CN117470227A - Obstacle avoidance smoothness detection method, obstacle avoidance smoothness detection device, and storage medium - Google Patents
Obstacle avoidance smoothness detection method, obstacle avoidance smoothness detection device, and storage medium Download PDFInfo
- Publication number
- CN117470227A CN117470227A CN202311230868.6A CN202311230868A CN117470227A CN 117470227 A CN117470227 A CN 117470227A CN 202311230868 A CN202311230868 A CN 202311230868A CN 117470227 A CN117470227 A CN 117470227A
- Authority
- CN
- China
- Prior art keywords
- obstacle avoidance
- smoothness
- curvature
- events
- path
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 73
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 230000033001 locomotion Effects 0.000 claims abstract description 89
- 238000000034 method Methods 0.000 claims abstract description 88
- 230000001133 acceleration Effects 0.000 claims description 54
- 238000005096 rolling process Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 14
- 238000005259 measurement Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 5
- 230000001960 triggered effect Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 101100039010 Caenorhabditis elegans dis-3 gene Proteins 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 101100030351 Schizosaccharomyces pombe (strain 972 / ATCC 24843) dis2 gene Proteins 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000005358 geomagnetic field Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
Abstract
The application discloses a method for detecting obstacle avoidance smoothness, an apparatus for detecting obstacle avoidance smoothness and a readable storage medium, wherein the method comprises the following steps: acquiring motion parameter information of mobile equipment in the travelling process; detecting obstacle avoidance events of the motion parameter information, and obtaining the number of the obstacle avoidance events of the mobile equipment in the advancing process; and detecting the obstacle avoidance smoothness of the number of obstacle avoidance events, and obtaining the obstacle avoidance smoothness of the mobile equipment in the travelling process. According to the obstacle avoidance smoothness detection method, the obstacle avoidance smoothness detection can be realized according to the obtained number of obstacle avoidance events by carrying out the obstacle avoidance event detection on the motion parameter information of the self-moving equipment in the advancing process, the detection process is simple, the obstacle avoidance event triggered by the obstacle avoidance of the self-moving equipment in the advancing process is fully considered, and the obstacle avoidance smoothness of the self-moving equipment can be detected simply, conveniently and accurately.
Description
Technical Field
The present application relates to the field of artificial intelligence, and in particular, to a method for detecting obstacle avoidance smoothness, an apparatus for detecting obstacle avoidance smoothness, and a computer-readable storage medium.
Background
With the rapid development of self-mobile device (e.g., mobile robot) technology, the range of applications of self-mobile devices is becoming wider and wider. In actual production and life, the self-mobile device is widely applied to the fields of storage, logistics, security protection and the like, the self-mobile device is often required to avoid obstacles in the operation process, and the obstacle avoidance capability of the self-mobile device can be used for measuring the performance of the self-mobile device. However, at present, there is no simple and accurate method for detecting the obstacle avoidance smoothness of the mobile device. Therefore, how to simply and accurately detect the obstacle avoidance smoothness of the self-mobile device is a problem to be solved.
Disclosure of Invention
The application provides an obstacle avoidance smoothness detection method, an obstacle avoidance smoothness detection device and a computer readable storage medium, which solve the problem that the related technology does not have a simple, convenient and accurate method for detecting the obstacle avoidance smoothness of a self-mobile device.
In a first aspect, the present application provides a method for detecting obstacle avoidance smoothness, where the method includes:
acquiring motion parameter information of mobile equipment in the travelling process; detecting obstacle avoidance events of the motion parameter information to obtain the number of obstacle avoidance events of the self-mobile equipment in the advancing process; and detecting the obstacle avoidance smoothness of the number of obstacle avoidance events to obtain the obstacle avoidance smoothness of the self-mobile equipment in the advancing process.
According to the obstacle avoidance smoothness detection method, the obstacle avoidance smoothness detection can be realized according to the obtained number of obstacle avoidance events by carrying out the obstacle avoidance event detection on the motion parameter information of the self-moving equipment in the advancing process, the detection process is simple, the obstacle avoidance event triggered by the obstacle avoidance of the self-moving equipment in the advancing process is fully considered, and the obstacle avoidance smoothness of the self-moving equipment can be detected simply, conveniently and accurately.
In a second aspect, the present application further provides a self-mobile device, including a memory, a processor, a camera, and an inertial measurement unit;
the shooting device is used for collecting path track information;
the inertial measurement unit is used for acquiring motion parameter information;
the memory is used for storing a computer program;
the processor is configured to execute the computer program and implement the obstacle avoidance smoothness detection method as described above when the computer program is executed.
In a third aspect, the present application further provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a processor causes the processor to implement the method for detecting obstacle avoidance smoothness as described above.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of an obstacle avoidance smoothness detection device according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a method for detecting obstacle avoidance smoothness according to an embodiment of the present application;
FIG. 3 is a graph of angular velocity provided by an embodiment of the present application;
FIG. 4 is a dot-plot of acceleration provided by an embodiment of the present application;
FIG. 5 is a schematic flow chart diagram of another obstacle avoidance smoothness detection method provided by an embodiment of the present application;
FIG. 6 is a schematic flow chart of a sub-step of path smoothness detection provided by an embodiment of the present application;
fig. 7 is a schematic diagram of a path track provided in an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
It is to be understood that the terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
The embodiment of the application provides an obstacle avoidance smoothness detection method, an obstacle avoidance smoothness detection device and a computer readable storage medium. The obstacle avoidance smoothness detection method can be applied to obstacle avoidance smoothness detection equipment, and can detect the obstacle avoidance smoothness of the self-moving equipment simply, conveniently and accurately by detecting the obstacle avoidance event according to the obtained number of the obstacle avoidance events by carrying out the obstacle avoidance event detection on the motion parameter information of the self-moving equipment in the advancing process, and fully considering the obstacle avoidance event triggered by the obstacle avoidance of the self-moving equipment in the advancing process.
The obstacle avoidance smoothness detection device may be a self-mobile device or an electronic device external to the self-mobile device.
The self-moving device may be a mobile robot such as a sweeping robot, a meal delivery robot, a snowplow robot, a greeting robot, or a vehicle such as an automobile with an automatic driving function.
