whether the type of the pollution is rain stains is determined by analyzing the point cloud characteristics of the near distance reflection layer and linking the vehicle sensor.

[0008] Optionally, the cleaning mode is determined according to the type of the contaminant and the cleaning target, including: in the case that the type of the contaminant is loose adhesion, determining that the contamination level is first-class contamination, the cleaning target is to remove the loose adhesion, and the mode for cleaning the first-class contamination corresponds to cleaning mode one; in the case that the type of the contaminant is insect corpses and / or water stains, determining that the contamination level is second-class contamination, the cleaning target is to remove the insect corpses and / or water stains, and the mode for cleaning the second-class contamination is cleaning mode two; in the case that the type of the contaminant is thick mud and / or oil stains, determining that the contamination level is third-class contamination, the cleaning target is to remove the thick mud and / or oil stains, and the mode for cleaning the third-class contamination is cleaning mode three.

[0009] Optionally, the pollution detection module is configured to determine the type of the oil stains according to the characteristic wavelength, the reflectivity increment, and the image features.

[0010] Optionally, the cleaning mechanism of the cleaning execution module includes a piezoelectric vibrator, a micro-channel nozzle, a blade material, and a heating film; and the cleaning execution module is configured to adjust the cleaning mechanism of the cleaning execution module according to the cleaning mode.

[0011] Optionally, the cleaning execution module is further configured to: in the case that the pollution detection module detects the contaminant and the vehicle speed is greater than or equal to a preset speed, only enable the air flow or vibration mode to clean; and in the case that the pollution detection module detects the contaminant and the battery power of the vehicle is less than or equal to a preset power, switch to the mechanical mode to clean.

[0012] Optionally, the cleaning execution module is further configured to: in the case that the remaining amount of the cleaning liquid is less than or equal to a predetermined amount and the contamination level is first-class contamination or second-class contamination, use the vibration cleaning; and in the case that the remaining amount of the cleaning liquid is less than or equal to the predetermined amount and the contamination level is third-class contamination, enable the water spraying mode to clean.

[0013] Optionally, the control module is configured to, in the case that the cleaning execution module fails to clean, send a signal to an autonomous driving system to prompt an operation object to clean according to the signal.

[0014] The application further provides a vehicle including the cleaning system of the laser radar.

[0015] In the embodiment of the present application, the cleaning system of the laser radar comprises a dirt detection module, a cleaning execution module and a control module. The dirt detection module is used to detect dirt on the surface of the optical window of the laser radar in real time or periodically to obtain dirt detection information. The control module is connected with the dirt detection module and the cleaning execution module, and is used to determine a cleaning mode according to the dirt detection information obtained from the dirt detection module. The cleaning execution module is used to perform a cleaning operation by using a corresponding cleaning mechanism according to the cleaning mode. The problems in the prior art that the laser radar is not intelligently cleaned are at least solved. BRIEF DESCRIPTION OF DRAWINGS

[0016] The drawings described herein are used to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their descriptions serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings: Figure 1 is a structural diagram of a cleaning system of a laser radar according to an embodiment of the present application; Figure 2 is a flowchart of a laser radar intelligent cleaning system based on dirt detection according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0018] It should be noted that the terms “first”, “second” and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms “include” and “have” and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a sequence of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0019] In the embodiment, a cleaning system of a laser radar is also provided, Figure 1 is a structural diagram of a cleaning system of a laser radar according to an embodiment of the present application, like Figure 1As shown, the cleaning system of the laser radar comprises a dirt detection module 11, a control module 13, and a cleaning execution module 15. The dirt detection module 11 is configured to detect dirt on the surface of the optical window of the laser radar in real time or periodically to obtain dirt detection information.

[0020] The control module 13 is connected to the dirt detection module 11 and the cleaning execution module 15, and is configured to determine a cleaning mode according to the dirt detection information obtained from the dirt detection module.

[0021] The cleaning execution module 15 is configured to perform a cleaning operation according to the corresponding cleaning mechanism of the cleaning mode.

[0022] In the embodiment, the dirt detection information can include the type of the dirt on the surface of the optical window, the position of the dirt on the surface of the optical window, and the degree of contamination.

[0023] According to the embodiments provided in the present application, the cleaning system of the laser radar comprises a dirt detection module 11, which is configured to detect dirt on the surface of the optical window of the laser radar in real time or periodically to obtain dirt detection information; a control module, which is connected to the dirt detection module and the cleaning execution module, and is configured to determine a cleaning mode according to the dirt detection information obtained from the dirt detection module; and a cleaning execution module, which is configured to perform a cleaning operation according to the corresponding cleaning mechanism of the cleaning mode. Thus, the intelligent cleaning of the laser radar in the prior art is at least solved.

