WO2021235100A1

WO2021235100A1 - Information processing device, information processing method, and program

Info

Publication number: WO2021235100A1
Application number: PCT/JP2021/013352
Authority: WO
Inventors: 淳也白石
Original assignee: ソニーグループ株式会社
Priority date: 2020-05-20
Filing date: 2021-03-29
Publication date: 2021-11-25

Abstract

An information processing device according to the present invention comprises a route planning unit that plans a movement route by using a reference point on an environment map expressed by point group data. The route planning unit determines a point group nearest to the reference point on the basis of the position and the degree of dispersion of each of the point groups included in the point group data, calculates the distance between the reference point and the nearest point group on the basis of the position and degree of dispersion of the nearest point group, and plans the movement route on the basis of said distance.

Description

Information processing equipment, information processing methods, and programs

This disclosure relates to information processing devices, information processing methods, and programs.

In recent years, with the development of the robot industry, the development of autonomously movable robots such as security robots and nursing care robots has been promoted. In order to make the robot move autonomously in various environments, for example, it is considered to make the robot autonomously perform map construction and self-position estimation using SLAM (Simultaneus Localization And Mapping) or the like. (For example, Patent Document 1).

Japanese Unexamined Patent Publication No. 2012-064131

In mobile objects including such autonomous mobile robots, it is possible to create a route plan to a destination on a constructed map with a lower computational load in order to increase the moving speed or reduce power consumption. It is desired.

Therefore, it is desirable to provide an information processing device, an information processing method, and a program capable of creating a mobile route plan with higher efficiency.

The information processing apparatus according to the embodiment of the present disclosure includes a route planning unit that plans a movement route using a reference point on an environmental map represented by point cloud data, and the route planning unit is the point. The point cloud closest to the reference point is determined based on the position and the degree of dispersion of each point cloud included in the group data, and the reference point is based on the position and the degree of dispersion of the nearest point cloud. And the distance between the nearest point cloud and the point cloud are calculated, and the movement route is planned based on the distance.

The information processing method according to the embodiment of the present disclosure is based on the position and the degree of dispersion of each point cloud included in the point cloud data on an environment map represented by the point cloud data by an arithmetic processing device. Determining the nearest point cloud from the reference point, and calculating the distance between the nearest point cloud and the reference point based on the position of the nearest point cloud and the degree of dispersion. It includes planning a movement route on the environmental map based on the distance.

The program according to the embodiment of the present disclosure causes a computer to function as a route planning unit for planning a movement route using a reference point on an environment map represented by point cloud data, and causes the route planning unit to perform the above-mentioned. The point cloud closest to the reference point is determined based on the position and the degree of dispersion of each point cloud included in the point cloud data, and the recent position based on the position and the degree of dispersion of the nearest point cloud. The distance between the nearby point cloud and the reference point is calculated, and the movement route is planned based on the distance.

In the information processing apparatus, information processing method, and program according to the embodiment of the present disclosure, the nearest point cloud is located on the environment map represented by the point cloud data, based on the position and the degree of dispersion of each point cloud. Determine the point cloud to be, calculate the distance between the nearest point cloud and the reference point based on the degree of dispersion of the nearest point cloud, and plan the movement route on the environmental map based on the calculated distance. be able to. Thereby, for example, the information processing apparatus according to the present embodiment can create a route plan considering the variation of the point cloud included in the point cloud data without performing complicated calculation.

It is a schematic diagram explaining the route plan created by the information processing apparatus which concerns on one Embodiment of this disclosure. It is a block diagram which shows the functional structure of the information processing apparatus which concerns on the same embodiment. It is explanatory drawing explaining the point cloud data and the clustering of a point cloud data. It is explanatory drawing explaining the method of determining the nearest cluster from a reference point. It is a flowchart explaining the operation flow of the information processing apparatus which concerns on this embodiment. It is a block diagram which shows the functional structure of the information processing apparatus which concerns on 1st modification. It is explanatory drawing explaining the route planning method of the information processing apparatus which concerns on the 2nd modification. It is explanatory drawing explaining the route planning method of the information processing apparatus which concerns on 3rd modification. It is a block diagram which shows the functional structure of the information processing apparatus which concerns on 4th modification. It is a block diagram which shows the functional structure of the information processing apparatus which concerns on 5th modification. It is a block diagram which shows the functional structure of the information processing apparatus which concerns on 6th modification. It is a block diagram which shows the hardware configuration example of the information processing apparatus which concerns on the same embodiment.

Hereinafter, embodiments in the present disclosure will be described in detail with reference to the drawings. The embodiments described below are specific examples of the present disclosure, and the technique according to the present disclosure is not limited to the following aspects. Further, the arrangement, dimensions, dimensional ratio, etc. of each component of the present disclosure are not limited to the modes shown in the respective figures.

The explanation will be given in the following order.
1. 1. Embodiment 1.1. Overview 1.2. Configuration example 1.3. Operation example 2. Modification example 3. Hardware configuration example

<1. First Embodiment>
(1.1. Overview)
First, with reference to FIG. 1, an outline of the information processing apparatus according to the embodiment of the present disclosure will be described. FIG. 1 is a schematic diagram illustrating a route plan created by the information processing apparatus according to the present embodiment.

As shown in FIG. 1, for example, in the autonomously movable mobile body 1, a route plan for finding a route r for moving from the current position A to the destination B without colliding with the obstacle 2 is performed. As the moving body 1 that can move autonomously, a robot traveling on a two-dimensional plane, a drone flying in a three-dimensional space, or the like can be exemplified.

In such a route plan, the positions of the moving body 1 and the obstacle 2 are recognized based on the data acquired by the sensor, and an environmental map expressing the environment around the moving body 1 is constructed based on the recognition result. NS. As a result, the moving body 1 can plan the optimum route r from the current position A to the destination B on the constructed environment map, and move according to the planned optimum route r. The moving body 1 can move to the destination B without colliding with the obstacle 2 by repeatedly executing the above-mentioned route planning and movement until the moving body 1 reaches the destination B.