The electronic device may be a server or a terminal. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. The terminal can be electronic equipment such as a smart phone, a tablet computer, a notebook computer, a desktop computer and the like.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an obstacle avoidance smoothness detection device 1000 according to an embodiment of the present disclosure. The obstacle avoidance smoothness detection device 1000 may comprise a processor 1001, a memory 1002, a camera 1003, and an inertial measurement unit 1004, where the processor 1001, the memory 1002, the camera 1003, and the inertial measurement unit 1004 may be connected by a bus, which may be any suitable bus such as an integrated circuit (Inter-integrated Circuit, I2C) bus.
The memory 1002 may include a storage medium and an internal memory, among others. The storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor 1001 to perform the obstacle avoidance smoothness detection method described in any one of the embodiments.
And a shooting device 1003 for acquiring path track information. The photographing device 1003 may be a monocular camera, a binocular camera, or any other type of camera, and is not limited herein. In the embodiment of the present application, taking the photographing device 1003 as a monocular camera as an example, how to collect path track information may be described. It should be noted that, the monocular camera may acquire information of a scene through an image captured by one lens. Although the monocular camera cannot directly acquire three-dimensional depth information, some three-dimensional information can be inferred from the image captured by the monocular camera by using computer vision and image processing techniques. For example, camera localization and creation of a three-dimensional model of a scene may be achieved by estimating camera motion from a sequence of consecutive images using feature point matching and motion estimation algorithms.
And an inertial measurement unit 1004, configured to collect motion parameter information. In the present embodiment, the inertial measurement unit (Inertial Measurement Unit, IMU) 1004 is a measurement device for measuring and reporting acceleration, angular velocity, and geomagnetic field information of an object. The inertial measurement unit 1004 typically includes sensors such as accelerometers, gyroscopes, and magnetometers. The accelerometer is used for measuring the acceleration of the object, and can detect the linear acceleration change of the object in three axes. The gyroscope is used for measuring the angular velocity of an object, and can detect the rotation speed of the object around three axes. Magnetometers are used to measure the magnetic field in which an object is located, and can provide directional information of the object relative to the earth's magnetic field. By combining the measurement data of the above-described sensors, the inertial measurement unit 1004 can provide the posture (including direction and angle) of the object and the change conditions of acceleration and angular velocity.
The processor 1001 is configured to provide computing and control capabilities, and support the operation of the overall obstacle avoidance smoothness detection device 1000.
The processor 1001 may be a central processing unit (Central Processing Unit, CPU) and may also be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (application specific integrated circuit, ASIC), a Field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The general purpose processor may be a microprocessor, or it may be any conventional processor or the like.
In one embodiment, the processor 1001 is configured to execute a computer program stored in the memory 1002, so as to implement the following steps:
acquiring motion parameter information of mobile equipment in the travelling process; detecting obstacle avoidance events of the motion parameter information, and obtaining the number of the obstacle avoidance events of the mobile equipment in the advancing process; and detecting the obstacle avoidance smoothness of the number of obstacle avoidance events, and obtaining the obstacle avoidance smoothness of the mobile equipment in the travelling process.
In one embodiment, the processor 1001 is further configured to implement:
acquiring path track information of the mobile equipment in the travelling process; detecting path smoothness of the path track information to obtain path smoothness of the mobile equipment in the running process; and detecting the path smoothness and the obstacle avoidance smoothness of the times of obstacle avoidance events, and obtaining the obstacle avoidance smoothness of the mobile equipment in the travelling process.
In one embodiment, the motion parameter information includes angular velocity and/or acceleration; the processor 1001 is configured to, when implementing obstacle avoidance event detection on motion parameter information and obtaining the number of obstacle avoidance events of the mobile device in the running process, implement:
detecting a head swing event of the angular velocity in the motion parameter information to obtain the frequency of the head swing event; detecting a pause event on the acceleration in the motion parameter information to obtain the times of the pause event; and determining the number of obstacle avoidance events according to the number of head swing events and/or the number of pause events.
In one embodiment, when implementing the detection of the yaw event for the angular velocity in the motion parameter information, the processor 1001 is configured to implement:
scrolling the angular speed in the motion parameter information according to a preset first scrolling time window; after each rolling, if the fluctuation range of the angular velocity in the first rolling time window is larger than a preset angular velocity threshold value, confirming triggering of the head-swing event and accumulating the triggering times until the rolling of the angular velocity in the motion parameter information is completed, and obtaining the times of the head-swing event.
In one embodiment, the processor 1001 is configured to, when implementing the detection of a quiesce event for acceleration in motion parameter information and obtaining the number of quiesce events, implement:
rolling the acceleration in the motion parameter information according to a preset second rolling time window; after each rolling, if the average value of the accelerations in the second rolling time window is in a preset acceleration range, confirming triggering of the pause event and accumulating the triggering times until the rolling of the accelerations in the motion parameter information is completed, and obtaining the times of the pause event.
In one embodiment, the processor 1001 is configured to, when implementing path smoothness detection on path trajectory information, obtain path smoothness from a mobile device during traveling, implement:
Determining a track point coordinate set of the self-mobile device according to the path track information; performing track point curvature calculation according to the track point coordinate set to obtain a track point curvature set; and calculating the path smoothness of the track point curvature set to obtain the path smoothness.
In one embodiment, the set of track point coordinates includes a plurality of track point coordinates recorded in time; when the processor 1001 performs the calculation of the curvature of the track point according to the coordinate set of the track point to obtain the curvature set of the track point, the processor is configured to perform:
sliding the coordinates of the plurality of track points according to a preset sliding time window; after each sliding, calculating the curvature of the track points in the sliding time window to obtain the curvature of the corresponding track points; and determining a track point curvature set according to the track point curvature corresponding to each sliding.
In one embodiment, the sliding time window includes first track point coordinates, second track point coordinates, third track point coordinates; the processor 1001 is configured to, when implementing calculating the curvature of the track point in the sliding time window and obtaining the curvature of the corresponding track point, implement:
calculating a first distance value between the first track point coordinate and the second track point coordinate; calculating a second distance value between the first track point coordinate and the third track point coordinate; calculating a third distance value between the second track point coordinate and a third track point coordinate; and determining the curvature of the track point according to the first distance value, the second distance value and the third distance value.
