WO2023213172A1 - 自移动设备的控制方法、设备及存储介质 - Google Patents

自移动设备的控制方法、设备及存储介质 Download PDF

Info

Publication number
WO2023213172A1
WO2023213172A1 PCT/CN2023/087711 CN2023087711W WO2023213172A1 WO 2023213172 A1 WO2023213172 A1 WO 2023213172A1 CN 2023087711 W CN2023087711 W CN 2023087711W WO 2023213172 A1 WO2023213172 A1 WO 2023213172A1
Authority
WO
WIPO (PCT)
Prior art keywords
tof
group
sensor
sensing data
sensors
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2023/087711
Other languages
English (en)
French (fr)
Inventor
罗绍涵
孙佳佳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dreame Innovation Technology Suzhou Co Ltd
Original Assignee
Dreame Innovation Technology Suzhou Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Dreame Innovation Technology Suzhou Co Ltd filed Critical Dreame Innovation Technology Suzhou Co Ltd
Publication of WO2023213172A1 publication Critical patent/WO2023213172A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions

Definitions

  • This application belongs to the field of automatic control technology, and specifically relates to control methods, equipment and storage media for autonomous mobile devices.
  • self-mobile devices can move within a designated environment and perform data processing on information in the environment.
  • This application provides a control method, equipment and storage medium for self-mobile devices, which can solve the problem that traditional self-mobile devices usually use visual sensors for mapping.
  • traditional self-mobile devices usually use visual sensors for mapping.
  • the use of visual sensors for mapping requires a large amount of calculation and the mapping efficiency is relatively low. low question.
  • This application provides the following technical solutions.
  • a control method for autonomous mobile equipment characterized in that the autonomous mobile equipment is provided with at least one group of time-of-flight TOF sensors, each group of TOF sensors including at least two TOF sensors, and the method includes:
  • the sensing data collected by each group of TOF sensors is obtained;
  • the arrangement direction of each group of TOF sensors is perpendicular to the device body of the mobile device.
  • the TOF sensor is an area array TOF sensor.
  • controlling the work of the self-mobile device based on the sensing data includes:
  • the initial processing results are corrected to obtain the work results.
  • each group of TOF sensors includes a first TOF sensor and a second TOF sensor, and the ranging range of the first TOF sensor is greater than the ranging range of the second TOF sensor; the range is determined according to current work requirements.
  • the main sensor in each group of TOF sensors includes:
  • the second TOF sensor in each group of TOF sensors is determined to be the main sensor.
  • the initial processing result includes an initial area map, and the initial area map includes the first obstacle information obtained based on the sensing data collected by the main sensor. ;
  • the initial processing results are corrected using the sensing data collected by the auxiliary sensors in each group of TOF sensors except the main sensor, and the working results are obtained, including:
  • the first obstacle information is corrected using the second obstacle information to obtain an area map.
  • the number of the auxiliary sensors is at least two, and using the second obstacle information to correct the first obstacle information to obtain a regional map includes:
  • the correction weight of the auxiliary sensor is determined based on the ranging range of each auxiliary sensor, and the correction weight is negatively correlated with the ranging range;
  • the first obstacle information is corrected using the weighted sum of each second obstacle information and the corresponding correction weight to obtain the area map.
  • the initial processing result includes a first recognition result based on the sensing data collected by the main sensor, and the first recognition result includes whether there is obstacle;
  • the initial processing results are corrected using the sensing data collected by the auxiliary sensors in each group of TOF sensors except the main sensor, and the working results are obtained, including:
  • the first recognition result is corrected using the second recognition result to obtain obstacle information.
  • a second aspect provides an electronic device.
  • the device includes a processor and a memory; a program is stored in the memory, and the program is loaded and executed by the processor to implement the automatic operation as described in any one of the first aspects. Control methods for mobile devices.
  • a computer-readable storage medium characterized in that a program is stored in the storage medium, and when executed by a processor, the program is used to implement the control method of a mobile device as described in the second aspect. .
  • the self-mobile device is provided with at least one set of TOF sensors, each set of TOF sensors includes at least two TOF sensors, and the sensing data collected by each set of TOF sensors is obtained during the movement of the self-mobile device, and
  • the self-mobile device is controlled based on sensing data. Since the sensing data collected by the TOF sensor is depth information, at this time, the self-mobile device only needs to calculate the depth information. Compared with image recognition, the calculation of depth information The amount of mapping is low, so the calculation amount of mapping can be reduced and the efficiency of mapping can be improved.
  • the accuracy of controlling the mobile device using the sensing data collected by the TOF sensor may not be high. Based on this, in this embodiment, by setting at least two TOF sensors and fusing the sensing data collected by the at least two TOF sensors to control the mobile device, the control accuracy can be improved.
  • the arrangement direction of each group of TOF sensors is not perpendicular to the device body of the mobile device, the overlapping area of the collection field of view of each group of TOF sensors may be smaller, resulting in fusion.
  • the arrangement direction of each group of TOF sensors is perpendicular to the device body of the mobile device. In this way, the area of the overlapping portion of the collection field of view of each group of TOF sensors can be maximized, thereby as much as possible Fusion of sensor data further improves the accuracy of control from mobile devices.
  • the area array sensor has a larger field of view to collect sensing data compared to a single-point TOF sensor, the collection efficiency of sensing data is higher.
  • the main sensor in each group of TOF sensors is determined according to the current work requirements.
  • the sensor with the corresponding field of view is selected as the main sensor for data collection according to the current work requirements, which can enable different work requirements.
  • the TOF sensor can collect sensing data in different collection fields in a targeted manner, which can improve the accuracy of data collection.
  • the sensing data collected by the main sensor is corrected by the sensing data collected by the auxiliary sensor in each group of TOF sensors, which can avoid the problem of inaccurate data collected by a single TOF sensor, thus Improve the accuracy of mapping or obstacle avoidance.
  • Figure 1 is a schematic structural diagram of a mobile device provided by an embodiment of the present application.
  • FIG. 2 is a schematic diagram of a field of view collected by a TOF sensor provided by an embodiment of the present application
  • FIG. 3 is a schematic diagram of the TOF sensor arrangement provided by an embodiment of the present application.
  • Figure 4 is a flow chart of a control method for a mobile device provided by an embodiment of the present application.
  • FIG. 5 is a block diagram of a control device provided by an embodiment of the present application.
  • Figure 6 is a block diagram of an electronic device provided by an embodiment of the present application.
  • the directional words used such as “upper, lower, top, and bottom” usually refer to the direction shown in the drawings, or to the vertical or vertical position of the component itself. Vertically or in the direction of gravity; similarly, for ease of understanding and description, “inside and outside” refers to the inside and outside relative to the outline of each component itself, but the above directional terms are not used to limit this application.
  • Figure 1 is a schematic structural diagram of a self-moving device provided by an embodiment of the present application.
  • the self-moving device can be a sweeping robot, a floor-washing robot, or other self-moving equipment. This embodiment does not limit the type of the self-moving device. limited.
  • the mobile device at least includes: a driving component 110, a moving component 120, a controller 130 and a Time Of Flight (TOF) sensor 140.
  • TOF Time Of Flight
  • the driving component 110 is connected to the moving component 120 and the controller 130 respectively, and is used to drive the moving component 120 to operate in response to instructions issued by the controller 130 to drive the mobile device to move.
  • the driving component 110 can be implemented as a DC motor, a servo motor, a stepper motor, etc. This embodiment does not limit the implementation of the driving component 110 .
  • the TOF sensor 140 emits near-infrared ( ⁇ 850nm or 940nm) pulse waves through a flood illuminator (solid-state laser or LED). After the pulse wave encounters an object, it is reflected and collected by the TOF sensor 140. By calculating the distance between the pulse waves of each pixel Frequency difference or time difference is used to obtain sensing data.
  • the TOF sensor 140 is used to collect sensing data, which is data indicating the frequency difference or time difference between pulse waves of each pixel.
  • the sensing data can be depth information of the object or point cloud data, etc.
  • the mobile device is provided with at least one group of TOF sensors 140, and each group of TOF sensors 140 includes at least two TOF sensors 140.
  • the sensing accuracy of the TOF sensor 140 is limited, when one TOF sensor 140 is provided, the accuracy of controlling the mobile device using the sensing data collected by the TOF sensor 140 may not be high. Based on this, in this embodiment, by arranging at least two TOF sensors 140 and fusing the sensing data collected by the at least two TOF sensors 140 to control the mobile device, the control accuracy can be improved.
  • the sensing accuracy of at least two TOF sensors 140 in the same group of TOF sensors is the same or different.
  • the collection fields of view of each group of TOF sensors 140 have overlapping portions.
  • the collection field of view refers to the scanning range when the TOF sensor 140 collects sensing data.
  • the collection field of view includes the scanning range in the left and right directions, the scanning range in the up and down directions, and the scanning range in the front and rear directions.