For example, ESDF (Euclidean Signed Distance Fields) or ESDF (Euclidean Signed Distance Fields) that expresses the environment around the moving body 1 by setting the physical distance to the obstacle 2 acquired by the distance measuring sensor or the like in each grid on the map. Technologies such as TSDF (Truncated Signed Distance Fields) are being studied. By using such a technique, the mobile body 1 can construct an environmental map expressing the surrounding environment and perform route planning based on the environmental map.

However, in reality, the data acquired by the sensor includes variations in frequency and magnitude or outliers depending on the surrounding environment and measurement conditions. Therefore, the environment map constructed based on the data acquired by the sensor and the route plan of the moving body 1 planned based on the environment map also include errors and ambiguities according to the accuracy of the sensor. It ends up.

Here, when an environmental map is constructed using some representative value (for example, a median value or an average value) without considering the above-mentioned variations and outliers, and a route plan is performed based on the environmental map. It is possible that the moving object 1 cannot safely avoid the obstacle 2. Further, in order for the moving body 1 to safely avoid the obstacle 2, the route is planned with an excessively large margin, so that the planned route may not be the optimum route. could be.

On the other hand, when an environmental map is constructed in consideration of the above variations and outliers and a route plan is performed based on the environmental map, the calculation load of the route plan may become excessively large. In particular, in a three-dimensional space, the amount of data is significantly larger than that in a two-dimensional plane, so that the computational load of constructing an environmental map and route planning becomes extremely large. In such a case, it becomes difficult to calculate the route plan at high speed, so that the moving speed of the moving body may be limited according to the calculation speed of the route plan. Further, as the calculation load increases, the power consumption of the information processing apparatus that calculates the route plan may increase.

The information processing apparatus according to the present embodiment expresses the environment map with point cloud data, and plans the movement route of the moving body 1 based on the position and the degree of dispersion of each point cloud included in the point cloud data. Specifically, the information processing apparatus sets the point cloud closest to the reference point on the map represented by the point cloud data based on the position and the degree of dispersion of each point cloud included in the point cloud data. It is possible to determine and plan the movement path of the moving body 1 based on the distance considering the degree of dispersion between the reference point and the nearest point cloud.

According to this, the information processing apparatus according to the present embodiment can reflect the error and ambiguity of the sensor in the movement path of the moving body 1 as the degree of dispersion of the point cloud included in the point cloud data. Therefore, the information processing apparatus according to the present embodiment can create a route plan of the mobile body 1 reflecting the error and ambiguity of the sensor with higher efficiency.

(1.2. Configuration example)
Subsequently, with reference to FIGS. 2 to 4, a more specific configuration of the information processing apparatus according to the present embodiment, which has been outlined above, will be described. FIG. 2 is a block diagram showing a functional configuration of the information processing apparatus 10 according to the present embodiment. FIG. 3 is an explanatory diagram illustrating the point cloud data and the clustering of the point cloud data. FIG. 4 is an explanatory diagram illustrating a method of determining the nearest cluster from the reference point.

As shown in FIG. 2, the information processing apparatus 10 according to the present embodiment includes a map construction unit 110, a route planning unit 120, and a self-position estimation unit 130.

For example, the information processing apparatus 10 constructs an environmental map around the moving body 1 based on the data acquired by the sensor unit 20, and moves to the destination of the moving body 1 using the constructed environmental map. You can plan the route. The movement path planned by the information processing apparatus 10 is output to, for example, a drive control unit 31 that controls the drive unit 32 of the mobile body 1.

Here, the sensor unit 20, the drive control unit 31, and the drive unit 32 may be provided in, for example, the moving body 1. The information processing apparatus 10 may be provided inside the moving body 1 or may be provided outside the moving body 1. When the information processing device 10 is provided inside the moving body 1, the information processing device 10 may output a route plan to the moving body 1 via the internal wiring. Further, when the information processing device 10 is provided outside the mobile body 1, the information processing device 10 may transmit a route plan to the mobile body 1 via wireless communication or the like.

The sensor unit 20 outputs the sensing result of the environment around the moving body 1 as point cloud data which is a set of points.

For example, the sensor unit 20 includes a distance measuring sensor that measures a distance to an object, such as an ultrasonic sensor (Sound Navigation And Ringing: SONAR), a ToF (Time of Flat) sensor, or a LiDAR (Light Detection And Ringing) sensor. But it may be. In such a case, the sensor unit 20 generates point cloud data by converting the measurement points into points in the three-dimensional coordinate system based on the information regarding the distance and direction to the measurement points acquired from the distance measurement sensor. be able to.

Alternatively, the sensor unit 20 may include an image pickup device that acquires an image of the surrounding environment of the moving body 1 such as a stereo camera, a monocular camera, a color camera, an infrared camera, or a polarized camera. In such a case, the sensor unit 20 estimates the depth of the image points included in the captured image based on the captured image, and converts the image points into points in the three-dimensional coordinate system based on the information regarding the estimated depth. This makes it possible to generate point cloud data.

The sensor unit 20 may be provided in an external device or object of the mobile body 1 as long as it can acquire information about the environment around the mobile body 1. For example, the sensor unit 20 may be provided on the ceiling, wall, floor, or the like of the space in which the moving body 1 is present.

The map construction unit 110 includes a clustering unit 111, a cluster extraction unit 112, and a map generation unit 113, and uses the point cloud data acquired by the sensor unit 20 to represent an environment around the moving body 1. To build.

The clustering unit 111 generates cluster data including a plurality of clusters by clustering the point cloud included in the point cloud data acquired by the sensor unit 20. Specifically, as shown in FIG. 3, the clustering unit 111 generates cluster data including a plurality of cluster CLs by clustering a point cloud PC which is a set of points P in a three-dimensional coordinate system. The cluster CL generated by clustering corresponds to one microplane constituting the surface of the object existing around the moving body 1.