In one embodiment, before implementing the path smoothness calculation for the set of curvature of the track points, the processor 1001 is further configured to implement:
and filtering out the curvature of the track points in the curvature set of the track points, which is smaller than a preset curvature threshold value, so as to obtain the curvature set of the track points after filtering.
In one embodiment, when implementing the path smoothness calculation for the set of curvature of the track points, the processor 1001 is configured to implement:
and detecting the path smoothness of the filtered track point curvature set to obtain the path smoothness.
In one embodiment, when implementing the path smoothness calculation for the set of curvature of the track points, the processor 1001 is configured to implement:
determining curvature peak values, curvature average values and curvature variance corresponding to the track point curvature sets; weighting and summing the curvature peak value, the curvature mean value and the curvature variance based on a preset weight calculation formula to obtain a target curvature; and determining the path smoothness according to the target curvature.
In one embodiment, the number of obstacle avoidance events includes a number of head-swing events and a number of quiesce events; the processor 1001 is configured to, when implementing obstacle avoidance smoothness detection on the path smoothness and the number of obstacle avoidance events, obtain the obstacle avoidance smoothness of the mobile device in the running process, implement:
And respectively carrying out normalization processing and summation on the path smoothness, the times of head swing events and the times of pause events to obtain the obstacle avoidance smoothness.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict. Referring to fig. 2, fig. 2 is a schematic flowchart of a method for detecting obstacle avoidance smoothness according to an embodiment of the present disclosure. As shown in fig. 2, the obstacle avoidance smoothness detection method includes steps S101 to S103.
Step S101, motion parameter information of the mobile device in the traveling process is obtained.
For example, motion parameter information from a mobile device may be collected during travel from the mobile device. For example, motion parameter information from a mobile device may be acquired through an IMU disposed on the mobile device.
Wherein the motion parameter information may comprise angular velocity and/or acceleration. In the embodiment of the application, the IMU may collect the angular velocity of the mobile device in the running process, or collect the acceleration of the mobile device in the running process, or collect the angular velocity and the acceleration of the mobile device in the running process at the same time.
It should be noted that the angular velocity may be used to detect the number of times the self-moving device swings during traveling. For example, when the change in angular velocity is large, it is confirmed that a severe swing occurs from the mobile device. The violent swing times can be used for representing the decision quality of the temporary obstacle avoidance path generated in advance by the self-mobile equipment when encountering an obstacle. Acceleration refers to acceleration of the self-moving device in the x-axis direction during travel, i.e., the forward vector of the self-moving device, which can be used to detect whether the self-moving device is stationary. For example, when the acceleration drops to zero, a dwell from the mobile device is confirmed. Wherein the number of pauses may be used to characterize the smoothness of obstacle detouring when the self-moving device encounters an obstacle.
In the above embodiment, by acquiring the motion parameter information of the mobile device during the traveling process, whether the mobile device triggers the obstacle avoidance event may be detected later according to the motion parameter information.
Step S102, obstacle avoidance event detection is carried out on the motion parameter information, and the number of obstacle avoidance events of the mobile equipment in the advancing process is obtained.
For example, after the motion parameter information of the mobile device in the travelling process is obtained, the motion parameter information can be subjected to obstacle avoidance event detection, so that the number of obstacle avoidance events of the mobile device in the travelling process is obtained.
In some embodiments, the detecting the obstacle avoidance event of the motion parameter information, which is obtained from the number of obstacle avoidance events of the mobile device in the travelling process, may include: detecting a head swing event of the angular velocity in the motion parameter information to obtain the frequency of the head swing event; and determining the number of obstacle avoidance events according to the number of head swing events.
It should be noted that, in the embodiment of the present application, when the motion parameter information includes an angular velocity, the angular velocity in the motion parameter information may be detected for a head-swing event, so as to obtain the number of times of the head-swing event. How to detect a trigger for a yaw event from a mobile device will be described in detail below.
In some embodiments, detecting the yaw event for the angular velocity in the motion parameter information, and obtaining the number of yaw events may include: scrolling the angular speed in the motion parameter information according to a preset first scrolling time window; after each rolling, if the fluctuation range of the angular velocity in the first rolling time window is larger than a preset angular velocity threshold value, confirming triggering of the head-swing event and accumulating the triggering times until the rolling of the angular velocity in the motion parameter information is completed, and obtaining the times of the head-swing event.
The time length of the first rolling time window may be denoted as T1, and the time length T1 may be set according to practical situations, and specific values are not limited herein. For example, the time length T1 may be 0.5s. The fluctuation range of the angular velocity means the difference between the maximum value and the minimum value of the angular velocity in the first rolling time window.
Referring to fig. 3, fig. 3 is a graph of angular velocity according to an embodiment of the present application. As shown in fig. 3, the horizontal axis represents time and the vertical axis represents angular velocity. The whole course angle change can be obtained by integrating the angular velocity data acquired by the IMU according to time, and the following formula is shown:
wherein t is k Represents the kth time, ω (t) k ) Represents the angular velocity, θ (t k ) Indicating the corresponding angular velocity throughout from the mobile device.
For example, the angular velocity in the motion parameter information is scrolled according to a first scroll time window with a time length of 0.5s, and after each scroll, it is determined that the fluctuation range of the angular velocity in the first scroll time window is greater than a preset angular velocity threshold. And if the fluctuation amplitude of the angular velocity in the first rolling time window is larger than a preset angular velocity threshold value, confirming triggering of the swing event and accumulating the triggering times. The preset angular velocity threshold may be set according to actual situations, and specific values are not limited herein. For example, the angular velocity threshold may be 40 °, and if the fluctuation amplitude of the angular velocity in the first rolling time window is greater than 40 °, the trigger of the head-swing event is confirmed and 1 is added on the basis of the number of the original head-swing events. The number of swing events may be denoted as n.
For example, the total number of yaw events may be obtained after scrolling through the angular velocity in the motion parameter information is completed. And then, determining the total swing event times as obstacle avoidance event times. At this time, the number of obstacle avoidance events may include the number of swing events.
According to the embodiment, the head-swing event number can be used as the obstacle-avoidance event number by detecting the head-swing event of the angular velocity in the motion parameter information and determining the obstacle-avoidance event number according to the obtained head-swing event number.