  • the overlap of the collection fields of view means that the projections of the collection fields of view on a plane parallel to the fuselage overlap.
  • an overlapping portion 23 shown by the hatched portion in the projections of the collection field of view 211 of the TOF sensor 21 and the collection field of view 212 of the TOF sensor 22 on a plane parallel to the fuselage.
  • the arrangement of each group of TOF sensors 140 includes but is not limited to: the arrangement direction is parallel to the plane where the fuselage is located, or the arrangement direction is parallel to the plane where the fuselage is located. There is a certain angle, or the arrangement direction is perpendicular to the plane where the fuselage is located.
  • the arrangement direction of each group of TOF sensors 140 is not perpendicular to the device body of the mobile device, for example: the arrangement direction is parallel to the plane where the body is located, or the arrangement direction If there is a certain angle with the plane where the fuselage is located, or the arrangement direction is perpendicular to the plane where the fuselage is located, it may lead to a problem that the overlapping area of the collection field of view of each group of TOF sensors 140 is smaller and the fused sensing data is less.
  • the arrangement direction of each group of TOF sensors is perpendicular to the device body of the mobile device. In this way, the area of the overlapping portion of the collection field of view of each group of TOF sensors can be maximized, thereby as much as possible Fusion of sensor data further improves the accuracy of control from mobile devices.
  • the mobile device is provided with a set of TOF sensors.
  • the set of TOF sensors includes two TOF sensors 140.
  • the two TOF sensors 140 are vertically distributed up and down on the body of the mobile device.
  • FIG. 3 only takes one group of TOF sensors as an example for illustration.
  • the autonomous mobile device can also be provided with at least two groups of TOF sensors, and the TOF sensors 140 in each group of TOF sensors are vertically distributed up and down on the autonomous mobile device. Device body.
  • the self-moving device will move in the direction directly in front of the fuselage. Based on this, arranging a set of TOF sensors 140 directly in front of the body of the mobile device can enable the TOF sensors 140 to continuously collect sensing data in the direction of travel, which can improve the timeliness of controlling the mobile device.
  • the TOF sensor 140 is an area array sensor.
  • the area array sensor refers to a TOF sensor 140 that uses an area array photosensitive chip inside the TOF sensor 140. Based on this, the area array sensor can obtain the geometric information structure of the object surface.
  • area array sensors Compared with single-point TOF sensors, area array sensors have a larger field of view for collecting sensing data, so the collection efficiency of sensing data is higher.
  • the TOF sensor 140 is connected to the controller 130, and the collected sensing data is sent to the controller 130.
  • the controller 130 is used to control the mobile device.
  • the controller 130 can be implemented as a single-chip computer or a processor. This embodiment does not limit the implementation of the controller 130 .
  • the controller 130 is configured to: acquire the sensing data collected by each group of TOF sensors while the self-mobile device is moving within the target area; and control the work of the self-mobile device based on the sensing data.
  • the self-mobile device may also include other components, such as power supply components, shock-absorbing components, etc., which will not be listed one by one in this embodiment.
  • the self-mobile device is provided with at least one group of TOF sensors, and each group of TOF sensors includes at least two TOF sensors.
  • the sensing data collected by each group of TOF sensors are obtained, and based on Sensing data controls the work of self-mobile devices. Since the sensing data collected by the TOF sensor is depth information, at this time, the self-mobile device only needs to calculate the depth information. Compared with image recognition, the amount of calculation of depth information is It is lower, so it can reduce the calculation amount of mapping and improve the efficiency of mapping.
  • the accuracy of controlling the mobile device using the sensing data collected by the TOF sensor may not be high. Based on this, in this embodiment, by setting at least two TOF sensors and fusing the sensing data collected by the at least two TOF sensors to control the mobile device, the control accuracy can be improved.
  • the arrangement direction of each group of TOF sensors is not perpendicular to the device body of the mobile device, the overlapping area of the collection field of view of each group of TOF sensors may be smaller, resulting in fusion.
  • the arrangement direction of each group of TOF sensors is perpendicular to the device body of the mobile device. In this way, the area of the overlapping portion of the collection field of view of each group of TOF sensors can be maximized, thereby as much as possible Fusion of sensor data further improves the accuracy of control from mobile devices.
  • the area array sensor has a larger field of view to collect sensing data compared to a single-point TOF sensor, the collection efficiency of sensing data is higher.
  • Step 401 During the movement of the mobile device within the target area, the sensing data collected by each group of TOF sensors is obtained.
  • the sensing data is obtained after the mobile device obtains the movement instruction; or the sensing data is obtained after the mobile device is turned on.
  • This embodiment does not limit the timing of obtaining the sensing data.
  • the methods of obtaining movement instructions include but are not limited to the following:
  • the first one Receive movement instructions sent by other devices.
  • Other devices are communicatively connected to the mobile device.
  • the other devices may be remote controls, mobile phones, tablets, wearable devices, etc. This embodiment does not limit the device types of other devices.
  • the second type since the mobile device is installed with a start movement button. Correspondingly, the mobile device generates a movement instruction upon receiving a trigger operation acting on the start movement button.
  • the start movement button may be a physical button installed on the mobile device, or it may be a virtual button displayed on the touch screen. This embodiment does not limit the implementation of the start movement button.
  • the method of obtaining movement instructions from the mobile device may also be other methods. This embodiment does not limit the method of obtaining instructions for data collection.
  • obtaining the sensing data collected by each group of TOF sensors includes: obtaining the moving direction of the mobile device; obtaining the data of different moving directions and different groups of TOF sensors. Correspondence; determine and obtain the sensing data collected by each group of TOF sensors based on the correspondence.
  • the two sets of TOF sensors are respectively installed directly in front and behind the mobile device.
  • a set of TOF sensors directly in front of the mobile device are acquired; when the mobile device is moving backward, a set of TOF sensors directly behind the mobile device are acquired.
  • Step 402 Control the operation of the mobile device based on the sensing data.
  • controlling the work of a mobile device based on sensing data includes at least the following steps S1 to S3:
  • Step S1 Determine the main sensor in each group of TOF sensors based on current work requirements.
  • the current work requirements include map construction or obstacle recognition, etc. This embodiment does not limit the type of current work requirements.
  • the method for determining the current work requirements from the mobile device includes but is not limited to one of the following methods:
  • the first type is to install a work requirement selection button on the mobile device.
  • the mobile device receives a work demand selection button during movement, it is determined that the current work demand is the work demand indicated by the work demand selection button.
  • the self-mobile device receives work requirement instructions sent by other devices during movement. Correspondingly, after receiving the work requirement instructions, the self-mobile device determines that the current work requirements are the work requirements indicated by the work requirement instructions.
  • the method of determining the current work requirements from the mobile device may also be other methods, and this embodiment does not limit the method of determining the current work requirements.
  • Determining the main sensor in each group of TOF sensors according to the current work requirements includes: determining the current work requirements to determine the ranging range required by the TOF sensor; determining the main sensor based on the ranging range.
  • each group of TOF sensors includes a first TOF sensor and a second TOF sensor.
  • the ranging range of the first TOF sensor is greater than the ranging range of the second TOF sensor.
  • Determining the main sensor based on the ranging range includes: obtaining the range threshold stored in the mobile device; when the ranging range is greater than the range threshold, determining the first TOF sensor as the primary sensor; when the ranging range is less than the range threshold Next, determine the second TOF sensor as the main sensor.
  • the range threshold stored in the mobile device is 2m
  • the range measurement range corresponding to the work requirement stored in the mobile device is map construction is 4m.
  • the ranging range required for map construction is greater than the range threshold, then the first TOF sensor in each group of TOF sensors is determined to be the main sensor.
  • the work requirement stored in the self-mobile device is the ranging corresponding to obstacle recognition.
  • the range is 50cm.
  • the ranging range required for obstacle recognition is less than the range threshold, and the second TOF sensor in each group of TOF sensors is determined to be the main sensor.
  • the main sensor in each group of TOF sensors is determined according to the current work requirements.
  • the sensor with the corresponding field of view is selected as the main sensor for data collection according to the current work requirements, which can enable different work requirements.
  • the TOF sensor can collect sensing data in different collection fields in a targeted manner, which can improve the accuracy of data collection.
  • Step S2 Process the sensing data collected by the main sensor according to the current work requirements to obtain the initial processing results.