For example, the clustering unit 111 may perform clustering after dividing the point cloud included in the point cloud data according to the following procedure.

First, the clustering unit 111 determines whether or not to divide the point cloud based on a predetermined division condition. When the point cloud satisfies a predetermined division condition, the clustering unit 111 divides the point cloud. Next, the clustering unit 111 repeatedly divides the divided point cloud until the above-mentioned division condition is not satisfied. Subsequently, the clustering unit 111 determines, based on a predetermined clustering condition, whether or not to perform clustering of the divided point cloud until the above-mentioned division condition is not satisfied. After that, the clustering unit 111 performs clustering on a point cloud satisfying a predetermined clustering condition.

Here, the predetermined division condition may include a condition that the number of points included in the point cloud is a predetermined number or more. In addition, the predetermined division condition is the longest side of the rectangular region when the minimum rectangular region (also called a bounding box) containing all the points of the point cloud is set in the three-dimensional coordinate system. It may include the condition that the length is equal to or longer than a predetermined length. Further, the predetermined division condition may include a condition that the density of points in the point cloud is equal to or higher than a predetermined value. The density of points in the point cloud may be, for example, a value obtained by dividing the number of points included in the point cloud by the size of the above bounding box. Further, the predetermined division condition may include a condition in which a plurality of the above-mentioned conditions are combined.

Further, the predetermined clustering condition may include a condition that the number of points included in the point cloud is a predetermined number or more. Further, the predetermined clustering condition may include a condition that the length of the longest side of the bounding box is equal to or greater than the predetermined length. Further, the predetermined clustering condition may include a condition that the density of points in the above point cloud is equal to or higher than a predetermined value. Further, the predetermined clustering condition may include a condition in which a plurality of the above-mentioned conditions are combined.

According to this, since the clustering unit 111 performs clustering for each of the point clouds after the division until the predetermined division condition is not satisfied, the size of each of the point clouds to be clustered is made smaller. be able to. Therefore, the clustering unit 111 can further shorten the clustering processing time. Further, since the clustering unit 111 can exclude a point cloud that does not satisfy a predetermined clustering condition and is likely to be inaccurate from the target of clustering, the accuracy of clustering can be further improved.

The cluster extraction unit 112 extracts parameters indicating the positions and shapes of the clusters generated by the clustering by the clustering unit 111. Specifically, the cluster extraction unit 112 extracts parameters indicating the position and shape when expressing each of the clusters as an ellipsoid which is an approximation of the second moment. For example, the cluster extraction unit 112 may calculate the average value of the coordinates of the point cloud included in the cluster in the three-dimensional coordinate system, and extract the average value of the coordinates of the point cloud as a parameter indicating the position of the cluster. Further, the cluster extraction unit 112 may calculate the covariance of the coordinates of the point cloud included in the cluster in the three-dimensional coordinate system, and extract the covariance of the coordinates of the point cloud as a parameter indicating the shape of the cluster.

The map generation unit 113 constructs an environment map expressing the environment around the mobile body 1 by using the cluster generated by the clustering by the clustering unit 111. Specifically, the map generation unit 113 is an ellipsoid in which the average value of the coordinates of the point cloud included in the cluster is the center of gravity and the covariance of the coordinates of the point cloud included in the cluster is the spread of the shape. Build an environmental map by spatially expressing. According to this, the map generation unit 113 can represent each of the clusters on the environmental map in a shape that reflects the degree of dispersion (that is, covariance) of the point cloud included in the cluster. That is, the map generation unit 113 can express a microplane group on the surface of an object existing around the moving body 1 by using each ellipsoid of the cluster generated by the clustering by the clustering unit 111.

The map generation unit 113 may group one or a plurality of clusters generated by clustering by the clustering unit 111 for each object existing in the environment map. Specifically, the map generation unit 113 recognizes which surface microplane of an object such as a person, a wall, or a floor exists around the moving object 1 in each of the clusters, and recognizes which surface microplane of the same object corresponds to. Clusters corresponding to microplanes may be grouped together.

The route planning unit 120 includes the nearest neighbor cluster determination unit 121, the distance calculation unit 122, and the route calculation unit 123, and plans the movement route of the moving body 1 on the environment map constructed by the map construction unit 110. Specifically, the route planning unit 120 sets a reference point between the current position A and the destination B of the moving body 1, and is located between the reference point and the cluster closest to the reference point. Plan the route so that the distance considering the degree of dispersion is maximized. The distance considering the degree of dispersion is, for example, the Mahalanobis distance.

The nearest neighbor cluster determination unit 121 determines the cluster closest to the reference point set between the current position A and the destination B of the mobile body 1 on the environmental map based on the degree of dispersion of the clusters. .. Specifically, the nearest neighbor cluster determination unit 121 determines the cluster that is the nearest neighbor on the environmental map with respect to the reference point based on the Mahalanobis distance.

For example, as shown in FIG. 4, the nearest neighbor cluster determination unit 121 is located between the reference point RP and each of the clusters CL1, CL2, CL3, CL4, CL5, and CL6 in the vicinity of the reference point RP on the environment map. Mahalanobis distance _{d m (x, xi ',} Σ'xi) by evaluating each from the reference point RP may be recently determined near a cluster CL5.

The distance calculation unit 122 calculates the distance based on the degree of dispersion of the cluster between the reference point RP and the nearest cluster CL5. Specifically, the distance calculation unit 122, a reference point RP, the Mahalanobis distance d _m between the nearest cluster _CL5, or Mahalanobis distance d _m functions as a variable U (x) is calculated, the Mahalanobis distance d _m or calculating the function U (x) as the value of the field at the reference point RP.