In other embodiments, the detecting the obstacle avoidance event of the motion parameter information, which is obtained from the number of obstacle avoidance events of the mobile device in the travelling process, may include: detecting a pause event on the acceleration in the motion parameter information to obtain the times of the pause event; and determining the number of obstacle avoidance events according to the number of the pause events.
It should be noted that, in the embodiment of the present application, when the motion parameter information includes acceleration, the acceleration in the motion parameter information may be detected to obtain the number of times of the quiescence event. How to perform the quiesce event detection will be described in detail below.
In some embodiments, the detecting the stall event on the acceleration in the motion parameter information to obtain the number of stall events may include: rolling the acceleration in the motion parameter information according to a preset second rolling time window; after each rolling, if the average value of the accelerations in the second rolling time window is in a preset acceleration range, confirming triggering of the pause event and accumulating the triggering times until the rolling of the accelerations in the motion parameter information is completed, and obtaining the times of the pause event.
The size of the second rolling time window may be expressed for a time length or for a frame number. For example, the time length of the second rolling time window may be denoted as T2, and the time length T2 may be set according to practical situations, and the specific value is not limited herein. For example, the time length T2 may be 1s. The average of the accelerations refers to the average of all accelerations in the second rolling time window.
Referring to fig. 4, fig. 4 is a dot-like diagram of acceleration according to an embodiment of the present application. As shown in fig. 4, the horizontal axis represents time and the vertical axis represents angular velocity. Since the IMU has zero drift, the determination increment is used instead of the integral of acceleration in determining whether the self-moving device is in a stopped state. The self-moving device is stopped at the beginning, and as shown in fig. 4, the acceleration ax on the x-axis oscillates at a fixed value in a steady state. The acceleration ax, which may be taken from the mobile device before starting to travel (e.g., the previous k frames), may be averaged to obtain the stall acceleration argax from when the mobile device is stopped. In the embodiment of the present application, the preset acceleration range may be set to argax±esp, where esp is a tolerance.
For example, the acceleration in the motion parameter information is scrolled according to a second scrolling time window with a time length of 1s, and after each scrolling, if the average value of the accelerations in the second scrolling time window is within the acceleration range argax±esp. And if the average value of the accelerations in the second rolling time window is in the acceleration range argax+/-esp, confirming triggering of the pause event and accumulating the triggering times until the rolling of the accelerations in the motion parameter information is completed, and obtaining the times of the pause event. The number of quiesce events may be denoted as i.
For example, the total number of quiescence events may be obtained after scrolling to acceleration in the motion parameter information is completed. And then, determining the total number of the pause events as the number of the obstacle avoidance events. At this time, the number of obstacle avoidance events may include the number of quiesce events.
According to the embodiment, the number of the stall events can be used as the number of the obstacle avoidance events by detecting the stall event of the acceleration in the motion parameter information and determining the number of the obstacle avoidance events according to the obtained number of the stall events.
In other embodiments, the detecting the obstacle avoidance event on the motion parameter information, which is obtained from the number of obstacle avoidance events of the mobile device in the travelling process, may further include: detecting a head swing event of the angular velocity in the motion parameter information to obtain the frequency of the head swing event; detecting a pause event on the acceleration in the motion parameter information to obtain the times of the pause event; and determining the number of obstacle avoidance events according to the number of head swing events and the number of pause events.
It should be noted that, in the embodiment of the present application, when the motion parameter information includes an angular velocity and an acceleration, the detection of a yaw event may be performed on the angular velocity in the motion parameter information or the detection of a pause event may be performed on the acceleration in the motion parameter information, or the detection of a yaw event may be performed on the angular velocity in the motion parameter information and the detection of a pause event may be performed on the acceleration in the motion parameter information at the same time.
For example, the angular velocity in the motion parameter information may be subjected to a head-swing event detection, so as to obtain the number of head-swing events. For a specific process of detecting the swing event, refer to the above embodiment, and the specific process is not described herein.
For example, the acceleration in the motion parameter information may be detected as a quiescence event, to obtain the number of quiescence events. For a specific process of detecting the quiesce event, refer to the above embodiment, and the specific process is not described herein.
After the number of the head swing events and the number of the pause events are detected, the number of the obstacle avoidance events can be determined according to the number of the head swing events and the number of the pause events. For example, the number of head-swing events and the number of quiesce events may be determined as the number of obstacle avoidance events. At this time, the number of obstacle avoidance events may include the number of head swing events and the number of pause events.
According to the embodiment, the obstacle avoidance event times are determined according to the head swing event times and the pause event times, and then the obstacle avoidance fluency of the self-moving equipment can be jointly determined by adopting the two indexes of head swing and pause, so that the probability of misjudgment can be reduced to the greatest extent, and the accuracy of obstacle avoidance fluency detection is improved.
Step S103, obstacle avoidance smoothness detection is carried out on the number of obstacle avoidance events, and the obstacle avoidance smoothness of the mobile equipment in the advancing process is obtained.
For example, after the number of obstacle avoidance events obtained from the mobile device in the travelling process is obtained, the number of obstacle avoidance events may be detected to obtain the obstacle avoidance smoothness of the mobile device in the travelling process.
The obstacle avoidance smoothness detection is carried out on the number of obstacle avoidance events, the detection process is simple, the obstacle avoidance events triggered by the obstacle avoidance in the travelling process of the self-moving equipment are fully considered, and the obstacle avoidance smoothness of the self-moving equipment can be simply, conveniently and accurately detected.
In the embodiment of the application, in order to eliminate the dimensional influence among different indexes, when the obstacle avoidance smoothness is detected on the number of obstacle avoidance events, normalization processing is required to be performed on the number of obstacle avoidance events.
In some embodiments, when the number of obstacle avoidance events includes the number of head-swing events, the number of head-swing events may be normalized to obtain a head-swing event score. Then, the swing event score is determined as obstacle avoidance fluency. Wherein, the maximum swing event times n can be set according to the use scene of the self-mobile device max According to the maximum swing event times n max Normalizing the frequency n of the head-swing event to obtain the score of the head-swing event as follows:
wherein n is normalized Representing the head-swing event score.
According to the embodiment, the decision quality of the temporary obstacle avoidance path generated in advance by the self-mobile device when encountering the obstacle can be used as the fluency of the self-mobile device by determining the head swing event score as the obstacle avoidance fluency.