  • the sensing data collected by the main sensor is processed according to the current work requirements to obtain the initial processing results, including: obtaining an initialization blank map; mapping the sensing data to the initialization blank In the map, the initial processing results are obtained.
  • the sensing data collected by the main sensor is processed according to the current work requirements to obtain the initial processing results, including: inputting the sensing data to the pre-trained first Obstacle recognition model to obtain initial processing results.
  • the first obstacle recognition model is obtained by training a neural network model using the first sample sensing data and the obstacle labels in the first sample sensing data.
  • the obstacle label is used to indicate whether there is an obstacle in the first sample sensing data.
  • the neural network model can be a convolutional neural network (CNN), a recursive neural network (RNN), or a feedforward neural network (FNN).
  • CNN convolutional neural network
  • RNN recursive neural network
  • FNN feedforward neural network
  • Step S3 Use the sensing data collected by the auxiliary sensors in each group of TOF sensors except the main sensor to correct the initial processing results and obtain the work results.
  • the initial processing result when the current work requirement is map construction, includes an initial area map, and the initial area map includes first obstacle information obtained based on sensing data collected by the main sensor.
  • the initial processing results are corrected using the sensing data collected by the auxiliary sensors in each group of TOF sensors except the main sensor, and the work results are obtained, including: determining the second obstacle information based on the sensing data collected by the auxiliary sensors. ; Use the second obstacle information to correct the first obstacle information to obtain the area map.
  • the number of auxiliary sensors is at least two.
  • Use the second obstacle information to correct the first obstacle information to obtain a regional map including: determining the correction weight of the auxiliary sensor based on the ranging range of each auxiliary sensor, and the correction weight is negatively correlated with the ranging range; using each auxiliary sensor.
  • the weighted sum of the second obstacle information and the corresponding correction weight is used to correct the first obstacle information to obtain a regional map.
  • the ranging range of the first auxiliary sensor is 60cm.
  • the corresponding correction weight of the first auxiliary sensor is 0.6
  • the corresponding correction weight of the second auxiliary sensor is 0.6.
  • the ranging range of the auxiliary sensor is 80cm.
  • the corresponding correction weight of the second auxiliary sensor is 0.5.
  • the product of the point cloud coordinates of the second obstacle information corresponding to the first auxiliary sensor and the correction weight is P. 1
  • the product of the point cloud coordinates of the second obstacle information corresponding to the second auxiliary sensor and the correction weight is P 2
  • the initial processing result includes a first recognition result based on the sensing data collected by the main sensor, and the first recognition result includes whether there is an obstacle.
  • the initial processing results are corrected using the sensing data collected by the auxiliary sensors in each group of TOF sensors except the main sensor, and the work results are obtained, including: determining the second recognition result based on the sensing data collected by the auxiliary sensors, The second recognition result includes whether there is an obstacle; the second recognition result is used to correct the first recognition result to obtain obstacle information.
  • Determining the second recognition result based on the sensor data collected by the auxiliary sensor includes: inputting the sensor data into a pre-trained second obstacle recognition model to obtain the recognition result.
  • the second obstacle recognition model is obtained by training a neural network model using the second sample sensing data and the obstacle labels in the second sample sensing data.
  • the obstacle tag is used to indicate whether there is an obstacle in the second sample sensing data.
  • Using the second recognition result to correct the first recognition result includes: determining the second recognition result to be the corrected first recognition result.
  • the sensing data collected by the main sensor is corrected by the sensing data collected by the auxiliary sensor in each group of TOF sensors, which can avoid the problem of inaccurate data collected by a single TOF sensor, thereby improving the construction efficiency.
  • Figure or obstacle avoidance accuracy is a measure of the distance between the two TOF sensors.
  • controlling the work of a mobile device based on sensing data includes: determining the fusion weight of each TOF sensor in each group of TOF sensors according to current work requirements; combining the sensing data collected by each TOF sensor with the corresponding fusion weight Perform weighted fusion to obtain the work results.
  • each group of TOF sensors includes a first TOF sensor and a second TOF sensor.
  • the ranging range of the first TOF sensor is greater than the ranging range of the second TOF sensor.
  • the fusion weight of each TOF sensor has a positive correlation with the ranging range of the TOF sensor.
  • the fusion weight of the first TOF sensor is determined to be 0.7, and the fusion weight of the second TOF sensor is 0.3.
  • the sensing data collected by the first TOF sensor and the second TOF sensor are combined.
  • the sensing data of the TOF sensor is weighted and summed with the corresponding fusion weight to obtain the work result.
  • the control method of the autonomous mobile device obtains the sensing data collected by each group of TOF sensors during the movement of the autonomous mobile device in the target area; and controls the operation of the autonomous mobile device based on the sensing data. ; It can solve the problem of large amount of calculation and low efficiency of mapping using visual sensors; since the sensing data collected by the TOF sensor is depth information, at this time, the mobile device only needs to calculate the depth information. , compared with image recognition, the computational complexity of depth information is lower, so it can reduce the computational complexity of mapping and improve mapping efficiency.
  • the main sensor in each group of TOF sensors is determined according to the current work requirements.
  • the sensor with the corresponding field of view is selected as the main sensor for data collection according to the current work requirements, which can enable different work requirements.
  • the TOF sensor can collect sensing data in different collection fields in a targeted manner, which can improve the accuracy of data collection.
  • the sensing data collected by the main sensor is corrected by the sensing data collected by the auxiliary sensor in each group of TOF sensors, which can avoid the problem of inaccurate data collected by a single TOF sensor, thus Improve the accuracy of mapping or obstacle avoidance.
  • FIG. 5 is a block diagram of a self-mobile equipment control device provided by an embodiment of the present application. This embodiment uses the example of applying the device to self-mobile equipment for explanation.
  • the device includes at least the following modules: data acquisition module 510 and work control module 520.
  • the data collection module 510 is used to obtain the sensing data collected by each group of TOF sensors during the movement of the mobile device within the target area.
  • the work control module 520 is used to control the work of the mobile device based on sensing data.
  • the mobile device control device provided in the above embodiment performs control
  • only the division of the above functional modules is used as an example.
  • the above functions can be allocated to different functional modules as needed. Completion means dividing the internal structure of the mobile device control device into different functional modules to complete all or part of the functions described above.
  • the self-mobile equipment control apparatus and the self-mobile equipment control method embodiments provided in the above embodiments belong to the same concept. Please refer to the method embodiments for the specific implementation process, which will not be described again here.
  • the electronic device may be a mobile device.
  • the electronic device includes at least a processor 601 and a memory 602.
  • the processor 601 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc.
  • the processor 601 can adopt at least one hardware form among DSP (Digital Signal Processing, digital signal processing), FPGA (Field-Programmable Gate Array, field programmable gate array), and PLA (Programmable Logic Array, programmable logic array).
  • the processor 601 may also include a main processor and a co-processor.
  • the main processor is a processor used to process data in the wake-up state, also called a CPU (Central Processing Unit, central processing unit); the co-processor is A low-power processor used to process data in standby mode.
  • the processor 601 may be integrated with a GPU (Graphics Processing Unit, image processor), and the GPU is responsible for rendering and drawing content to be displayed on the display screen.
  • the processor 601 may also include an AI (Artificial Intelligence, artificial intelligence) processor, which is used to process computing operations related to machine learning.
  • AI Artificial Intelligence, artificial intelligence
  • Memory 602 may include one or more computer-readable storage media, which may be non-transitory. Memory 602 may also include high-speed random access memory, and non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 602 is used to store at least one instruction, and the at least one instruction is used to be executed by the processor 601 to implement the self-moving provided by the method embodiments in this application. Device control methods.
  • the electronic device optionally further includes: a peripheral device interface and at least one peripheral device.
  • the processor 601, the memory 602 and the peripheral device interface may be connected through a bus or a signal line.
  • Each peripheral device can be connected to the peripheral device interface through a bus, a signal line or a circuit board.
  • peripheral devices include but are not limited to: radio frequency circuits, touch display screens, audio circuits, power supplies, etc.
  • the electronic device may also include fewer or more components, which is not limited in this embodiment.
  • this application also provides a computer-readable storage medium in which a program is stored, and the program is loaded and executed by the processor to implement the self-mobile device control method of the above method embodiment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