The route calculation unit 123 evaluates the field value at the reference point RP and sequentially calculates a route that secures a sufficient margin for the nearest neighbor cluster, so that the current position A of the mobile body 1 to the destination B can be calculated. Plan a travel route. Specifically, the route calculating section 123 calculates a Mahalanobis distance d _m, or Mahalanobis distance d _m functions as a variable U (x) in the reference point RP calculated in the distance calculating section 122, these Mahalanobis distances d _m or function U (x) that is sequentially calculating the comparison satisfies path between predefined threshold, to plan a travel route of the moving body 1. For example, the route calculation unit 123 may plan the movement route of the moving body 1 by calculating the Mahalanobis distance dm or the route in which the value of the function U (x) having the Mahalanobis distance dm as a variable is maximized. ..

The Mahalanobis distance d _m, as shown in Equation 1 below, a distance that reflects the covariance representing the degree of dispersion of clusters, as covariance smaller distance is large, the distance as the covariance is large is evaluated small The distance. By using the Mahalanobis distance d _m, the route calculation unit 123, in consideration of the variations set of points included in the point cloud data can be a margin of the point group to plan a sufficient path.

The self-position estimation unit 130 estimates the position of the mobile body 1 on the environment map based on the information about the environment around the mobile body 1 acquired by the sensor unit 20. Further, the self-position estimation unit 130 generates position data indicating the estimated position of the moving body 1 and outputs the position data to the route calculation unit 123.

Further, the self-position estimation unit 130 may estimate the position of the moving body 1 based on the sensing result of the sensor that measures the state of the moving body 1.

For example, the self-position estimation unit 130 calculates the moving direction and moving distance of the moving body 1 based on the sensing result of the encoder provided at each joint of the leg portion included in the moving mechanism of the moving body 1, and the moving body 1 is used. The position of 1 may be estimated. For example, the self-position estimation unit 130 calculates the moving direction and the moving distance of the moving body 1 based on the sensing result of the encoder provided on each wheel included in the moving mechanism of the moving body 1, and determines the position of the moving body 1. You may estimate. For example, the self-position estimation unit 130 has a moving direction and a moving distance of the moving body 1 based on the sensing result of an IMU (Inertial Measurement Unit) having a 3-axis gyro sensor and a 3-way accelerometer provided in the moving body 1. May be calculated to estimate the position of the moving body 1.

Further, the self-position estimation unit 130 may estimate the position of the moving body 1 based on the information acquired by another sensor such as a GNSS (Global Navigation Satellite System) sensor.

The drive control unit 31 controls the movement of the moving body 1 by controlling the drive unit 32 based on the route plan created by the route planning unit 120. For example, the drive control unit 31 may control the drive unit 32 so that the moving body 1 moves along the route planned in the route plan.

The drive unit 32 is, for example, a motor or an actuator that drives a movement mechanism included in the moving body 1. Specifically, the drive unit 32 is a motor that drives a two-wheeled or four-wheeled wheel-type moving mechanism, an actuator that drives a two-legged or four-legged moving mechanism, or a moving mechanism such as a propeller or a rotary wing. It may be a motor or the like that drives the wheel.

The information processing apparatus 10 having the above configuration determines the cluster closest to the reference point based on the Mahalanobis distance in the environment map represented by the point cloud data, and the Mahalanobis between the reference point and the nearest cluster. The movement route of the moving body 1 can be planned so that a sufficient distance is secured. Therefore, the information processing apparatus 10 can plan a movement path reflecting the variation of the point cloud included in the point cloud data with high efficiency without performing additional complicated calculation.

In the above embodiment, the Mahalanobis distance is exemplified as the distance in consideration of the degree of dispersion, but the technique according to the present disclosure is not limited to the above example. The distance considering the degree of dispersion may be, for example, a distance calculated with the Mahalanobis distance as a variable. Further, the distance considering the degree of dispersion may be any distance as long as it is a distance defined with the variation of the point cloud (for example, the covariance of the coordinates of each point included in the point cloud) as a variable.

(1.3. Operation example)
Next, an example of the operation of the information processing apparatus 10 according to the present embodiment will be described with reference to FIG. FIG. 5 is a flowchart illustrating an operation flow of the information processing apparatus 10 according to the present embodiment.

As shown in FIG. 5, first, the map construction unit 110 acquires point cloud data from the sensor unit 20 (S101). Subsequently, the clustering unit 111 clusters the point cloud included in the point cloud data (S102). Next, the cluster extraction unit 112 extracts the position and shape of each cluster by calculating the average value and covariance of the coordinates of the point cloud included in each clustered cluster (S103). After that, the map generation unit 113 constructs an environment map in which each cluster is represented by an ellipsoid of the extracted position and shape (S104). As a result, the map construction unit 110 can construct an environment map that expresses the environment around the moving body 1.

Subsequently, the route planning unit 120 sets a reference point on the constructed environment map (S111). Next, the nearest neighbor cluster determination unit 121 determines the nearest neighbor cluster from the reference point by calculating the Mahalanobis distance between each cluster on the environment map and the reference point (S112). Subsequently, the distance calculation unit 122 calculates a Mahalanobis distance between the reference point and the nearest cluster, or a function using the Mahalanobis distance as a variable, and calculates the field value at the reference point (S113). Further, the route calculation unit 123 creates a route plan so that the value of the field based on the Mahalanobis distance between the reference point and the nearest cluster satisfies the comparison condition with the predetermined threshold value (S114). After that, the drive control unit 31 controls the drive of the drive unit 32 so that the moving body 1 moves along the route based on the created route plan (S115).

The route planning unit 120 sequentially and repeatedly calculates a route such that the Mahalanobis distance between the reference point and the nearest cluster satisfies the comparison condition with the predetermined threshold value until the moving body 1 reaches the destination. , The moving body 1 can be moved to the destination by a safe route.

According to the above operation example, the information processing apparatus 10 according to the present embodiment clusters the point cloud data obtained by sensing the objects existing around the moving body 1, and determines the distance based on the position and the degree of dispersion of each cluster. Can be used to create a route plan. According to this, the information processing apparatus 10 according to the present embodiment can create a route plan in consideration of the sensing variation of the point cloud data and the like with high efficiency.

<2. Modification example>
Hereinafter, the first to sixth modifications of the information processing apparatus 10 according to the present embodiment will be described with reference to FIGS. 6 to 11.

(First modification)
The information processing apparatus according to the first modification will be described with reference to FIG. FIG. 6 is a block diagram showing a functional configuration of the information processing apparatus 11 according to the first modification.

As shown in FIG. 6, the information processing apparatus 11 according to the first modification further includes a database construction unit 140. Since the other configurations are substantially the same as those of the information processing apparatus 10 described with reference to FIG. 2, the description thereof is omitted here.

The database construction unit 140 constructs a search database that is referred to when the nearest neighbor cluster determination unit 121 determines the nearest neighbor cluster from the reference point. The search database is a database having a tree-shaped spatially divided data structure for classifying points existing in a predetermined space such as a kd tree, a quadtree, or an ocree. The database construction unit 140 may construct a search database by, for example, classifying the positions of each cluster existing in the three-dimensional coordinate system according to the spatial division data structure as described above.

According to this, the nearest cluster determination unit 121 can more efficiently determine the cluster closest to the reference point by searching the spatially divided data structure of the search database. Therefore, the information processing apparatus 11 according to the first modification can plan the movement route more efficiently.

(Second modification)
The information processing apparatus according to the second modification will be described with reference to FIG. 7. FIG. 7 is an explanatory diagram illustrating a route planning method of the information processing apparatus according to the second modification.

The route calculation unit 123 may define the potential field PF as shown in FIG. 7 and plan a route along the differential gradient of the potential field PF as the movement route of the moving body 1. Specifically, the path calculation unit 123 defines the potential field PF represented by the following mathematical formula 2 on the environment map, and calculates the differential gradient at each point of the potential field PF to move the moving body 1. You may plan a route.

As shown in Equations 3 and 4, V _m is a potential based on the Mahalanobis distance between the reference point and the nearest cluster. As shown in Equation 5, V _w is a potential based on the Euclidean distance between the current position A and the destination B. Further, α and β are weighting variables. Therefore, the potential field PF is, for example, a field in which the repulsive force from the nearest cluster corresponding to the object existing in the environment around the moving body 1 and the attractive force to the destination B are weighted and superimposed.

According to this, the path calculation unit 123 can plan a movement path according to the differential gradient by sequentially calculating the differential gradient of the potential field PF at the current position A of the moving body 1. Since the calculation of the differential gradient of the potential field PF can be executed at high speed with a small amount of calculation, the information processing apparatus 10 according to the second modification can plan the movement path more efficiently. Is.

(Third modification example)
The information processing apparatus according to the third modification will be described with reference to FIG. FIG. 8 is an explanatory diagram illustrating a route planning method of the information processing apparatus according to the third modification.

The route calculation unit 123 may create a topological map obtained by dividing the environmental map TM as shown in FIG. 8 by Voronoi, and plan the movement route of the moving body 1 based on the topological map.

Specifically, the route calculation unit 123 first divides the environment map TM into a plurality of areas (Voronoi division) depending on which of the objects Ob is closest to the Mahalanobis distance. That is, the Voronoi division line BB that divides the environment map TM into a plurality of regions is provided so as to be equidistant from each of the clusters on the surface of the objects Ob facing each other at the Mahalanobis distance. Next, the route calculation unit 123 provides a plurality of nodes nd on the Voronoi partition line BB, and expresses the connection relationship between the nodes nd as a topological map.

According to this, the route calculation unit 123 can calculate the plan of the movement route of the moving body 1 on the environment map TM as the connection plan between the nodes nd on the topological map. In such a case, the mobile body 1 moves on the Voronoi partition line BB of the environment map TM based on the connection between the nodes nd planned in the topological map. Therefore, since the information processing apparatus 10 according to the third modification can perform route planning in consideration of the variation of the point cloud included in the point cloud data, it is possible to plan a movement route with higher robustness. can.

(Fourth modification)
The information processing apparatus according to the fourth modification will be described with reference to FIG. 9. FIG. 9 is a block diagram showing a functional configuration of the information processing apparatus 14 according to the fourth modification.

As shown in FIG. 9, the information processing apparatus 14 according to the fourth modification includes N first sensor units 20-1 to Nth sensor units 20-N. Since the other configurations are substantially the same as those of the information processing apparatus 10 described with reference to FIG. 2, the description thereof is omitted here.

The first sensor unit 20-1 to the Nth sensor unit 20-N include sensors of the same type or different types, and output the sensing result of the environment around the moving body 1 as point cloud data. For example, the first sensor unit 20-1 to the Nth sensor unit 20-N may include a distance measuring sensor such as a stereo camera, an ultrasonic sensor, a ToF sensor, or a LiDAR sensor, and may include a monocular camera, a color camera, and an infrared camera. , Or an image pickup device such as a polarized camera may be included.

The point cloud data acquired by the plurality of first sensor units 20-1 to Nth sensor unit 20-N are individually clustered by the clustering unit 111, and individually by the cluster extraction unit 112 of each cluster. The position and shape are extracted. After that, the point cloud data acquired by the plurality of first sensor units 20-1 to Nth sensor unit 20-N are integrated by the map generation unit 113 and used to generate the environment map around the moving body 1. Will be.

The information processing apparatus 14 determines the degree of dispersion of the point cloud of the ellipsoid of the cluster even when the variation of the point cloud data acquired by each of the plurality of first sensor units 20-1 to Nth sensor unit 20-N is different. It can be reflected in the environmental map as a shape. Therefore, the information processing apparatus 14 can be used to generate an environmental map by the same processing even if the point cloud data has different variations, and it is possible to create a route plan using the environmental map. Is.

(Fifth variant)
The information processing apparatus according to the fifth modification will be described with reference to FIG. 10. FIG. 10 is a block diagram showing a functional configuration of the information processing apparatus 15 according to the fifth modification.