In other embodiments, when the number of obstacle avoidance events includes the number of quiesce events, the number of quiesce events may be normalized to obtain a quiesce event score. The quiesce event score is then determined as obstacle avoidance fluency. Wherein, the maximum pause event number i can be set according to the use scene of the self-mobile device max According to the maximum number i of pause events max Normalizing the number i of the pause events to obtain the score of the pause event as follows:
wherein i is normalized Representing the quiesce event score.
According to the embodiment, the pause event score is determined to be the obstacle avoidance smoothness, so that the smoothness of the self-mobile device around the obstacle when the self-mobile device encounters the obstacle can be used as the smoothness of the self-mobile device.
In some embodiments, when the number of obstacle avoidance events includes the number of head-swing events and the number of pause events, the number of head-swing events and the number of pause events may be normalized to obtain a head-swing event score and a pause event score. And then, the swing event score and the pause event score are added to determine the obstacle avoidance smoothness. Of course, the yaw event score and the pause event score may be weighted and summed according to the importance level to obtain the obstacle avoidance smoothness.
The lower the obstacle avoidance smoothness is, the better the obstacle avoidance capability of the self-mobile equipment when encountering an obstacle is.
According to the embodiment, the obstacle avoidance smoothness is determined according to the swing event score and the pause event score, so that the decision quality of generating the temporary obstacle avoidance path in advance when the self-moving equipment encounters an obstacle and the smoothness of the self-moving equipment around the obstacle when the self-moving equipment encounters the obstacle can be used as two indexes for measuring the smoothness of the self-moving equipment, and the obstacle avoidance smoothness of the self-moving equipment can be accurately detected.
Referring to fig. 5, fig. 5 is a schematic flowchart of another obstacle avoidance smoothness detection method according to an embodiment of the present disclosure. As shown in fig. 5, the obstacle avoidance smoothness detection method includes steps S201 to S204.
Step S201, obtaining path track information and motion parameter information of the mobile device during the running process.
For example, during the travelling process of the self-mobile device, the motion parameter information of the self-mobile device and the path track information of the self-mobile device in the travelling direction can be respectively acquired in real time through an IMU (inertial measurement unit) deployed on the self-mobile device.
It should be noted that the motion parameter information and the path track information may be collected separately. It will be appreciated that there is no need to keep the motion parameter information consistent in time with the path trajectory information due to the time stamps of the camera and IMU being inconsistent.
For example, the path trajectory information may include image data of the self-mobile device in the direction of travel. In the embodiment of the application, feature extraction can be performed on the image data shot by the shooting device, so as to obtain the track point coordinates of the self-mobile equipment.
In the above embodiment, by obtaining the path track information and the motion parameter information of the mobile device during the traveling process, the path smoothness of the mobile device may be detected according to the path track information, and whether the mobile device triggers the obstacle avoidance event may be detected according to the motion parameter information.
Step S202, path smoothness detection is carried out on path track information, and path smoothness of the mobile equipment in the running process is obtained.
For example, after the path track information of the mobile device in the travelling process is obtained, the path smoothness of the path track information can be detected, so that the path smoothness of the mobile device in the travelling process is obtained.
The path smoothness is used to indicate the smoothness of the path of the self-mobile device during walking. The smoother the path, the larger the corresponding turning radius, the inverse relation between the turning radius of the self-mobile device and the curvature, and the curvature can be used for measuring the path smoothness. The path smoothness may be denoted S.
According to the embodiment, the path smoothness is detected through the path track information, the path smoothness can be detected subsequently, the path smoothness when the self-mobile device walks is used as an index for measuring the obstacle avoidance smoothness, and the accuracy of the obstacle avoidance smoothness detection can be improved effectively.
Step S203, carrying out obstacle avoidance event statistics on the motion parameter information to obtain the number of obstacle avoidance events of the mobile equipment in the advancing process.
It is understood that step S203 is the same as step S102 described above, and will not be described herein.
Step S204, detecting the path smoothness and the obstacle avoidance event times to obtain the obstacle avoidance smoothness of the mobile equipment in the travelling process.
After the path smoothness and the obstacle avoidance event times of the mobile equipment in the travelling process are obtained, the obstacle avoidance smoothness detection can be carried out on the path smoothness and the obstacle avoidance event times, and the obstacle avoidance smoothness of the mobile equipment in the travelling process is obtained.
In some embodiments, the detecting the path smoothness and the number of obstacle avoidance events to obtain the obstacle avoidance smoothness of the mobile device in the travelling process may include: and respectively carrying out normalization processing and summation on the path smoothness, the times of head swing events and the times of pause events to obtain the obstacle avoidance smoothness.
For example, the path smoothness may be normalized to obtain normalized path smoothness.
For example, the maximum path smoothness S may be set according to the usage scenario of the self-mobile device max According to the maximum path smoothness S max The path smoothness S is normalized, and the normalized path smoothness is obtained as follows:
wherein S is normalized Indicating the normalized path smoothness.
For example, when the number of obstacle avoidance events includes the number of head-swing events and the number of pause events, the number of head-swing events and the number of pause events may be normalized, to obtain a head-swing event score and a pause event score, respectively. The normalization process of the number of the head swing events and the number of the pause events can be referred to the detailed description of the above embodiments, and will not be described herein.
In some embodiments, the normalized path smoothness S may be used in performing obstacle avoidance smoothness detection on the path smoothness and the number of obstacle avoidance events normalized Head-swing event score n normalized And a quiesce event score i normalized And adding to obtain the obstacle avoidance smoothness. Obstacle avoidance fluency may be expressed as:
Score＝S normalized +n normalized +i normalized
in the embodiment of the present application, the normalized path smoothness, the yaw event score and the pause event score may be weighted and summed according to the importance degree, so as to obtain the obstacle avoidance smoothness.
The lower the obstacle avoidance smoothness is, the better the obstacle avoidance capability of the self-mobile equipment when encountering an obstacle is.
According to the embodiment, the obstacle avoidance smoothness detection is carried out according to the path smoothness and the obstacle avoidance event times, the calculation process is simple, the curve size encountered by the self-moving equipment in the advancing process and the triggered obstacle avoidance event are fully considered, and the obstacle avoidance smoothness of the self-moving equipment can be simply, conveniently and accurately detected.