本申请属于自动控制技术领域，具体涉及自移动设备的控制方法、设备及存储介质，自移动设备设置有至少一组飞行时间TOF传感器，每组TOF传感器包括至少两个TOF传感器，该方法包括：在自移动设备在目标区域内移动过程中，获取每组TOF传感器采集的传感数据；基于传感数据控制自移动设备工作；可以解决视觉传感器所需的计算量通常较大，导致自移动设备的建图效率较低的问题；通过在自移动设备移动过程中，获取TOF传感器采集的传感数据，并基于传感数据控制自移动设备工作，由于传感数据为深度信息，自移动设备只需要对深度信息进行计算即可，相较于图像识别来说，深度信息的计算量较低，因此，可以减少建图的计算量，提高建图效率。

Description

自移动设备的控制方法、设备及存储介质
本公开要求如下专利申请的优先权：于2022年05月06日提交中国专利局、申请号为：202210484952.X、发明名称为“自移动设备的控制方法、设备及存储介质”的中国专利申请；上述专利申请的全部内容通过引用结合在本公开中。
技术领域
本申请属于自动控制技术领域，具体涉及自移动设备的控制方法、设备及存储介质。
 背景技术
目前，自移动设备可以在指定环境下移动并对环境中的信息进行数据处理。
传统的自移动设备上通常采用视觉传感器进行建图。然而，使用视觉传感器进行建图的计算量较大，建图效率较低。
 发明内容
本申请提供了自移动设备的控制方法、设备及存储介质，可以解决传统的自移动设备上通常采用视觉传感器进行建图，然而，使用视觉传感器进行建图的计算量较大，建图效率较低的问题。本申请提供如下技术方案。
第一方面，提供了自移动设备的控制方法，其特征在于，所述自移动设备设置有至少一组飞行时间TOF传感器，每组TOF传感器包括至少两个TOF传感器，所述方法包括：
在所述自移动设备在目标区域内移动过程中，获取每组TOF传感器采集的传感数据；
基于所述传感数据控制所述自移动设备工作。
可选地，每组TOF传感器的排列方向垂直于所述自移动设备的设备机身。
可选地，所述TOF传感器为面阵TOF传感器。
可选地，所述基于所述传感数据控制所述自移动设备工作，包括：
根据当前工作需求确定所述每组TOF传感器中的主传感器；
按照所述当前工作需求对所述主传感器采集的传感数据进行处理，得到初始处理结果；
使用所述每组TOF传感器中除所述主传感器之外的辅传感器采集的传感数据，对所述初始处理结果进行修正，得到工作结果。
可选地，所述每组TOF传感器包括第一TOF传感器和第二TOF传感器，所述第一TOF传感器的测距范围大于所述第二TOF传感器的测距范围；所述根据当前工作需求确定所述每组TOF传感器中的主传感器，包括：
在所述当前工作需求为地图构建的情况下，确定所述每组TOF传感器中的所述第一TOF传感器为主传感器；
在所述当前工作需求为障碍物识别的情况下，确定所述每组TOF传感器中的所述第二TOF传感器为主传感器。
可选地，在所述当前工作需求为地图构建的情况下，所述初始处理结果包括初始区域地图，所述初始区域地图包括基于所述主传感器采集的传感数据得到的第一障碍物信息；
相应地，所述使用所述每组TOF传感器中除所述主传感器之外的辅传感器采集的传感数据，对所述初始处理结果进行修正，得到工作结果，包括：
基于所述辅传感器采集的传感数据确定第二障碍物信息；
使用所述第二障碍物信息对所述第一障碍物信息进行修正，得到区域地图。
可选地，所述辅传感器的数量为至少两个，所述使用所述第二障碍物信息对所述第一障碍物信息进行修正，得到区域地图，包括：
基于每个辅传感器的测距范围确定所述辅传感器的修正权重，所述修正权重与所述测距范围呈负相关关系；
使用每个第二障碍物信息与对应的修正权重的加权和，对所述第一障碍物信息进行修正，得到所述区域地图。
可选地，在所述当前工作需求为障碍物识别的情况下，所述初始处理结果包括基于所述主传感器采集的传感数据得到的第一识别结果，所述第一识别结果包括是否存在障碍物；
相应地，所述使用所述每组TOF传感器中除所述主传感器之外的辅传感器采集的传感数据，对所述初始处理结果进行修正，得到工作结果，包括：
基于所述辅传感器采集的传感数据确定第二识别结果，所述第二识别结果包括是否存在障碍物；
使用所述第二识别结果对所述第一识别结果进行修正，得到障碍物信息。
第二方面，提供一种电子设备，所述设备包括处理器和存储器；所述存储器中存储有程序，所述程序由所述处理器加载并执行以实现如第一方面任一所述的自移动设备的控制方法。
第三方面，提供一种计算机可读存储介质，其特征在于，所述存储介质中存储有程序，所述程序被处理器执行时用于实现如第二方面所述的自移动设备的控制方法。
本申请的有益效果在于：自移动设备设置有至少一组TOF传感器，每组TOF传感器包括至少两个TOF传感器，通过在自移动设备移动过程中，获取每组TOF传感器采集的传感数据，并基于传感数据控制自移动设备工作，由于TOF传感器采集的传感数据为深度信息，此时，自移动设备只需要对深度信息进行计算即可，相较于图像识别来说，深度信息的计算量较低，因此，可以减少建图的计算量，提高建图效率。
另外，由于TOF传感器的传感精度有限，因此，在设置一个TOF传感器的情况下，使用该TOF传感器采集的传感数据对自移动设备进行控制的精度可能不高。基于此，本实施例中，通过设置至少两个TOF传感器，将至少两个TOF传感器采集的传感数据进行融合来控制自移动设备，可以提高控制精度。
另外，由于TOF传感器的采集视野有限，因此，在每组TOF传感器的排列方向非垂直于自移动设备的设备机身的情况下，可能导致每组TOF传感器的采集视野重叠部分面积较小，融合的传感数据较少的问题。基于上述技术问题，本实施例中，每组TOF传感器的排列方向垂直于自移动设备的设备机身，这样，可以使每组TOF传感器的采集视野的重叠部分的面积最大，从而尽可能多地融合的传感数据，进一步提高控制自移动设备的准确性。
另外，由于相较于单点TOF传感器来说，面阵传感器采集传感数据的采集视野更大，因此，传感数据的采集效率更高。
另外，由于不同的TOF传感器的采集视野不同，因此，在针对不同工作需求进行工作时，若不根据工作需求使用相同相应采集视野的TOF传感器，可能会导致在进行工作时数据采集不够准确的问题。基于上述技术问题，本实施例中，根据当前工作需求确定每组TOF传感器中的主传感器，这样，在根据当前工作需求选择相应采集视野的传感器作为主传感器进行数据采集，可以使得在不同工作需求的情况下，TOF传感器可以针对性地采集不同采集视野的传感数据，可以提高数据采集的准确性。
另外，由于TOF传感器140的采集视野有限，因此，在使用单个TOF传感器采集数据的情况下，可能导致采集不到TOF传感器采集视野以外的传感数据的问题，从而导致传感数据不够准确的问题，基于上述技术问题，本实施例中，通过每组TOF传感器中的辅传感器采集的传感数据对主传感器采集的传感数据进行修正，可以避免单个TOF传感器采集的数据不精准的问题，从而提高建图或者避障的准确性。
 附图说明