As shown in FIG. 10, the information processing apparatus 15 according to the fifth modification includes a variation estimation unit 114 in place of the clustering unit 111 and the cluster extraction unit 112, and determines the nearest neighbor point in place of the nearest neighbor cluster determination unit 121. A unit 124 is provided. Since the other configurations are substantially the same as those of the information processing apparatus 10 described with reference to FIG. 2, the description thereof is omitted here.

The information processing device 15 according to the fifth modification is a modification in which the variation of the point cloud is estimated by using another method instead of the clustering of the point cloud.

For example, depending on the type of sensor included in the sensor unit 20, it may be possible to construct a variation model of measurement results from the principle of sensing or the like. In such a case, the variation estimation unit 114 may estimate the variation of each point included in the point cloud data based on the variation model of the sensor unit 20 that acquires the point cloud data.

According to this, even if the number of point clouds included in the point cloud data acquired by the sensor unit 20 is small and clustering becomes difficult, by constructing an appropriate variation model, the map generation unit 113 can be similarly used. It becomes possible to construct an environmental map.

Further, depending on the type of sensor included in the sensor unit 20, it may be possible to calculate the reliability of the measurement result. In such a case, the variation estimation unit 114 may estimate the variation of each point included in the point cloud data based on the reliability of the measurement result provided by the sensor unit 20 that acquires the point cloud data.

For example, in a stereo camera, it is determined by score calculation that the objects captured by the left and right cameras are the same. Therefore, when the sensor that acquires the point cloud data is a stereo camera, the score for evaluating that the objects captured by the left and right cameras are the same can be used as the reliability of the measurement result. Further, for example, in the ToF sensor, the certainty of the measurement result can be evaluated by the intensity of the reflected light from the object. Therefore, when the sensor that acquires the point cloud data is a ToF sensor, the intensity of the reflected light can be used as the reliability of the measurement result.

According to this, even if the number of point clouds included in the point cloud data acquired by the sensor unit 20 is small and clustering becomes difficult, the information processing apparatus 15 similarly uses the map generation unit 113 to map the environment. Can be constructed. Further, the information processing apparatus 15 can estimate the variation with relatively high accuracy by estimating the variation of each point included in the point cloud data based on the state of sensing by the sensor unit 20.

Therefore, in the information processing apparatus 15 according to the fifth modification, the map generation unit 113 determines the coordinates and variations of each point included in the point group data, similarly to the information processing apparatus 10 described with reference to FIG. Based on this, an environmental map can be constructed. That is, the map generation unit 113 can express the surface of the object existing around the moving body 1 by expressing each point included in the point cloud data as a sphere having a size corresponding to the variation.

In such a case, in the route planning unit 120, the nearest neighbor cluster determination unit 121 does not determine the cluster that is the closest to the reference point on the environment map, but the nearest neighbor point determination unit 124 determines the reference point. On the other hand, the nearest point on the environmental map will be determined. Therefore, the nearest neighbor point determination unit 124 can determine the point closest to the reference point on the environmental map based on the Mahalanobis distance, similarly to the nearest neighbor cluster determination unit 121.

Therefore, the information processing apparatus 15 according to the fifth modification builds an environmental map in the map generation unit 113 in the same manner even when the number of point clouds included in the point cloud data acquired by the sensor unit 20 is small. It is possible to do.

(Sixth modification)
The information processing apparatus according to the sixth modification will be described with reference to FIG. FIG. 11 is a block diagram showing a functional configuration of the information processing apparatus 16 according to the sixth modification.

As shown in FIG. 11, the information processing apparatus 16 according to the sixth modification further includes an uncertainty extraction unit 150. Since the other configurations are substantially the same as those of the information processing apparatus 10 described with reference to FIG. 2, the description thereof is omitted here.

The uncertainty extraction unit 150 extracts the uncertainty of the self-position of the moving body 1 estimated by the self-position estimation unit 130. Specifically, the uncertainty extraction unit 150 may extract the uncertainty of the self-position of the moving body 1 as the covariance of the coordinates of the self-position. Since the Mahalanobis distance is a distance index considering the covariance, it is possible to easily incorporate the uncertainty or variation of other factors as the covariance. For example, the map generation unit 113 further adds the covariance of the coordinates of the self-position of the moving body 1 to the covariance of the coordinates of the point cloud included in each cluster to increase the uncertainty of the self-position of the moving body 1. It may be reflected in the environmental map.

According to this, the information processing apparatus 16 according to the sixth modification can reflect the uncertainty of the self-position of the moving body 1 on the environmental map, so that it is possible to plan a safer moving route. be.

<3. Hardware configuration example>
Further, with reference to FIG. 12, the hardware configuration of the information processing apparatus 10 according to the present embodiment will be described. FIG. 12 is a block diagram showing a hardware configuration example of the information processing apparatus 10 according to the present embodiment.

The function of the information processing apparatus 10 according to the present embodiment is realized by the cooperation between the software and the hardware described below. For example, the functions of the

map construction unit

110, 110A, the

route planning unit

120, 120A, the self-position estimation unit 130, the database construction unit 140, and the uncertainty extraction unit 150 described above may be executed by the CPU 901.

As shown in FIG. 12, the information processing device 10 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 903, and a RAM (Random Access Memory) 905.

Further, the information processing device 10 may further include a host bus 907, a bridge 909, an external bus 911, an interface 913, an input device 915, an output device 917, a storage device 919, a drive 921, a connection port 923, and a communication device 925. .. Further, the information processing apparatus 10 may have another processing circuit such as a DSP (Digital Signal Processor) or an ASIC (Application Specific Integrated Circuit) in place of the CPU 901 or together with the CPU 901.

The CPU 901 functions as an arithmetic processing device or a control device, and controls the overall operation of the information processing device 10 according to various programs recorded in the ROM 903, the RAM 905, the storage device 919, or the removable recording medium 927. The ROM 903 stores programs used by the CPU 901, calculation parameters, and the like. The RAM 905 temporarily stores a program used in the execution of the CPU 901, a parameter used in the execution, and the like.

The CPU 901, ROM 903, and RAM 905 are connected to each other by a host bus 907 composed of an internal bus such as a CPU bus. Further, the host bus 907 is connected to an external bus 911 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 909.