Referring to fig. 6, fig. 6 is a schematic flowchart of a sub-step of path smoothness detection according to an embodiment of the present application. As shown in fig. 6, the path smoothness detection of the path trajectory information in step S202 may include the following steps S301 to S303.
Step S301, determining a track point coordinate set of the self-mobile device according to the path track information.
The path trajectory information includes image data of the mobile device in a traveling direction, and a trajectory point coordinate set can be obtained by extracting a trajectory point from the image data. Wherein the set of track point coordinates includes a plurality of track point coordinates recorded in time.
In some embodiments, performing trace point extraction on image data may include: key feature points, such as corner points or edge points, are extracted from the image data and the change of the key feature points with time is tracked. Then, camera motion between adjacent image data is calculated, displacement and rotation of the self-mobile device on the trajectory are predicted, and by accumulating motion estimates for each time step, trajectory point coordinates of the self-mobile device on the path trajectory can be obtained.
For example, feature descriptors may be used to match and track key feature points. The feature descriptors may include, but are not limited to, SIFT (Scale-invariant feature transform, scale invariant feature transform), SURF (speed-up Robust Feature, an accelerated version of the SIFT algorithm), ORB (Oriented FAST and Rotated BRIEF, feature extraction based on the FAST algorithm), and the like. By tracking and analyzing the movement of key feature points, the pose change of the self-mobile device on the path track can be predicted.
For example, techniques such as optical streaming, direct, or sparse feature matching may be used to calculate camera motion between adjacent image data.
Referring to fig. 7, fig. 7 is a schematic diagram of a path track according to an embodiment of the present application. As shown in fig. 7, the path trajectory is an origin of a point coordinate system started from the mobile device, an x-axis direction from the traveling direction of the mobile device, and a y-axis direction discrete point (x k ,y k ) As shown in fig. 7, the start time is taken as a time stamp zero point to record the coordinates of discrete points, namely the coordinates of track points, of the whole travelling process of the mobile device.
And step S302, calculating the curvature of the track points according to the coordinate set of the track points to obtain the curvature set of the track points.
For example, after determining the set of trajectory point coordinates from the mobile device, a trajectory point curvature calculation may be performed from the set of trajectory point coordinates to obtain a set of trajectory point curvatures.
In some embodiments, performing the track point curvature calculation according to the track point coordinate set to obtain the track point curvature set may include: sliding the coordinates of the plurality of track points according to a preset sliding time window; after each sliding, calculating the curvature of the track points in the sliding time window to obtain the curvature of the corresponding track points; and determining a track point curvature set according to the track point curvature corresponding to each sliding.
The size of the sliding time window may be set according to practical situations, and specific values are not limited herein. In the embodiment of the present application, in order to facilitate calculation of the curvature of the track point, the size of the sliding time window may be the time length of three track point coordinates. I.e. three track point coordinates, e.g. a first track point coordinate, a second track point coordinate, a third track point coordinate, within the sliding time window. Wherein the first trajectory point coordinates may be expressed as (x) k-1 ,y k-1 ) The second trajectory point coordinates may be expressed as (x) k ,y k ) The third track point coordinates may be expressed as (x k+1 ,y k+1 )。
For example, after each sliding, the track point curvature in the sliding time window may be calculated according to the three track point coordinates in the sliding time window, so as to obtain the corresponding track point curvature. The following will describe in detail how the trajectory point curvature is calculated.
In the above embodiment, by calculating the curvature of the track point in the sliding time window after each sliding, the curvature of the track point corresponding to each sliding can be obtained.
In some embodiments, calculating the curvature of the track point within the sliding time window, resulting in a corresponding curvature of the track point, may include: calculating a first distance value between the first track point coordinate and the second track point coordinate; calculating a second distance value between the first track point coordinate and the third track point coordinate; calculating a third distance value between the second track point coordinate and a third track point coordinate; and determining the curvature of the track point according to the first distance value, the second distance value and the third distance value.
For example, a first distance value between the first track point coordinate and the second track point coordinate may be calculated, where the calculation formula of the first distance value is as follows:
Where dis1 represents a first distance value.
A second distance value between the first track point coordinate and the third track point coordinate may be calculated, where a calculation formula of the second distance value is as follows:
where dis2 represents the second distance value.
A third distance value between the second track point coordinate and the third track point coordinate may be calculated, where a calculation formula of the third distance value is as follows:
where dis3 represents a third distance value.
Illustratively, the trajectory point curvature is determined from the first distance value, the second distance value, and the third distance value. The calculation formula of the curvature of the track point is as follows:
where k represents the trajectory point curvature. Wherein,dis=dis 1+dis3 dis3-dis 2. By the above formulaTo calculate the track point curvature k, the specific calculation process is not described here in detail.
For example, after calculating the track point curvature corresponding to each slide, a track point curvature set may be generated according to the track point curvature corresponding to each slide.
In the above embodiment, the first distance value between the first track point coordinate and the second track point coordinate is calculated, the second distance value between the first track point coordinate and the third track point coordinate is calculated, the third distance value between the second track point coordinate and the third track point coordinate is calculated, and the track point curvature is determined according to the first distance value, the second distance value and the third distance value, so that the calculation process is simple, and the track point curvature can be conveniently calculated.
Step S303, calculating the path smoothness of the curvature set of the track points to obtain the path smoothness.
For example, after the track point curvature calculation is performed according to the track point coordinate set to obtain the track point curvature set, the track point curvature set may be subjected to the path smoothness calculation to obtain the path smoothness.
In some embodiments, performing a path smoothness calculation on the set of track point curvatures to obtain path smoothness may include: determining curvature peak values, curvature average values and curvature variance corresponding to the track point curvature sets; weighting and summing the curvature peak value, the curvature mean value and the curvature variance based on a preset weight calculation formula to obtain a target curvature; and determining the path smoothness according to the target curvature.
For example, a set of trajectory point curvatures may be traversed, querying a peak of curvature in the set of trajectory point curvatures, i.e., a maximum curvature. Wherein the curvature peak may be expressed as k max . Can be according to the formulaCalculating the curvature mean value k arg . Where size (k) represents the number of track point curvatures of the track point curvature set. Can be->Calculating the curvature variance k var . Wherein k is i The i-th track point curvature k is represented, and N represents the total number of track point curvatures.