为了更清楚地说明本发明具体实施方式或现有技术中的技术方案，下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍，显而易见，下面描述中的附图是本发明的一些实施方式，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请一个实施例提供的自移动设备的结构示意图；
图2是本申请一个实施例提供的TOF传感器采集视野的示意图；
图3是本申请一个实施例提供的TOF传感器排布的示意图；
图4是本申请一个实施例提供的自移动设备的控制方法的流程图；
图5是本申请一个实施例提供的控制装置的框图；
图6是本申请一个实施例提供的电子设备的框图。
 实施方式
下面将结合附图对本申请的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。下文中将参考附图并结合实施例来详细说明本申请。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
在本申请中，在未作相反说明的情况下，使用的方位词如“上、下、顶、底”通常是针对附图所示的方向而言的，或者是针对部件本身在竖直、垂直或重力方向上而言的；同样地，为便于理解和描述，“内、外”是指相对于各部件本身的轮廓的内、外，但上述方位词并不用于限制本申请。
如图1所示为本申请一个实施例提供的自移动设备的结构示意图，该自移动设备可以为扫地机器人，洗地机器人等可自行移动的设备，本实施例不对自移动设备的设备类型作限定。根据图1可知，自移动设备至少包括：驱动组件110、移动组件120、控制器130和飞行时间 (Time Of Flight，TOF) 传感器140。
驱动组件110分别与移动组件120和控制器130相连，并用于响应控制器130发出的指令，驱动移动组件120运行，以带动自移动设备移动。
可选地，驱动组件110可以实现为直流电机、伺服电机、步进电机等，本实施例不对驱动组件110的实现方式作限定。
TOF传感器140通过泛光照明器（固态激光器或者LED）发射近红外（~850nm或940nm）的脉冲波，脉冲波遇到物体以后反射被TOF传感器140收集，通过计算每个像素脉冲波之间的频率差或时间差得到传感数据。
换言之，TOF传感器140用于采集传感数据，该传感数据为指示每个像素脉冲波之间的频率差或时间差的数据。
可选地，传感数据可以为物体的深度信息或点云数据等。
本实施例中，自移动设备设置有至少一组TOF传感器140，每组TOF传感器140包括至少两个TOF传感器140。
由于TOF传感器140的传感精度有限，因此，在设置一个TOF传感器140的情况下，使用该TOF传感器140采集的传感数据对自移动设备进行控制的精度可能不高。基于此，本实施例中，通过设置至少两个TOF传感器140，将至少两个TOF传感器140采集的传感数据进行融合来控制自移动设备，可以提高控制精度。
可选地，同一组TOF传感器中的至少两个TOF传感器140的传感精度相同或不同。
为了保证能够将不同传感精度的TOF传感器140采集的传感数据进行融合，每组TOF传感器140的采集视野存在重叠部分。其中，采集视野是指TOF传感器140采集传感数据时的扫描范围，采集视野包括左右方向上的扫描范围、上下方向上的扫描范围和前后方向上的扫描范围。
采集视野重叠是指：采集视野在平行于机身平面上的投影存在重叠。比如：参考图2， TOF传感器21的采集视野211与TOF传感器22的采集视野212在平行于机身平面上的投影存在重叠部分23（阴影部分所示）。
在保证每组TOF传感器140的采集视野存在重叠部分的前提下，每组TOF传感器140的排布方式包括但不限于：排布方向与机身所在平面平行、或者排布方向与机身所在平面存在一定角度、或者排布方向与机身所在平面垂直。
由于TOF传感器140的采集视野有限，因此，在每组TOF传感器140的排列方向非垂直于自移动设备的设备机身的情况下，比如：排布方向与机身所在平面平行、或者排布方向与机身所在平面存在一定角度、或者排布方向与机身所在平面垂直的情况下，可能导致每组TOF传感器140的采集视野重叠部分面积较小，融合的传感数据较少的问题。基于上述技术问题，本实施例中，每组TOF传感器的排列方向垂直于自移动设备的设备机身，这样，可以使每组TOF传感器的采集视野的重叠部分的面积最大，从而尽可能多地融合的传感数据，进一步提高控制自移动设备的准确性。
比如：参考图3，自移动设备设置有一组TOF传感器，该组TOF传感器包括两个TOF传感器140，这两个TOF传感器140上下垂直分布于自移动设备机身。
图3中仅以TOF传感器为一组为例进行说明，在其它实施例中，自移动设备也可以设置至少两组TOF传感器，且每组TOF传感器中的TOF传感器140均上下垂直分布于自移动设备机身。
可选地，存在一组TOF传感器140设置于自移动设备机身的正前方。通常，自移动设备会向机身的正前方的方向进行移动。基于此，将一组TOF传感器140设置于自移动设备机身的正前方，可以使TOF传感器140持续采集到行进方向上的传感数据，可以提高控制自移动设备的及时性。
可选地，TOF传感器140为面阵传感器。面阵传感器是指在TOF传感器140内部使用面阵式感光芯片的TOF传感器140，基于此，面阵传感器可以获取到物体表面几何信息结构。
由于相较于单点TOF传感器来说，面阵传感器采集传感数据的采集视野更大，因此，传感数据的采集效率更高。
TOF传感器140与控制器130相连，并采集到的传感数据发送至控制器130。
控制器130用于对自移动设备进行控制。可选地，控制器130可以实现为单片机，或者处理器，本实施例不对控制器130的实现方式作限定。
本实施例中，控制器130用于：在自移动设备在目标区域内移动过程中，获取每组TOF传感器采集的传感数据；基于传感数据控制自移动设备工作。
需要补充说明的是，在实际实现时，自移动设备还可以包括其它元器件，如：供电组件、减震组件等，本实施例在此不再一一列举。
传统的自移动设备上通常采用视觉传感器进行建图。在使用视觉传感器进行建图时，自移动设备需要对视觉传感器采集的图像数据进行图像识别，基于识别结果控制自移动设备工作。然而，图像识别所需的计算量通常较大，这就会导致自移动设备的建图效率较低的问题。而本实施例中，自移动设备设置有至少一组TOF传感器，每组TOF传感器包括至少两个TOF传感器，通过在自移动设备移动过程中，获取每组TOF传感器采集的传感数据，并基于传感数据控制自移动设备工作，由于TOF传感器采集的传感数据为深度信息，此时，自移动设备只需要对深度信息进行计算即可，相较于图像识别来说，深度信息的计算量较低，因此，可以减少建图的计算量，提高建图效率。
另外，由于TOF传感器的传感精度有限，因此，在设置一个TOF传感器的情况下，使用该TOF传感器采集的传感数据对自移动设备进行控制的精度可能不高。基于此，本实施例中，通过设置至少两个TOF传感器，将至少两个TOF传感器采集的传感数据进行融合来控制自移动设备，可以提高控制精度。
另外，由于TOF传感器的采集视野有限，因此，在每组TOF传感器的排列方向非垂直于自移动设备的设备机身的情况下，可能导致每组TOF传感器的采集视野重叠部分面积较小，融合的传感数据较少的问题。基于上述技术问题，本实施例中，每组TOF传感器的排列方向垂直于自移动设备的设备机身，这样，可以使每组TOF传感器的采集视野的重叠部分的面积最大，从而尽可能多地融合的传感数据，进一步提高控制自移动设备的准确性。
另外，由于相较于单点TOF传感器来说，面阵传感器采集传感数据的采集视野更大，因此，传感数据的采集效率更高。
下面对本申请提供的自移动设备的控制方法进行详细介绍。
本实施例提供的自移动设备的控制方法，如图4所示。本实施例以该方法用于图1所示的自移动设备为例进行说明。该方法至少包括以下几个步骤：
步骤401，在自移动设备在目标区域内移动过程中，获取每组TOF传感器采集的传感数据。
可选地，自移动设备在获取到移动指令后获取传感数据；或者，在开机后获取传感数据，本实施例不对传感数据的获取时机作限定。
其中，移动指令的获取方式包括但不限于以下几种：
第一种：接收其它设备发送的移动指令。其它设备与自移动设备通信相连，该其它设备可以为遥控器、手机、平板电脑、可穿戴式设备等，本实施例不对其它设备的设备类型作限定。
第二种：自移动设备安装有开始移动按键。相应地，自移动设备在接收到作用于开始移动按键的触发操作的情况下，生成移动指令。
其中，开始移动按键可以为安装在自移动设备上的物理按键，或者也可以是通过触摸显示屏显示的虚拟按键，本实施例不对开始移动按键的实现方式作限定。
在实际实现时，自移动设备获取移动指令的方式也可以为其它方式，本实施例不对数据采集的指令的获取方式作限定。
可选地，当自移动设备为至少两组TOF传感器的情况下，获取每组TOF传感器采集的传感数据包括：获取自移动设备的移动方向；获取不同移动方向与不同组别的TOF传感器的对应关系；基于对应关系确定获取每组TOF传感器采集的传感数据。
比如：当自移动设备设置2组TOF传感器的情况下，2组TOF传感器分别设置于自移动设备的正前方和正后方。在自移动设备向前方行进时，获取正前方的一组TOF传感器；在自移动设备倒退时，获取正后方的一组TOF传感器。
步骤402，基于传感数据控制自移动设备工作。
在一个示例中，基于传感数据控制自移动设备工作，至少包括以下步骤S1至S3：
步骤S1：根据当前工作需求确定每组TOF传感器中的主传感器。
可选地，当前工作需求包括地图构建或障碍物识别等，本实施例不对当前工作需求的类型作限定。
在根据当前工作需求确定每组TOF传感器中的主传感器之前，自移动设备确定当前工作需求的方式包括但不限于以下几种方式中的一种：
第一种，自移动设备上安装有工作需求选择按键。相应地，自移动设备在移动过程中接收到作用于工作需求选择按键的情况下，确定当前工作需求为工作需求选择按键所指示的工作需求。
第二种，自移动设备在移动过程中接收其它设备发送的工作需求指令，相应地，自移动设备在接收到工作需求指令后，确定当前工作需求为工作需求指令所指示的工作需求。
在实际实现时，自移动设备确定当前工作需求的方式也可以为其它方式，本实施例不对当前工作需求确定的方式作限定。
根据当前工作需求确定每组TOF传感器中的主传感器，包括：确定当前工作需求确定TOF传感器所需要的测距范围；基于测距范围确定主传感器。
其中，每组TOF传感器包括第一TOF传感器和第二TOF传感器。
其中，第一TOF传感器的测距范围大于第二TOF传感器的测距范围。
基于测距范围确定主传感器，包括：获取存储在自移动设备内的范围阈值；在测距范围大于范围阈值的情况下，确定第一TOF传感器为主传感器；在测距范围小于范围阈值的情况下，确定第二TOF传感器为主传感器。
其中，自移动设备内存储有不同工作需求对应不同的测距范围。
在一个示例中，以自移动设备内存储的范围阈值为2m为例，在确定当前工作需求为地图构建的情况下，自移动设备内存储的工作需求为地图构建所对应的测距范围为4m，此时地图构建所需要的测距范围大于范围阈值，则确定每组TOF传感器中的第一TOF传感器为主传感器。
在另一个示例中，以自移动设备内存储的测距阈值为2m为例，在当前工作需求为障碍物识别的情况下，自移动设备内存储的工作需求为障碍物识别所对应的测距范围为50cm，此时障碍物识别所需要的测距范围小于范围阈值，则确定每组TOF传感器中的第二TOF传感器为主传感器。
由于不同的TOF传感器的采集视野不同，因此，在针对不同工作需求进行工作时，若不根据工作需求使用相同相应采集视野的TOF传感器，可能会导致在进行工作时数据采集不够准确的问题。基于上述技术问题，本实施例中，根据当前工作需求确定每组TOF传感器中的主传感器，这样，在根据当前工作需求选择相应采集视野的传感器作为主传感器进行数据采集，可以使得在不同工作需求的情况下，TOF传感器可以针对性地采集不同采集视野的传感数据，可以提高数据采集的准确性。
步骤S2: 按照当前工作需求对主传感器采集的传感数据进行处理，得到初始处理结果。
在一个示例中，当工作需求为地图构建的情况下，按照当前工作需求对主传感器采集的传感数据进行处理，得到初始处理结果，包括：获取初始化空白地图；将传感数据映射至初始化空白地图中，得到初始处理结果。
在另一个示例中，当工作需求为障碍物识别的情况下，按照当前工作需求对主传感器采集的传感数据进行处理，得到初始处理结果，包括：将传感数据输入至预先训练的第一障碍物识别模型，得到初始处理结果。
其中，第一障碍物识别模型是使用第一样本传感数据和该第一样本传感数据中的障碍物标签，对神经网络模型进行训练得到的。障碍物标签用于指示第一样本传感数据中是否存在障碍物。
其中，神经网络模型可以为卷积神经网络（Convolutional Neural Networks，CNN）、递归神经网络（Recursive Neural Network，RNN）、前馈神经网络（Feedforward Neural Network，FNN），本实施例不对神经网络模型的实现方式作限定。
步骤S3：使用每组TOF传感器中除主传感器之外的辅传感器采集的传感数据，对初始处理结果进行修正，得到工作结果。
在一个示例中，在当前工作需求为地图构建的情况下，初始处理结果包括初始区域地图，初始区域地图包括基于主传感器采集的传感数据得到的第一障碍物信息。
相应地，使用每组TOF传感器中除主传感器之外的辅传感器采集的传感数据，对初始处理结果进行修正，得到工作结果，包括：基于辅传感器采集的传感数据确定第二障碍物信息；使用第二障碍物信息对第一障碍物信息进行修正，得到区域地图。
其中，辅传感器的数量至少为两个。
使用第二障碍物信息对第一障碍物信息进行修正，得到区域地图，包括：基于每个辅传感器的测距范围确定辅传感器的修正权重，修正权重与测距范围呈负相关关系；使用每个第二障碍物信息与对应的修正权重的加权和，对第一障碍物信息进行修正，得到区域地图。
比如：当障碍物信息为点云数据，辅传感器的数量为两个时，第一个辅传感器的测距范围为60cm，此时，第一个辅传感器对应的修正权重为0.6，第二个辅传感器的测距范围为80cm，此时，第二个辅传感器的对应的修正权重为0.5，此时第一个辅传感器对应的第二障碍物信息的点云坐标与修正权重的乘积为P 1，第二个辅传感器对应的第二障碍物信息的点云坐标与修正权重的乘积为P 2，则修正后的第一障碍物信息的点云坐标为P 3= P 1+ P 2。
在另一个示例中，在当前工作需求为障碍物识别的情况下，初始处理结果包括基于主传感器采集的传感数据得到的第一识别结果，第一识别结果包括是否存在障碍物。
相应地，使用每组TOF传感器中除主传感器之外的辅传感器采集的传感数据，对初始处理结果进行修正，得到工作结果，包括：基于辅传感器采集的传感数据确定第二识别结果，第二识别结果包括是否存在障碍物；使用第二识别结果对第一识别结果进行修正，得到障碍物信息。
基于辅传感器采集的传感数据确定第二识别结果，包括：将传感数据输入至预先训练的第二障碍物识别模型，得到识别结果。
其中，第二障碍物识别模型是使用第二样本传感数据和该第二样本传感数据中的障碍物标签，对神经网络模型进行训练得到的。障碍物标签用于指示第二样本传感数据中是否存在障碍物。
使用第二识别结果对第一识别结果进行修正，包括：确定第二识别结果为修正后的第一识别结果。
由于TOF传感器140的采集视野有限，因此，在使用单个TOF传感器采集数据的情况下，可能导致采集不到TOF传感器采集视野以外的传感数据的问题，从而导致传感数据不够准确的问题，基于上述技术问题，本实施例中，通过每组TOF传感器中的辅传感器采集的传感数据对主传感器采集的传感数据进行修正，可以避免单个TOF传感器采集的数据不精准的问题，从而提高建图或者避障的准确性。
在另一个示例中，基于传感数据控制自移动设备工作，包括：根据当前工作需求确定每组TOF传感器中的各个TOF传感器的融合权重；将各个TOF传感器采集的传感数据与对应的融合权重进行加权融合，得到工作结果。
可选地，每组TOF传感器包括第一TOF传感器和第二TOF传感器。
其中，第一TOF传感器的测距范围大于第二TOF传感器的测距范围。
示意性地，当确定当前工作需求为建图的情况下，各个TOF传感器的融合权重与TOF传感器的测距范围呈正相关关系。
比如：当确定当前工作需求为建图的情况下，确定第一TOF传感器的融合权重为0.7，第二TOF传感器的融合权重为0.3，此时将第一TOF传感器采集的传感数据和第二TOF传感器的传感数据，与对应的融合权重进行加权求和，得到工作结果。
综上所述，本实施例提供的自移动设备的控制方法，通过在自移动设备在目标区域内移动过程中，获取每组TOF传感器采集的传感数据；基于传感数据控制自移动设备工作；可以解决使用视觉传感器进行建图的计算量较大，建图效率较低的问题；由于TOF传感器采集的传感数据为深度信息，此时，自移动设备只需要对深度信息进行计算即可，相较于图像识别来说，深度信息的计算量较低，因此，可以减少建图的计算量，提高建图效率。
另外，由于不同的TOF传感器的采集视野不同，因此，在针对不同工作需求进行工作时，若不根据工作需求使用相同相应采集视野的TOF传感器，可能会导致在进行工作时数据采集不够准确的问题。基于上述技术问题，本实施例中，根据当前工作需求确定每组TOF传感器中的主传感器，这样，在根据当前工作需求选择相应采集视野的传感器作为主传感器进行数据采集，可以使得在不同工作需求的情况下，TOF传感器可以针对性地采集不同采集视野的传感数据，可以提高数据采集的准确性。
另外，由于TOF传感器140的采集视野有限，因此，在使用单个TOF传感器采集数据的情况下，可能导致采集不到TOF传感器采集视野以外的传感数据的问题，从而导致传感数据不够准确的问题，基于上述技术问题，本实施例中，通过每组TOF传感器中的辅传感器采集的传感数据对主传感器采集的传感数据进行修正，可以避免单个TOF传感器采集的数据不精准的问题，从而提高建图或者避障的准确性。
图5是本申请一个实施例提供的自移动设备控制装置的框图，本实施例以该装置应用于自移动设备中为例进行说明。该装置至少包括以下几个模块：数据采集模块510和工作控制模块520。
数据采集模块510，用于在自移动设备在目标区域内移动过程中，获取每组TOF传感器采集的传感数据.
工作控制模块520，用于基于传感数据控制自移动设备工作。
相关细节参考上述实施例。
需要说明的是：上述实施例中提供的自移动设备控制装置在进行控制时，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将自移动设备控制装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。另外，上述实施例提供的自移动设备控制装置与自移动设备控制方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
本实施例提供一种电子设备，如图6所示，该电子设备可以为自移动设备。该电子设备至少包括处理器601和存储器602。
处理器601可以包括一个或多个处理核心，比如：4核心处理器、8核心处理器等。处理器601可以采用DSP（Digital Signal Processing，数字信号处理）、FPGA（Field－Programmable Gate Array，现场可编程门阵列）、PLA（Programmable Logic Array，可编程逻辑阵列）中的至少一种硬件形式来实现。处理器601也可以包括主处理器和协处理器，主处理器是用于对在唤醒状态下的数据进行处理的处理器，也称CPU（Central Processing Unit，中央处理器）；协处理器是用于对在待机状态下的数据进行处理的低功耗处理器。在一些实施例中，处理器601可以在集成有GPU（Graphics Processing Unit，图像处理器）， GPU用于负责显示屏所需要显示的内容的渲染和绘制。一些实施例中，处理器601还可以包括AI（Artificial Intelligence，人工智能）处理器，该AI处理器用于处理有关机器学习的计算操作。
存储器602可以包括一个或多个计算机可读存储介质，该计算机可读存储介质可以是非暂态的。存储器602还可包括高速随机存取存储器，以及非易失性存储器，比如一个或多个磁盘存储设备、闪存存储设备。在一些实施例中，存储器602中的非暂态的计算机可读存储介质用于存储至少一个指令，该至少一个指令用于被处理器601所执行以实现本申请中方法实施例提供的自移动设备的控制方法。
在一些实施例中，电子设备还可选包括有：外围设备接口和至少一个外围设备。处理器601、存储器602和外围设备接口之间可以通过总线或信号线相连。各个外围设备可以通过总线、信号线或电路板与外围设备接口相连。示意性地，外围设备包括但不限于：射频电路、触摸显示屏、音频电路、和电源等。
当然，电子设备还可以包括更少或更多的组件，本实施例对此不作限定。
可选地，本申请还提供有一种计算机可读存储介质，计算机可读存储介质中存储有程序，程序由处理器加载并执行以实现上述方法实施例的自移动设备控制方法。
以上所述实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。

Claims (1)

  1.  一种自移动设备的控制方法，其特征在于，所述自移动设备设置有至少一组飞行时间TOF传感器，每组TOF传感器包括至少两个TOF传感器，所述方法包括：
    在所述自移动设备在目标区域内移动过程中，获取每组TOF传感器采集的传感数据；
    基于所述传感数据控制所述自移动设备工作。
    2. 根据权利要求1所述的方法，其特征在于，每组TOF传感器的排列方向垂直于所述自移动设备机身所在的平面。
    3.根据权利要求1所述的方法，其特征在于，每组TOF传感器的排列方向平行于所述自移动设备机身所在的平面。
    4.根据权利要求1所述的方法，其特征在于，每组TOF传感器的排列方向与所述自移动设备机身所在的平面呈夹角。
    5.根据权利要求1至4任一所述的方法，其特征在于，同一组TOF传感器中的至少两个TOF传感器的传感精度相同。
    6.根据权利要求1至4任一所述的方法，其特征在于，同一组TOF传感器中的至少两个TOF传感器的传感精度不相同，且每组TOF传感器的采集视野存在重叠部分。
    7.根据权利要求6所述的方法，其特征在于，每组TOF传感器包括两个TOF传感器。
    8. 根据权利要求1至7任一所述的方法，其特征在于，所述TOF传感器为面阵TOF传感器。
    9. 根据权利要求1至8任一所述的方法，其特征在于，所述基于所述传感数据控制所述自移动设备工作，包括：
    根据当前工作需求确定所述每组TOF传感器中的主传感器；
    按照所述当前工作需求对所述主传感器采集的传感数据进行处理，得到初始处理结果；
    使用所述每组TOF传感器中除所述主传感器之外的辅传感器采集的传感数据，对所述初始处理结果进行修正，得到工作结果。
    10. 根据权利要求9所述的方法，其特征在于，所述每组TOF传感器包括第一TOF传感器和第二TOF传感器，所述第一TOF传感器的测距范围大于所述第二TOF传感器的测距范围；所述根据当前工作需求确定所述每组TOF传感器中的主传感器，包括：
    在所述当前工作需求为地图构建的情况下，确定所述每组TOF传感器中的所述第一TOF传感器为主传感器；
    在所述当前工作需求为障碍物识别的情况下，确定所述每组TOF传感器中的所述第二TOF传感器为主传感器。
    11. 根据权利要求9所述的方法，其特征在于，在所述当前工作需求为地图构建的情况下，所述初始处理结果包括初始区域地图，所述初始区域地图包括基于所述主传感器采集的传感数据得到的第一障碍物信息；
    相应地，所述使用所述每组TOF传感器中除所述主传感器之外的辅传感器采集的传感数据，对所述初始处理结果进行修正，得到工作结果，包括：
    基于所述辅传感器采集的传感数据确定第二障碍物信息；
    使用所述第二障碍物信息对所述第一障碍物信息进行修正，得到区域地图。
    12. 根据权利要求11所述的方法，其特征在于，所述辅传感器的数量为至少两个，所述使用所述第二障碍物信息对所述第一障碍物信息进行修正，得到区域地图，包括：
    基于每个辅传感器的测距范围确定所述辅传感器的修正权重，所述修正权重与所述测距范围呈负相关关系；
    使用每个第二障碍物信息与对应的修正权重的加权和，对所述第一障碍物信息进行修正，得到所述区域地图。
    13. 根据权利要求9所述的方法，其特征在于，在所述当前工作需求为障碍物识别的情况下，所述初始处理结果包括基于所述主传感器采集的传感数据得到的第一识别结果，所述第一识别结果包括是否存在障碍物；
    相应地，所述使用所述每组TOF传感器中除所述主传感器之外的辅传感器采集的传感数据，对所述初始处理结果进行修正，得到工作结果，包括：
    基于所述辅传感器采集的传感数据确定第二识别结果，所述第二识别结果包括是否存在障碍物；
    使用所述第二识别结果对所述第一识别结果进行修正，得到障碍物信息。
    14.根据权利要求1至8任一所述的方法，其特征在于，所述基于所述传感数据控制所述自移动设备工作，包括：
    根据当前工作需求确定每组TOF传感器中的各个TOF传感器的融合权重；
    将各个TOF传感器采集的传感数据与对应的融合权重进行加权融合，得到工作结果。
    15.根据权利要求1至14任一所述的方法，其特征在于，所述获取每组TOF传感器采集的传感数据，包括：
    获取所述自移动设备的移动方向和不同移动方向与不同组别的TOF传感器的对应关系；
    基于所述对应关系确定获取每组TOF传感器采集的传感数据。
    16.根据权利要求15所述的方法，其特征在于，所述自移动设备包括2组TOF传感器，其一组TOF传感器设置在所述自移动设备的正前方，另一组TOF传感器设置在所述自移动设备的正后方；所述基于所述对应关系确定获取每组TOF传感器采集的传感数据，包括：
    在所述自移动设备向前方行进时，获取正前方的一组TOF传感器的传感数据；
    在所述自移动设备倒退时，获取正后方的一组TOF传感器的传感数据。
    17. 一种电子设备，其特征在于，所述设备包括处理器和存储器；所述存储器中存储有程序，所述程序由所述处理器加载并执行以实现如权利要求1至16任一所述的自移动设备的控制方法。
    18．一种计算机可读存储介质，其特征在于，所述存储介质中存储有程序，所述程序被处理器执行时用于实现如权利要求1至16任一所述的自移动设备的控制方法。
PCT/CN2023/087711 2022-05-06 2023-04-12 自移动设备的控制方法、设备及存储介质 Ceased WO2023213172A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210484952.XA CN117055541A (zh) 2022-05-06 2022-05-06 自移动设备的控制方法、设备及存储介质
CN202210484952.X 2022-05-06

Publications (1)

Publication Number Publication Date
WO2023213172A1 true WO2023213172A1 (zh) 2023-11-09

Family

ID=88646218

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/087711 Ceased WO2023213172A1 (zh) 2022-05-06 2023-04-12 自移动设备的控制方法、设备及存储介质

Country Status (2)

Country Link
CN (1) CN117055541A (zh)
WO (1) WO2023213172A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025190391A1 (zh) * 2024-03-15 2025-09-18 北京石头创新科技有限公司 自移动设备的环境感知方法、自移动设备、介质、设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009031884A (ja) * 2007-07-25 2009-02-12 Toyota Motor Corp 自律移動体、自律移動体におけるマップ情報作成方法および自律移動体における移動経路特定方法
CN106612387A (zh) * 2015-10-15 2017-05-03 杭州海康威视数字技术股份有限公司 一种组合深度图获得方法及深度相机
CN108814452A (zh) * 2018-08-22 2018-11-16 上海炬佑智能科技有限公司 扫地机器人及其障碍检测方法
CN112204486A (zh) * 2018-04-03 2021-01-08 尚科宁家运营有限公司 机器人导航的飞行时间传感器布置及用其定位的方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009031884A (ja) * 2007-07-25 2009-02-12 Toyota Motor Corp 自律移動体、自律移動体におけるマップ情報作成方法および自律移動体における移動経路特定方法
CN106612387A (zh) * 2015-10-15 2017-05-03 杭州海康威视数字技术股份有限公司 一种组合深度图获得方法及深度相机
CN112204486A (zh) * 2018-04-03 2021-01-08 尚科宁家运营有限公司 机器人导航的飞行时间传感器布置及用其定位的方法
CN108814452A (zh) * 2018-08-22 2018-11-16 上海炬佑智能科技有限公司 扫地机器人及其障碍检测方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025190391A1 (zh) * 2024-03-15 2025-09-18 北京石头创新科技有限公司 自移动设备的环境感知方法、自移动设备、介质、设备

Also Published As

Publication number Publication date
CN117055541A (zh) 2023-11-14

Similar Documents

Publication Publication Date Title
CN110023867B (zh) 用于机器人绘图的系统和方法
CN112171675B (zh) 一种移动机器人的避障方法、装置、机器人及存储介质
CN110703747A (zh) 一种基于简化广义Voronoi图的机器人自主探索方法
CN113741438A (zh) 路径规划方法、装置、存储介质、芯片及机器人
WO2024037299A1 (zh) 定位方法、装置、机器人和存储介质
CN207373179U (zh) 一种用于slam及导航的机器人控制系统
AU2021314387A1 (en) Automatic recharging method and apparatus, storage medium, charging base, and system
CN113985894B (zh) 一种自主避障路径规划方法、装置、设备及存储介质
WO2021003983A1 (zh) 回归引导方法、回归引导装置、移动机器人及存储介质
CN115318759B (zh) 一种基于无人机的绝缘子激光清洗方法及系统
KR20200102378A (ko) 정보 처리 방법, 장치 및 저장 매체
CN116300875A (zh) 水位线信息的获取方法、装置以及泳池清洁机器人
CN119068055B (zh) 一种移动机器人的自动控制方法及控制器
EP4177790A1 (en) Map creation method and apparatus for self-moving device, and device and storage medium
CN115366097A (zh) 机器人跟随方法、装置、机器人及计算机可读存储介质
WO2023213172A1 (zh) 自移动设备的控制方法、设备及存储介质
CN114609925A (zh) 水下探索策略模型的训练方法及仿生机器鱼水下探索方法
WO2023045749A1 (zh) 充电设备、自移动设备、充电方法、系统及存储介质
EP4675388A1 (en) Path planning method, related device for path planning method, and robot
CN116045961A (zh) 导航方法、装置、电子设备及存储介质
KR102394062B1 (ko) 수중 위치추적장치 및 그 제어 방법
CN120651237B (zh) 一种泳池机器人的多模态惯性导航方法及系统
WO2023179393A1 (zh) 区域划分方法、设备及存储介质
US12535334B2 (en) Autonomous travel route planning method, autonomous traveling method, and program
CN116576859B (zh) 路径导航方法、作业控制方法及相关装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23799159

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 23799159

Country of ref document: EP

Kind code of ref document: A1