The input device 915 is a device that receives input from a user such as a mouse, a keyboard, a touch panel, a button, a switch, or a lever. The input device 915 may be a microphone or the like that detects a user's voice. Further, the input device 915 may be, for example, a remote control device using infrared rays or other radio waves, or an externally connected device 929 corresponding to the operation of the information processing device 10.

The input device 915 further includes an input control circuit that outputs an input signal generated based on the information input by the user to the CPU 901. By operating the input device 915, the user can input various data to the information processing device 10 or instruct the processing operation.

The output device 917 is a device capable of visually or audibly presenting the information acquired or generated by the information processing device 10 to the user. The output device 917 may be, for example, a display device such as an LCD (Liquid Crystal Display), a PDP (Plasma Display Panel), an OLED (Organic Light Emitting Display) display, a hologram, or a projector. Further, the output device 917 may be a sound output device such as a speaker or headphones, or may be a printing device such as a printer device. The output device 917 may output the information obtained by the processing of the information processing device 10 as a video such as a text or an image, or a sound such as voice or sound.

The storage device 919 is a data storage device configured as an example of the storage unit of the information processing device 10. The storage device 919 may be configured by, for example, a magnetic storage device such as an HDD (Hard Disk Drive), a semiconductor storage device, an optical storage device, an optical magnetic storage device, or the like. The storage device 919 can store a program executed by the CPU 901, various data, various data acquired from the outside, and the like.

The drive 921 is a read or write device for a removable recording medium 927 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and is built in or externally attached to the information processing device 10. For example, the drive 921 can read the information recorded in the attached removable recording medium 927 and output it to the RAM 905. Further, the drive 921 can write a record on the removable recording medium 927 mounted on the drive 921.

The connection port 923 is a port for directly connecting the external connection device 929 to the information processing device 10. The connection port 923 may be, for example, a USB (Universal Serial Bus) port, an IEEE1394 port, a SCSI (Small Computer System Interface) port, or the like. Further, the connection port 923 may be an RS-232C port, an optical audio terminal, an HDMI (registered trademark) (High-Definition Multidimedia Interface) port, or the like. By connecting the connection port 923 to the externally connected device 929, various data can be transmitted and received between the information processing device 10 and the externally connected device 929.

The communication device 925 is, for example, a communication interface composed of a communication device for connecting to the communication network 931. The communication device 925 may be, for example, a communication card for a wired or wireless LAN (Local Area Network), Bluetooth (registered trademark), WUSB (Wireless USB), or the like. Further, the communication device 925 may be a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), a modem for various communications, or the like.

The communication device 925 can send and receive signals and the like to and from the Internet or other communication devices using a predetermined protocol such as TCP / IP. The communication network 931 connected to the communication device 925 is a network connected by wire or wirelessly, and is, for example, an Internet communication network, a home LAN, an infrared communication network, a radio wave communication network, a satellite communication network, or the like. May be good.

It is also possible to create a program for making hardware such as the CPU 901, ROM 903, and RAM 905 built in the computer exhibit the same functions as the above information processing device 10. It is also possible to provide a recording medium that can be read by a computer that records the program.

The techniques related to the present disclosure have been described above with reference to embodiments and modifications. However, the technique according to the present disclosure is not limited to the above-described embodiment and the like, and various modifications can be made. For example, the technique according to the present disclosure can be applied not only to a route plan in an environmental map of a three-dimensional space but also to a route plan in an environmental map of a two-dimensional plane.

Furthermore, not all of the configurations and operations described in each embodiment are essential as the configurations and operations of the present disclosure. For example, among the components in each embodiment, the components not described in the independent claims indicating the top-level concept of the present disclosure should be understood as arbitrary components.

The terms used throughout this specification and the appended claims should be construed as "non-limiting" terms. For example, the term "contains" or "contains" should be construed as "not limited to the mode described as being included." The term "have" should be construed as "not limited to the mode described as having".

The terms used herein include terms that are used solely for convenience of explanation and are not used for the purpose of limiting configuration and operation. For example, terms such as "right," "left," "top," and "bottom" only indicate the direction on the referenced drawing. Further, the terms "inside" and "outside" merely indicate the direction toward the center of the attention element and the direction away from the center of the attention element, respectively. The same applies to terms similar to these and terms having a similar purpose.

The technology according to the present disclosure may have the following configuration. According to the technique according to the present disclosure having the following configuration, the movement of a moving object on the environmental map based on the distance reflecting the degree of dispersion of the point cloud on the environmental map represented by the point cloud data. The route will be planned. Therefore, according to the technique according to the present disclosure, it is possible to create a safe route plan for a moving object with higher efficiency. The effects exerted by the techniques according to the present disclosure are not necessarily limited to the effects described herein, and may be any of the effects described in the present disclosure.
(1)
It is equipped with a route planning unit that plans a movement route using reference points on an environmental map represented by point cloud data.
The route planning unit determines a point cloud closest to the reference point based on the position and degree of dispersion of each point cloud included in the point cloud data, and the position of the nearest point cloud and the said An information processing device that calculates the distance between the reference point and the nearest point cloud based on the degree of dispersion, and plans the movement path based on the distance.
(2)
The information processing apparatus according to (1) above, wherein the point cloud data is data obtained by further clustering the point clouds acquired by the sensor.
(3)
The above (2), wherein the route planning unit determines the cluster closest to the reference point based on the average value and covariance of the point cloud included in each of the clusters generated by the clustering. Information processing device.
(4)
The information processing apparatus according to (1) above, wherein the degree of dispersion is calculated based on a model of measurement variation of a sensor that has acquired the point cloud data.
(5)
The information processing apparatus according to (1) above, wherein the degree of dispersion is calculated based on the reliability of the point cloud data provided by the sensor that acquired the point cloud data.
(6)
The information processing according to any one of (1) to (5) above, wherein the degree of dispersion is further calculated based on the uncertainty of the self-position of the moving body moving based on the planned movement path. Device.
(7)
The information processing apparatus according to any one of (1) to (6) above, wherein the distance calculated by the route planning unit is a distance based on the Mahalanobis distance.
(8)
The information according to (7) above, wherein the route planning unit plans the movement route so that the Mahalanobis distance between the reference point and the nearest point cloud satisfies a comparison condition with a predetermined threshold value. Processing equipment.
(9)
The information processing apparatus according to (8) above, wherein the route planning unit plans the movement route so that the Mahalanobis distance between the reference point and the nearest point cloud is maximized.
(10)
The route planning unit plans the travel route using a potential field based on the distance to the destination in the travel route and the Mahalanobis distance between the reference point and the nearest point cloud (7). The information processing apparatus according to any one of (9).
(11)
The route planning unit generates a topological map obtained by dividing the environmental map into Voronoi diagrams based on the Mahalanobis distance, and plans the movement route based on the topological map, any one of the above (7) to (9). The information processing device described in the section.
(12)
Further provided with a database construction unit for constructing a map database showing the interrelationship of each of the point clouds included in the point cloud data.
The information processing apparatus according to any one of (1) to (11) above, wherein the route planning unit determines a point cloud in the nearest neighbor using the map database.
(13)
The information processing apparatus according to any one of (1) to (12) above, wherein the point cloud data includes point cloud data acquired by two or more sensors.
(14)
The information processing apparatus according to (13) above, wherein the two or more sensors include sensors of different types or the same type.
(15)
The information processing apparatus according to any one of (1) to (14) above, wherein the environment map is a map of a three-dimensional space.
(16)
Depending on the arithmetic processing unit
On the environment map represented by the point cloud data, the point cloud closest to the reference point is determined based on the position and the degree of dispersion of each point cloud included in the point cloud data.
To calculate the distance between the nearest point cloud and the reference point based on the position of the nearest point cloud and the degree of dispersion.
An information processing method comprising planning a travel route on the environmental map based on the distance.
(17)
Computer,
It functions as a route planning unit that plans a movement route using reference points on an environmental map represented by point cloud data.
The route planning unit is made to determine the point cloud closest to the reference point based on the position and the degree of dispersion of each point cloud included in the point cloud data, and the position of the nearest point cloud and the said A program that calculates the distance between the nearest point cloud and the reference point based on the degree of dispersion, and plans the movement route based on the distance.

This application claims priority on the basis of Japanese Patent Application No. 2020-08487 filed on May 20, 2020 at the Japan Patent Office, and this application is made by reference to all the contents of this application. Invite to.

Those skilled in the art may conceive various modifications, combinations, sub-combinations, and changes, depending on design requirements and other factors, which are included in the claims and their equivalents. It is understood that it is a person skilled in the art.

Claims

It is equipped with a route planning unit that plans a movement route using reference points on an environmental map represented by point cloud data.
The route planning unit determines a point cloud closest to the reference point based on the position and degree of dispersion of each point cloud included in the point cloud data, and the position of the nearest point cloud and the said An information processing device that calculates the distance between the reference point and the nearest point cloud based on the degree of dispersion, and plans the movement path based on the distance.
The information processing device according to claim 1, wherein the point cloud data is data obtained by further clustering the point clouds acquired by the sensor.
The information according to claim 2, wherein the route planning unit determines the cluster closest to the reference point based on the average value and covariance of the point cloud included in each of the clusters generated by the clustering. Processing equipment.
The information processing device according to claim 1, wherein the degree of dispersion is calculated based on a model of measurement variation of a sensor that has acquired the point cloud data.
The information processing apparatus according to claim 1, wherein the degree of dispersion is calculated based on the reliability of the point cloud data provided by the sensor that acquired the point cloud data.
The information processing apparatus according to claim 1, wherein the degree of dispersion is further calculated based on the uncertainty of the self-position of the moving body that moves based on the planned movement path.
The information processing device according to claim 1, wherein the distance calculated by the route planning unit is a distance based on the Mahalanobis distance.
The information processing according to claim 7, wherein the route planning unit plans the movement route so that the Mahalanobis distance between the reference point and the nearest point cloud satisfies a comparison condition with a predetermined threshold value. Device.
The information processing apparatus according to claim 8, wherein the route planning unit plans the movement route so that the Mahalanobis distance between the reference point and the nearest point cloud is maximized.
The route planning unit plans the travel route using a potential field based on the distance to the destination in the travel route and the Mahalanobis distance between the reference point and the nearest point cloud, according to claim 7. The information processing device described.
The information processing device according to claim 7, wherein the route planning unit generates a topological map obtained by dividing the environmental map into Voronoi diagrams based on the Mahalanobis distance, and plans the movement route based on the topological map.
Further provided with a database construction unit for constructing a map database showing the interrelationship of each of the point clouds included in the point cloud data.
The information processing device according to claim 1, wherein the route planning unit determines the nearest point cloud using the map database.
The information processing device according to claim 1, wherein the point cloud data includes point cloud data acquired by two or more sensors.
The information processing device according to claim 13, wherein the two or more sensors include sensors of different types or the same type.
The information processing device according to claim 1, wherein the environmental map is a map of a three-dimensional space.
Depending on the arithmetic processing unit
On the environment map represented by the point cloud data, the point cloud closest to the reference point is determined based on the position and the degree of dispersion of each point cloud included in the point cloud data.
To calculate the distance between the nearest point cloud and the reference point based on the position of the nearest point cloud and the degree of dispersion.
An information processing method comprising planning a travel route on the environmental map based on the distance.
Computer,
It functions as a route planning unit that plans a movement route using reference points on an environmental map represented by point cloud data.
The route planning unit is made to determine the point cloud closest to the reference point based on the position and the degree of dispersion of each point cloud included in the point cloud data, and the position of the nearest point cloud and the said A program that calculates the distance between the nearest point cloud and the reference point based on the degree of dispersion, and plans the movement route based on the distance.