For example, the curvature peak, the curvature mean and the curvature variance may be weighted and summed to obtain the target curvature based on a preset weight calculation formula. The preset weight calculation formula is as follows:
S＝a*k max +b*k arg +c*k var
wherein a represents a curvature peak k max Corresponding weights, b represents the curvature mean k arg Corresponding weights, c represents the peak value k of curvature var The corresponding weights, S, represent the target curvature.
For example, after calculating the target curvature, the target curvature may be determined as the path smoothness.
According to the embodiment, the curvature peak value, the curvature mean value and the curvature variance corresponding to the curvature set of the track point are respectively determined, and the curvature peak value, the curvature mean value and the curvature variance are weighted and summed, so that the path smoothness can be comprehensively and comprehensively determined according to the curvature peak value, the curvature mean value and the curvature variance, and the accuracy of calculating the path smoothness is improved.
In some embodiments, the calculating the path smoothness of the curvature set of the track point may further include, before obtaining the path smoothness: and filtering out the curvature of the track points in the curvature set of the track points, which is smaller than a preset curvature threshold value, so as to obtain the curvature set of the track points after filtering.
Since the straight line has no reference value for evaluating the path smoothness, the curvature of the trajectory point of the curve needs to be considered with emphasis. Because the curvature and the turning radius are in inverse relation, by filtering the curvature set of the track points, straight channels with smaller curvature can be filtered, and curved channels with larger curvature can be reserved. It will be appreciated that a curve with a larger turning radius approximates a straight path.
For example, the preset curvature threshold may be set according to practical situations, and specific values are not limited herein.
In the above embodiment, by filtering out the curvature of the track point in the curvature set of track points, which is smaller than the curvature threshold, the curvature corresponding to the straight line can be removed, and the interference of the straight line on the calculation of the path smoothness is avoided.
In some embodiments, performing a path smoothness calculation on the set of track point curvatures to obtain path smoothness may include: and detecting the path smoothness of the filtered track point curvature set to obtain the path smoothness.
For example, after the filtered set of track point curvatures, the filtered set of track point curvatures may be subjected to path smoothness detection to obtain path smoothness. The specific process of detecting the path smoothness for the filtered set of curvature points of the track may be referred to the detailed description of the above embodiment, which is not described herein.
Embodiments of the present application further provide a computer readable storage medium, where the computer readable storage medium stores a computer program, where the computer program includes program instructions, and a processor executes the program instructions to implement any one of the obstacle avoidance smoothness detection methods provided in the embodiments of the present application.
For example, the program is loaded by a processor, and the following steps may be performed:
acquiring motion parameter information of mobile equipment in the travelling process; detecting obstacle avoidance events of the motion parameter information, and obtaining the number of the obstacle avoidance events of the mobile equipment in the advancing process; and detecting the obstacle avoidance smoothness of the number of obstacle avoidance events, and obtaining the obstacle avoidance smoothness of the mobile equipment in the travelling process.
The computer readable storage medium may be an internal storage unit of the obstacle avoidance smoothness detection device of the foregoing embodiment, for example, a hard disk or a memory of the obstacle avoidance smoothness detection device. The computer readable storage medium may also be an external storage device of the obstacle avoidance smoothness detection device, for example, a plug-in hard disk, a Smart Media Card (SMC), a secure digital Card (Secure Digital Card, SD Card), a Flash memory Card (Flash Card) or the like provided on the obstacle avoidance smoothness detection device.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, a program required for at least one function, and the like; the storage data area may store data created according to each program, and the like.
The foregoing is merely a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any equivalent modifications or substitutions will be apparent to those skilled in the art within the scope of the present application, and these modifications or substitutions should be covered in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (13)
1. A method for detecting obstacle avoidance smoothness, the method comprising:
acquiring motion parameter information of mobile equipment in the travelling process;
detecting obstacle avoidance events of the motion parameter information to obtain the number of obstacle avoidance events of the self-mobile equipment in the advancing process;
and detecting the obstacle avoidance smoothness of the number of obstacle avoidance events to obtain the obstacle avoidance smoothness of the self-mobile equipment in the advancing process.
2. The obstacle avoidance smoothness detection method of claim 1, further comprising:
Acquiring path track information of the self-mobile device in the running process;
detecting path smoothness of the path track information to obtain the path smoothness of the self-mobile equipment in the running process;
and detecting the path smoothness and the obstacle avoidance smoothness of the times of the obstacle avoidance events to obtain the obstacle avoidance smoothness of the self-mobile equipment in the advancing process.
3. The obstacle avoidance smoothness detection method according to claim 1, wherein the motion parameter information includes angular velocity and/or acceleration; the step of detecting the obstacle avoidance event of the motion parameter information to obtain the number of obstacle avoidance events of the self-mobile device in the advancing process comprises the following steps:
detecting a head-swing event of the angular velocity in the motion parameter information to obtain the frequency of the head-swing event;
detecting a pause event on the acceleration in the motion parameter information to obtain the times of the pause event;
and determining the number of obstacle avoidance events according to the number of head swing events and/or the number of pause events.
4. The obstacle avoidance smoothness detection method according to claim 3, wherein said detecting the angular velocity in the motion parameter information to obtain the number of swing events comprises:
Scrolling the angular velocity in the motion parameter information according to a preset first scrolling time window;
after each rolling, if the fluctuation range of the angular velocity in the first rolling time window is larger than a preset angular velocity threshold value, confirming triggering of the head-swing event and accumulating the triggering times until the rolling of the angular velocity in the motion parameter information is completed, and obtaining the times of the head-swing event.
5. The method for detecting obstacle avoidance smoothness according to claim 3, wherein said detecting a quiescence event of the acceleration in the motion parameter information to obtain the number of quiescence events comprises:
rolling the acceleration in the motion parameter information according to a preset second rolling time window;
after each rolling, if the average value of the accelerations in the second rolling time window is in a preset acceleration range, confirming triggering of a pause event and accumulating triggering times until the rolling of the accelerations in the motion parameter information is completed, and obtaining the pause event times.