[0024] Optionally, the dirt detection module 11 determines the type of the dirt based on a dirt detection algorithm of point cloud characteristics. The specific algorithm process is as follows: through intensity anomaly analysis of the point cloud characteristics of the near-distance reflection layer, it is determined whether the type of the dirt is a dead insect; and / or through signal attenuation analysis of the point cloud characteristics of the near-distance reflection layer, it is determined whether the type of the dirt is water stains or soil; and / or through the point cloud characteristics of the near-distance reflection layer, the vehicle sensor is linked to determine whether the type of the dirt is rain stains.

[0025] As shown in the flowchart of the laser radar intelligent cleaning system based on dirt detection. Figure 2

[0026] In the embodiment, the dirt detection module utilizes the point cloud characteristics of the laser radar itself to detect the existence, type, position, and degree of the dirt on the surface of the optical window of the laser radar in real time or periodically.

[0027] The dirt detection module implements a dirt detection algorithm based on point cloud characteristics.

[0028] Step 1: Extract the near-distance reflection layer (0.1-0.3m).

[0029] Step 2: Intensity anomaly analysis (dead insect detection). ​

[0030] Step 3: Signal attenuation analysis (water stains / mud).

[0031] Step 4: Link the vehicle sensors (if the rainfall is >5mm / h, prioritize identifying it as water stains).

[0032] Cleaning execution module: The core cleaning mechanism used, such as a fluid jet device, a scraping mechanism, an ultrasonic vibrator, a heating device, or a combination thereof.

[0033] Control module: Connected to the dirt detection module and the cleaning execution module, and configured as follows: 1. Receive waste detection information.

[0034] 2. Based on dirt information, vehicle status information, and environmental information, determine whether to start cleaning and which cleaning mode to select.

[0035] 3. Control the cleaning execution module to perform the selected cleaning operation.

[0036] In this embodiment, the rules for determining solid contaminants are as follows:

[0037] Oil stain identification rules and reflective characteristics

[0038] Optionally, the cleaning mode is determined based on the type of contaminant and the cleaning objective, and may include: if the contaminant is loose deposits, the contamination level is determined to be Level 1, and the cleaning objective is to remove the loose deposits; the cleaning mode for Level 1 contamination corresponds to Cleaning Mode 1. If the contaminant is insect carcasses and / or water stains, the contamination level is determined to be Level 2, and the cleaning objective is to remove the insect carcasses and / or water stains; the cleaning mode for Level 2 contamination is Cleaning Mode 2. If the contaminant is thick mud and / or oil stains, the contamination level is determined to be Level 3, and the cleaning objective is to remove the thick mud and / or oil stains; the cleaning mode for Level 3 contamination is Cleaning Mode 3.

[0039] Optionally, a pollution detection module 11 is used to determine the type of oil stain based on characteristic wavelength, reflectance increase, and image features.

[0040] Optionally, the cleaning mechanism of the cleaning execution module 15 includes: a piezoelectric vibrator, a microchannel nozzle, a scraper material, and a heating film; the cleaning execution module 15 is used to adjust the cleaning mechanism of the cleaning execution module according to the cleaning mode.

[0041] In this embodiment, the cleaning actuator includes a cleaning mechanism:

[0042] The pollution level definition and cleaning strategy are as follows:

[0043] Optionally, the cleaning execution module 15 is also configured to: activate only the airflow or vibration mode for cleaning when the pollution detection module detects pollutants and the vehicle speed is greater than or equal to a preset speed; and switch to mechanical mode for cleaning when the pollution detection module detects pollutants and the vehicle battery power is less than or equal to a preset power.

[0044] Optionally, the cleaning execution module 15 is also used to: use vibration cleaning when the remaining cleaning fluid is less than or equal to a predetermined amount and the contamination level is level one or level two; and enable water spray cleaning when the remaining cleaning fluid is less than or equal to a predetermined amount and the contamination level is level three.

[0045] In this embodiment, dynamic priority adjustment is performed: Disable scraping at vehicle speeds > 60km / h (to avoid wind resistance interference) → enable only airflow / vibration.

[0046] When the battery level is less than 20%, disable the heating function and switch to mechanical cleaning mode.

[0047] Resource optimization example: When the cleaning fluid level is <10%: Vibration cleaning is preferred for light pollution (level 1-2); water spray is used only for heavy pollution (level 3), and the spraying time is reduced by 50%.

[0048] Optionally, the control module 13 sends a signal to the autonomous driving system in the event that the cleaning execution module fails to clean, so as to prompt the object to be operated to clean according to the signal.

[0049] In this embodiment, the failure protection mechanism handles cleaning failures as follows: if the contamination level is still ≥2 after three consecutive cleanings, a "LiDAR Degraded" signal is sent to the autonomous driving system.

[0050] Triggered behavior: The system downgrades to Level 2 assisted driving, and the navigation system prompts "Please manually clean the sensors". Hardware fault diagnosis: Monitor abnormal scraper motor current (>0.5A) → determine mechanical jamming → automatically retract scraper arm and issue alarm.

[0051] This embodiment significantly reduces perception errors (false alarms / missed alarms) caused by LiDAR contamination. It improves the reliability and safety of autonomous driving systems under various adverse weather and road conditions (rain, snow, mud, insects). It reduces system degradation or the need for manual intervention due to contamination. It extends the effective operating time of the LiDAR, reducing maintenance frequency (compared to systems without self-cleaning). Intelligent control optimizes resource (cleaning fluid, energy) usage.

[0052] As an alternative embodiment, this application also provides a vehicle that includes the cleaning system of the lidar described above.

[0053] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0054] This embodiment also provides an automated pressure testing device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0055] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0056] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0057] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0058] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0059] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A cleaning system for a lidar, the system comprising: The system comprises a dirt detection module, a cleaning execution module, and a control module. The dirt detection module is configured to acquire dirt detection information in real time or periodically from the surface of the optical window of the lidar. The control module is connected to the dirt detection module and the cleaning execution module, and is configured to determine a cleaning mode according to the dirt detection information acquired from the dirt detection module. The cleaning execution module is configured to perform a cleaning operation according to the corresponding cleaning mechanism of the cleaning mode. The dirt detection information includes the type of the dirt on the surface of the optical window, the position of the dirt on the surface of the optical window, and the degree of contamination.

2. The system of claim 1, wherein, The dirt detection module determines the type of the dirt based on a dirt detection algorithm of point cloud characteristics; the specific algorithm process is as follows:

3. The system of claim 2, wherein, By analyzing the intensity anomaly of the point cloud characteristics of the near-distance reflection layer, it is determined whether the type of the dirt is insect carcass; and / or By analyzing the signal attenuation of the point cloud characteristics of the near-distance reflection layer, it is determined whether the type of the dirt is water stain or mud; and / or By analyzing the point cloud characteristics of the near-distance reflection layer, the vehicle sensor is linked to determine whether the type of the dirt is rain stain. The cleaning mode is determined according to the type of the dirt and the cleaning target, including:

4. The system of claim 2 or 3, wherein, In the case that the type of the dirt is loose adhesion, the contamination level is determined to be first-class contamination, the cleaning target is to remove the loose adhesion, and the mode for cleaning the first-class contamination corresponds to cleaning mode one; In the case that the type of the dirt is insect carcass and / or water stain, the contamination level is determined to be second-class contamination, the cleaning target is to remove the insect carcass and / or water stain, and the mode for cleaning the second-class contamination is cleaning mode two; In the case that the type of the dirt is thick mud and / or oil stain, the contamination level is determined to be third-class contamination, the cleaning target is to remove the thick mud and / or oil stain, and the mode for cleaning the third-class contamination is cleaning mode three. The system comprises a dirt detection module, a cleaning execution module, and a control module.

5. The system of claim 1, wherein, The dirt detection module is configured to determine the type of the oil stain according to the characteristic wavelength, the reflectivity increment, and the image characteristics. The cleaning mechanism of the cleaning execution module includes a piezoelectric vibrator, a micro-channel nozzle, a blade material, and a heating film.

6. The system of claim 1, wherein, The cleaning execution module is configured to adjust the cleaning mechanism of the cleaning execution module according to the cleaning mode. The cleaning execution module is further configured to:

7. The system of claim 4, wherein, In the case that the dirt detection module detects dirt and the vehicle speed is greater than or equal to a preset speed, only the airflow or vibration mode is enabled for cleaning; In the case that the dirt detection module detects dirt and the battery power of the vehicle is less than or equal to a preset power, the mechanical mode is switched to for cleaning. The cleaning execution module is further configured to:

8. The system of claim 6, wherein, In the case that the remaining amount of the cleaning liquid is less than or equal to a predetermined amount and the contamination level is first-class contamination or second-class contamination, the vibration mode is used for cleaning; In the case that the remaining amount of the cleaning liquid is less than or equal to a predetermined amount and the contamination level is third-class contamination, the water spraying mode is enabled for cleaning. The system comprises a dirt detection module, a cleaning execution module, and a control module.

9. The system of claim 1, wherein, The control module sends a signal to the autonomous driving system to prompt an operation object to perform cleaning according to the signal in the case that the cleaning execution module fails to clean. The system comprises a lidar according to any one of claims 1-9.

10. A vehicle characterized by comprising: ​

Images