6. The obstacle avoidance smoothness detection method according to claim 2, wherein said performing path smoothness detection on the path trajectory information to obtain path smoothness of the self-mobile device during traveling comprises:
Determining a track point coordinate set of the self-mobile equipment according to the path track information;
performing track point curvature calculation according to the track point coordinate set to obtain a track point curvature set;
and calculating the path smoothness of the track point curvature set to obtain the path smoothness.
7. The obstacle avoidance smoothness detection method of claim 6 wherein said set of trace point coordinates comprises a plurality of trace point coordinates recorded in time; the track point curvature calculation is performed according to the track point coordinate set to obtain a track point curvature set, including:
sliding the coordinates of the plurality of track points according to a preset sliding time window;
after each sliding, calculating the curvature of the track points in the sliding time window to obtain the curvature of the corresponding track points;
and determining the curvature set of the track points according to the curvature of the track points corresponding to each sliding.
8. The obstacle avoidance fluency detection method of claim 7 wherein the sliding time window comprises first, second, and third track point coordinates; the calculating the curvature of the track point in the sliding time window to obtain the curvature of the corresponding track point comprises the following steps:
Calculating a first distance value between the first track point coordinate and the second track point coordinate;
calculating a second distance value between the first track point coordinate and the third track point coordinate;
calculating a third distance value between the second track point coordinate and the third track point coordinate;
and determining the curvature of the track point according to the first distance value, the second distance value and the third distance value.
9. The method for detecting obstacle avoidance smoothness according to claim 6, wherein before said calculating the path smoothness for the set of trajectory point curvatures, further comprising:
filtering out the track point curvature set which is smaller than a preset curvature threshold value, so as to obtain a filtered track point curvature set;
the calculating the path smoothness of the track point curvature set to obtain the path smoothness comprises the following steps:
and detecting the path smoothness of the filtered curvature set of the track points to obtain the path smoothness.
10. The obstacle avoidance smoothness detection method according to claim 6, wherein said performing a path smoothness calculation on the set of trajectory point curvatures to obtain the path smoothness comprises:
Determining curvature peak values, curvature average values and curvature variance corresponding to the track point curvature sets;
weighting and summing the curvature peak value, the curvature mean value and the curvature variance based on a preset weight calculation formula to obtain a target curvature;
and determining the path smoothness according to the target curvature.
11. The obstacle avoidance smoothness detection method of claim 2 wherein the number of obstacle avoidance events comprises a number of swing events and a number of pause events; the step of detecting the path smoothness and the obstacle avoidance smoothness according to the number of obstacle avoidance events to obtain the obstacle avoidance smoothness of the self-mobile device in the travelling process comprises the following steps:
and respectively carrying out normalization processing and summation on the path smoothness, the times of the head swing events and the times of the pause events to obtain the obstacle avoidance smoothness.
12. The obstacle avoidance smoothness detection device is characterized by comprising a memory, a processor, a shooting device and an inertia measurement unit;
the shooting device is used for collecting path track information;
the inertial measurement unit is used for acquiring motion parameter information;
The memory is used for storing a computer program;
the processor for executing the computer program and implementing the obstacle avoidance smoothness detection method according to any one of claims 1 to 11 when executing the computer program.
13. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program, which when executed by a processor causes the processor to implement the obstacle avoidance smoothness detection method according to any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311230868.6A CN117470227A (en) | 2023-09-21 | 2023-09-21 | Obstacle avoidance smoothness detection method, obstacle avoidance smoothness detection device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311230868.6A CN117470227A (en) | 2023-09-21 | 2023-09-21 | Obstacle avoidance smoothness detection method, obstacle avoidance smoothness detection device, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117470227A true CN117470227A (en) | 2024-01-30 |
Family
ID=89638651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311230868.6A Pending CN117470227A (en) | 2023-09-21 | 2023-09-21 | Obstacle avoidance smoothness detection method, obstacle avoidance smoothness detection device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117470227A (en) |
-
2023
- 2023-09-21 CN CN202311230868.6A patent/CN117470227A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110322500B (en) | Optimization method and device for instant positioning and map construction, medium and electronic equipment | |
| US11285613B2 (en) | Robot vision image feature extraction method and apparatus and robot using the same | |
| US10948297B2 (en) | Simultaneous location and mapping (SLAM) using dual event cameras | |
| CN107990899B (en) | Positioning method and system based on SLAM | |
| CN109671105B (en) | Tracking recovery method and device of visual navigation system | |
| EP2813082A1 (en) | Head pose tracking using a depth camera | |
| JP6820967B2 (en) | Indoor positioning systems and methods based on geomagnetic signals combined with computer vision | |
| CN112819860B (en) | Visual inertial system initialization method and device, medium and electronic equipment | |
| CN110942474B (en) | Robot target tracking method, device and storage medium | |
| CN113012224B (en) | Positioning initialization method and related device, equipment and storage medium | |
| CN110245641A (en) | A kind of target tracking image pickup method, device, electronic equipment | |
| TW201926141A (en) | Image object tracking method and apparatus | |
| KR20190001086A (en) | Sliding windows based structure-less localization method using inertial and single optical sensor, recording medium and device for performing the method | |
| Zhang et al. | NaviGlass: Indoor Localisation Using Smart Glasses. | |
| CN112991441A (en) | Camera positioning method and device, electronic equipment and storage medium | |
| CN112087728B (en) | Method and device for acquiring Wi-Fi fingerprint spatial distribution and electronic equipment | |
| CN111736190B (en) | Unmanned aerial vehicle airborne target detection system and method | |
| CN117470227A (en) | Obstacle avoidance smoothness detection method, obstacle avoidance smoothness detection device, and storage medium | |
| Jurado et al. | Inertial and imaging sensor fusion for image-aided navigation with affine distortion prediction | |
| CN114037977B (en) | Road vanishing point detection method, device, equipment and storage medium | |
| KR101870542B1 (en) | Method and apparatus of recognizing a motion | |
| CN111339226B (en) | Method and device for constructing map based on classification detection network | |
| CN114359338A (en) | Pose estimation method and device, terminal equipment and computer readable storage medium | |
| CN114593735A (en) | Pose prediction method and device | |
| Artemciukas et al. | Kalman filter for hybrid tracking technique in augmented reality |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |