JP2022012540A - Information processing device, information processing method, and program - Google Patents

Abstract

To provide an information processing device, an information processing method, and a program that can form a highly accurate map with a small amount of a calculation.SOLUTION: In order to achieve the above object, an information processing device according to one embodiment of the present technology comprises a generation unit. The generation unit generates one or more regions with boundary representation for estimating an obstacle based on occupancy rate information with respect to a map which contains the occupancy rate information for indicating a probability of the obstacle being present at each location, generated from a detection result from a sensor. This makes it possible to form a highly accurate map with a small amount of calculation. In addition, it will be possible to realize self-position estimation and SLAM that are resistant to disturbance.SELECTED DRAWING: Figure 2

Description

The present technology relates to an information processing device, an information processing method, and a program applicable to control of autonomous movement and the like.

In the moving body control device described in Patent Document 1, distance point data for obstacles around the moving body are acquired. Based on the distance point data, a polygon map showing the outline of the obstacle is generated. If it is determined that the movement route calculated on the grid-like grid map showing the movement environment of the moving object cannot pass based on the generated polygon map, the movement route is corrected. Thereby, the optimum movement route is set (paragraph [0015] [0029] FIG. 3 of Patent Document 1 and the like).

Japanese Unexamined Patent Publication No. 2014-123200

When a map is generated with a grid-like data structure as in Patent Document 1, there is a problem that the amount of calculation becomes enormous when the grid width is made finer in order to improve the accuracy of self-position estimation. As described above, there is a demand for a technology that enables highly accurate map creation with a small amount of calculation.

In view of the above circumstances, an object of the present technology is to provide an information processing device, an information processing method, and a program capable of creating a highly accurate map with a small amount of calculation.

In order to achieve the above object, the information processing apparatus according to one embodiment of the present technology includes a generation unit.
The generation unit creates the obstacle based on the occupancy rate information on a map including occupancy rate information indicating the probability of presence or absence of an obstacle at each position generated by the detection result from the sensor. Generate one or more regions with boundary representation for estimation.

In this information processing device, a map including occupancy rate information indicating the probability of presence of an obstacle at each position generated by the detection result from the sensor is expressed by boundary representation according to the occupancy rate information. The above area is generated. This makes it possible to create a highly accurate map with a small amount of calculation.

The generation unit may generate the one or more regions based on the occupancy rate information expressed as the rotation speed.

The one or more regions may be a plurality of regions. In this case, the generation unit may change the occupancy rate information based on the distance between the plurality of regions.

The generation unit may change the occupancy rate information based on the distance between a predetermined point in the one or more regions and a boundary constituting the one or more regions.

The generation unit may superimpose the one or more regions based on the occupancy rate information.

The sensor may include a ranging sensor. In this case, the generation unit may generate each of the one or more regions based on the distance information from the distance measuring sensor.

The generation unit may determine the boundaries constituting the one or more regions based on the distance information.

The sensor may be mounted on a moving body. In this case, the information processing apparatus may further include an estimation unit that estimates the position of the moving body.

The sensor may be mounted on a moving body. In this case, the information processing apparatus may further include a determination unit for determining whether or not the amount of calculation required for estimating the position of the moving body exceeds a predetermined threshold value.

The generation unit may control one or more regions based on the boundary representation based on the determination result of the determination unit.

The generation unit may delete the region represented by the boundary representation based on the determination result of the determination unit and the position of the moving body.

The generation unit may delete the region represented by the boundary representation based on the determination result of the determination unit and the path of the moving body.

The information processing apparatus may further include a route generation unit that generates a route for a moving body having the sensor based on a map in which one or more regions are generated.

The sensor may include LiDAR (Light Detection and Ranging).

The information processing method according to one form of the present technology is an information processing method executed by a computer system, and is an occupancy rate that indicates the probability of whether or not an obstacle exists at each position generated by the detection result from the sensor. For a map containing information, it includes generating one or more regions by boundary representation for estimating the obstacle based on the occupancy information.

A program according to an embodiment of the present technology causes a computer system to perform the following steps.
Boundary point for estimating the obstacle based on the occupancy information for the map including the occupancy rate information indicating the probability of the presence or absence of the obstacle at each position generated by the detection result from the sensor. A step to generate one or more regions by representation.

It is a schematic diagram for demonstrating the outline of the map generation system which concerns on this technology. It is a block diagram which shows the functional configuration example of a map generation system. It is a flowchart which shows an example of the control of self-position estimation of a moving body. It is a flowchart which shows an example of map area generation. It is a schematic diagram which shows the example of the rotation area. It is a schematic diagram which shows another example of a rotation region. It is a schematic diagram which shows another example of a rotation region. It is a block diagram which shows the hardware configuration example of an information processing apparatus.

Hereinafter, embodiments of the present technology will be described with reference to the drawings.

FIG. 1 is a schematic diagram for explaining an outline of a map generation system according to the present technology.
As shown in FIG. 1, the map generation system 100 includes a mobile body 10 and an information processing device 20. The mobile body 10 and the information processing device 20 are communicably connected via a wire or a radio. The connection form between each device is not limited, and for example, wireless LAN communication such as WiFi and short-range wireless communication such as Bluetooth (registered trademark) can be used.

The mobile body 10 is a robot capable of autonomous movement. For example, the moving body 10 may be a drone capable of flying, a wheel-type robot, a multi-legged walking type robot, and a robot having legs having an articulated structure.
In the present embodiment, the moving body 10 has a sensor unit capable of observing the surroundings of the moving body 10. For example, LiDAR (Light Detection and Ranging, Laser Imaging Detection and Ranging) is used for the sensor unit. In addition to this, an image pickup device such as a stereo camera, a digital camera, and a monocular camera, a sensor device such as a laser ranging sensor, a contact sensor, an ultrasonic sensor, and a sonar may be used.
Further, in the present embodiment, the mobile body 10 outputs the detection result from the sensor unit to the information processing device 20. For example, the position of the obstacle 1 existing around the moving body 10, the shape of the obstacle 1, and the type of the obstacle 1 such as an animal body are transmitted to the information processing apparatus 20.

The information processing apparatus 20 generates an area with one or more boundary representations according to the occupancy rate information for the map including the occupancy rate information generated by the data acquired from the sensor unit. For example, the boundary of the region (the line segment constituting the region) is generated based on the distance information acquired from LiDAR or the like.
The occupancy rate information is information indicating the probability of whether or not the obstacle 1 exists at each position. In the present embodiment, the information processing apparatus 20 generates occupancy rate information based on the detection result from the sensor unit.
The boundary representation is an expression indicating whether or not an obstacle 1 exists in a predetermined area in the map. In the present embodiment, for example, the occupancy rate information is expressed as a region where the obstacle 1 is unlikely to exist inside the region and a region where the obstacle 1 is likely to exist outside the region.

Further, in the present embodiment, the occupancy rate information is expressed by the number of rotations as the boundary representation.
The rotation speed is an integer representing the total number of rotations counterclockwise with respect to the region. For example, with the point at infinity outside the region, the rotation speed of the clockwise region 2 is -1, and the rotation speed of the counterclockwise region 3 is +1. Here, the area at the point at infinity (rotational speed 0) outside the area is treated as an unknown area. That is, it is an area where it is unknown whether or not an obstacle exists.

As shown in FIG. 1, it is shown that there is a high possibility that an obstacle exists on the left side and the right side with respect to the traveling direction (arrow direction) of each line segment constituting the region.
That is, the clockwise (negative rotation speed) region is a region where there is a high possibility that no obstacle exists. Further, the counterclockwise region (the rotation speed is positive) is a region where an obstacle is likely to exist.
Further, as shown in FIG. 1, a part or all of the area represented by the boundary representation (hereinafter referred to as a rotation area) is superimposed. For example, when the counterclockwise rotation region is superimposed in the counterclockwise rotation region (rotation speed + 1 region), the rotation speed of the rotation region becomes +2. Further, for example, when the counterclockwise rotation region is superimposed in the clockwise rotation region (region of rotation speed -1), the rotation speed of the rotation region becomes 0.

Further, the information processing apparatus 20 outputs a map (hereinafter referred to as an area map) in which a rotation area is generated. In the present embodiment, the output area map is output to the moving body 10 and used for route generation in the autonomous movement of the moving body 10. For example, the path of the moving body 10 may be generated by a cost function such as reducing the cost of a portion having a large rotation speed in the rotation region.
Further, the information processing apparatus 20 may present the area map to the user. For example, the area map may be presented to a PC, a smartphone, or the like for controlling the mobile body 10 owned by the user.
The map includes map information prepared in advance and map information of the surroundings generated by the moving body 10 such as SLAM (Simultaneous Localization and Mapping).

FIG. 2 is a block diagram showing a functional configuration example of the map generation system 100.
As shown in FIG. 2, the map generation system 100 includes a mobile body 10 and an information processing device 20.

The mobile body 10 has a drive system control unit 11, an external information detection unit 12, a state detection unit 13, a sensor unit 14, and a map acquisition unit 15.

The drive system control unit 11 generates various control signals of the moving body 10 and controls various devices related to the driving system of the moving body.
For example, the moving body 10 includes a servomotor that can specify the angle and torque provided in each joint of the four legs, a motion controller that decomposes and replaces the movement of the robot itself into the movements of the four legs, and each of them. It is equipped with a feedback control device using a sensor inside the motor and a sensor on the back of the foot.
Further, for example, the moving body 10 includes a motor having four or six propellers upward, and a motion controller that decomposes and replaces the moving movement of the robot itself into the rotation amount of each motor.
Further, for example, the moving body 10 includes a driving force generating device for generating a driving force of an internal combustion engine or a driving motor, a driving force transmitting mechanism for transmitting the driving force to the wheels, a steering mechanism for adjusting the steering angle, and the like. A braking device that generates a braking force, an ABS (Antilock Brake System), an ESC (Electronic Stability Control), an electric power steering device, and the like may be provided.

The external information detection unit 12 performs detection processing of external information of the moving body 10 based on the detection result from the sensor unit 14.
For example, the external information detection unit 12 performs detection processing, recognition processing, and tracking processing of obstacles around the moving body 10, and detection processing of the distance to the obstacle.
Further, for example, the external information detection unit 12 performs detection processing of the environment around the moving body 10. The surrounding environment to be detected includes, for example, weather, temperature, humidity, brightness, road surface condition, and the like.
In the present embodiment, the external information detection unit 12 supplies data indicating the result of the detection process to the information acquisition unit 21.

The state detection unit 13 detects the state of the moving body 10 based on the data or signal from the drive system control unit 11. For example, the state detection unit 13 detects the speed, acceleration, steering angle, presence / absence and content of abnormality of the moving body 10, and the state of other moving body-mounted devices.
In the present embodiment, the state detection unit 13 supplies data indicating the result of the detection process to the information acquisition unit 21.

The sensor unit 14 observes the surroundings of the moving body 10. In the present embodiment, the detection result acquired by the sensor unit 14 is supplied to the external information detection unit 12 and the information acquisition unit 21.

The map acquisition unit 15 acquires a map around the moving body 10 or around the moving route of the moving body 10. For example, when the moving body 10 moves the first floor of the building, the map acquisition unit 15 acquires the map of the first floor of the building. In this case, a map of the first floor of the building prepared in advance may be input, or the map may be generated by observing the surroundings of the moving body 10 by the self-position estimation unit 22.
In the present embodiment, the acquired map is supplied to the information acquisition unit 21.

The information processing device 20 has hardware necessary for configuring a computer, such as a processor such as a CPU, GPU, and DSP, a memory such as ROM and RAM, and a storage device such as an HDD (see FIG. 8). For example, the information processing method according to the present technology is executed by the CPU loading and executing the program according to the present technology recorded in advance in the ROM or the like into the RAM.
For example, the information processing apparatus 20 can be realized by any computer such as a PC. Of course, hardware such as FPGA and ASIC may be used.
In the present embodiment, the area generation unit as a functional block is configured by the CPU executing a predetermined program. Of course, in order to realize the functional block, dedicated hardware such as an IC (integrated circuit) may be used.
The program is installed in the information processing apparatus 20 via, for example, various recording media. Alternatively, the program may be installed via the Internet or the like.
The type of recording medium on which the program is recorded is not limited, and any computer-readable recording medium may be used. For example, any non-transient storage medium readable by a computer may be used.

As shown in FIG. 2, the information processing apparatus 20 includes an information acquisition unit 21, a self-position estimation unit 22, an occupancy rate information generation unit 23, an area generation unit 24, a determination unit 25, an area map output unit 26, and a route generation unit. Has 27.

The information acquisition unit 21 acquires various information. In the present embodiment, the information acquisition unit 21 acquires various information from the moving body 10. For example, the detection result regarding an object around the moving body 10 or an obstacle such as a wall is acquired.
Further, the information acquisition unit 21 outputs various acquired information to the self-position estimation unit 22 and the occupancy rate information generation unit 23.

The self-position estimation unit 22 is the position of the moving body 10 based on the data or signals from the external information detection unit 12, the state detection unit 13, the sensor unit 14, and the map acquisition unit 15 acquired by the information acquisition unit 21. And estimation processing such as posture is performed. Further, the self-position estimation unit 22 stores the time-series information supplied in the time series in the database based on the detection result supplied from the sensor unit 14, and also stores the self-position based on the accumulated time-series information. Estimate and output as time series information self-position.
Further, the self-position estimation unit 22 estimates the self-position based on the current detection result supplied from the sensor unit 14, and outputs the current information self-position. Then, the self-position estimation unit 22 outputs the self-position estimation result by integrating or switching between the time-series information self-position and the current information self-position. Further, the self-position estimation unit 22 detects the posture of the moving body 10 based on the detection result supplied from the sensor unit 14, changes in the posture are detected, the self-position changes significantly, and the time-series information self. When the position estimation accuracy is considered to be reduced, the self-position is estimated only from the current information self-position.
Further, the self-position estimation unit 22 generates a map used for self-position estimation by SLAM or the like.
In the present embodiment, the self-position of the moving body 10 estimated by the self-position estimation unit 22 is supplied to the occupancy rate information generation unit 23 and the route generation unit 27.

The occupancy rate information generation unit 23 generates occupancy rate information based on the detection result from the sensor unit 14. In the present embodiment, the occupancy rate information generation unit 23 generates occupancy rate information based on the detection result and the self-position of the moving body 10. For example, the occupancy rate information generation unit 23 generates occupancy rate information at each position on the map based on the acquired map and the position information of the obstacle.
In the present embodiment, the occupancy rate information generation unit 23 outputs the generated occupancy rate information to the area generation unit 24.

The area generation unit 24 generates one or more rotation areas according to the occupancy rate information. In the present embodiment, the area generation unit 24 generates a rotation area according to the occupancy rate information generated by the occupancy rate information generation unit 23 with respect to the acquired map. For example, the region generation unit 24 generates a rotation region at the estimated self-position of the moving body 10.
Further, the area generation unit 24 can change the occupancy rate information in the rotation area. For example, when the rotation regions are superimposed, the region generation unit 24 adds the rotation speeds of the rotation regions. Specifically, when the counterclockwise rotation region B is superimposed on the counterclockwise rotation region A, the rotation speed of the rotation region B becomes +2.
Further, the area generation unit 24 changes the occupancy rate information according to the distance between the rotation areas. For example, the region generation unit 24 changes the occupancy rate information based on the distance between a predetermined point in the rotation region and the boundary of the rotation region.

The determination unit 25 determines whether or not the amount of calculation required for various processes exceeds a predetermined threshold value. In the present embodiment, the determination unit 25 determines whether or not the amount of calculation for estimating the self-position of the moving body 10 exceeds a predetermined threshold value. For example, the determination unit 25 determines based on the performance of processing the calculation of the mobile body 10 or the information processing apparatus 20.
Further, when the calculation amount exceeds a predetermined threshold value according to the determination result of the determination unit 25, the rotation region is controlled by the region generation unit 24. For example, when an area map including many rotation areas is generated on the map, the rotation area is deleted by the area generation unit 24.
Further, the region generation unit 24 deletes the rotation region based on the distance between the movement direction (path) of the moving body 10 and the rotation region. For example, the region generation unit 24 deletes a rotation region existing in a direction opposite to the movement direction of the moving body 10. Further, for example, the region generation unit 24 deletes a rotation region that is separated from the path of the moving body 10 by a predetermined threshold value or more.

The area map output unit 26 outputs a region map including a rotation region generated by the region generation unit 24. In the present embodiment, the area map controlled by the area generation unit 24 is output based on the determination result of the determination unit 25. The output area map may be presented to the user's PC or the like.

The route generation unit 27 generates a movement route through which the moving body 10 passes. In the present embodiment, the route generation unit 27 generates the movement route of the moving body 10 based on the area map output by the area map output unit 26. For example, a movement path of the moving body 10 is generated by a cost function in which the cost of the counterclockwise rotation region is higher than the cost of the clockwise rotation region.
The movement path includes the path through which the moving body 10 passes, and the movement of the moving body 10 such as start, stop, traveling direction (for example, forward, backward, turning, etc.), and moving speed. The movement path also includes a flight pattern of the moving body 10. That is, the locus and speed defined as a pattern such as a turn and a figure of eight are also included in the action plan and the motion plan. For example, for a flight pattern such as a turn or a figure of eight, the speed, curvature, or the like of the moving body 10 when making the turn or the figure of eight is generated as a movement path.
The method of generating the movement route is not limited, for example, A * algorithm (A star search algorithm) that divides the environment in a grid pattern and optimizes the arrival judgment and the weight of the route to generate the best path, and self. An RRT (Rapidly-exploring Random Tree) algorithm or the like that extends the path from the position to the place where the incremental can be reached while appropriately pruning may be used.

In the present embodiment, the occupancy rate information generation unit 23 and the area generation unit 24 are maps including occupancy rate information generated by the detection result from the sensor and showing the probability of whether or not an obstacle exists at each position. On the other hand, it functions as a generation unit that generates one or more regions by boundary representation for estimating the obstacle based on the occupancy rate information.
In this embodiment, the self-position estimation unit 22 corresponds to an estimation unit that estimates the position of a moving body having a sensor.
In the present embodiment, the determination unit 25 corresponds to a determination unit that determines whether or not the amount of calculation for estimating the position of the moving body exceeds a predetermined threshold value.
In the present embodiment, the route generation unit 27 corresponds to a route generation unit that generates a movement route related to the movement of the moving body having the sensor based on the map in which the region is generated.

FIG. 3 is a flowchart showing an example of control of self-position estimation of the moving body 10.

The self-position estimation unit 22 determines the initial position of the moving body 10 (step 101). For example, the self-position estimation unit 22 determines the initial position of the moving body 10 by using the odometry that estimates the current position from the rotation speed of the tire.

The map acquisition unit 15 acquires a map around the moving body 10 (step 102).

The sensor unit 14 acquires the detection result around the moving body 10. The occupancy rate information generation unit 23 generates occupancy rate information based on the detection result (step 103).

The region generation unit 24 generates a rotation region for the acquired map (step 104). In the present embodiment, based on the detection result acquired from the sensor unit 14, a clockwise rotation region is generated in the region where there is a high possibility that an obstacle does not exist. In addition, a counterclockwise rotation region is generated in the region where obstacles are likely to exist.

The self-position estimation unit 22 samples the self-position of the mobile body 10 according to the already estimated distribution of the self-position of the mobile body 10 (step 105).
Further, the self-position estimation unit 22 calculates the likelihood for each self-position of the sampled mobile body 10 by comparing the rotation region with the map (step 106).
Further, the self-position estimation unit 22 predicts the distribution from the self-position and the likelihood of the moving body 10, and updates the distribution of the self-position of the moving body 10 (step 107).
When the estimation of the self-position of the moving body 10 by the self-position estimation unit 22 is completed, the self-position estimation is completed (YES in step 108).
When it becomes necessary to update the self-position of the moving body 10, the process returns to step 103 (NO in step 108). For example, the self-position estimation unit 22 updates the self-position estimation based on the passage of a predetermined time or the movement of the moving body 10 by a predetermined distance.

FIG. 4 is a flowchart showing an example of map area generation.

The self-position estimation unit 22 determines the initial position of the moving body 10 (step 201).

If the area map already exists, the area generation unit 24 initializes the area map (step 202). It was generated when the environment around the moving body 10 changed, for example, when the moving body 10 moved from the point where the area map was generated, or when an obstacle around the moving body 10 moved. The area map is initialized. The initialization includes the deletion of the rotation area and the map generated by SLAM or the like.

After the area map is initialized, the processes of steps 103 to 107 shown in FIG. 3 are executed (step 203).

The region generation unit 24 adds a rotation region to the estimated self-position of the moving body 10 on the map (step 204). For example, the region generation unit 24 adds a rotation region to the position according to the distribution of the self-position of the moving body 10.

The determination unit 25 determines whether or not the amount of calculation required for estimating the self-position exceeds a predetermined threshold value (step 205).

The region generation unit 24 deletes the rotation region having little influence from the region map (step 206). The fact that the influence is small means that the movement of the moving body 10 is not interfered with. For example, the region generation unit 24 deletes a rotation region that is separated from the self-position of the moving body 10 or the moving path by a predetermined distance or more. Further, for example, the region generation unit 24 deletes a rotation region located in a direction opposite to the movement direction of the moving body 10. That is, the region generation unit 24 deletes the rotation region existing at a position that does not interfere with the movement of the moving body 10. As a result, the area map can be simplified and the amount of calculation can be reduced.

If the output area map is suitable for the application, the flow of map area generation ends (YES in step 207). For example, if the area map contains sufficient information to generate the movement path of the moving body 10, the flow ends. If the output area map is not suitable for the intended use, or if the area map needs to be updated, the process returns to step 203 (NO in step 207).

FIG. 5 is a schematic diagram showing an example of a rotation region.
The example shown in FIG. 5 shows a state in which the rotation region is completely included (superimposed).
In the present embodiment, as shown in FIG. 5, the region generation unit 24 provides a clockwise circular rotation region 30, a counterclockwise rectangular rotation region 31 within the rotation region 30, and a counterclockwise rectangular rotation region. 32 and a counterclockwise pentagonal rotation region 33 within the rotation region 32 are generated.

In this case, assuming that the outside of the region is an infinity point (rotation speed 0), the occupancy rate information in the rotation region 30 is expressed as -1 as the rotation speed. Further, since the rotation direction (direction) of the rotation region 31 is counterclockwise, the occupancy information in the rotation region 30 becomes 0 by adding 1 to -1.
The occupancy rate information in the rotation region 32 is +1. Further, the occupancy rate information in the rotation region 32 becomes +2 by adding 1 to +1 because the direction of the rotation region 33 is counterclockwise.

That is, it is unlikely that an obstacle exists in the circular rotation region 30 excluding the rectangular rotation region 31, and it is unknown whether an obstacle exists in the rectangular rotation region 31.
Further, there is a high possibility that an obstacle exists in the rectangular rotation region 32 excluding the pentagonal rotation region 33, and it is more likely that an obstacle exists in the pentagonal rotation region 33 than in the rectangular rotation region 32. ..

FIG. 6 is a schematic diagram showing another example of the rotation region.
The example shown in FIG. 6 shows a state in which a part of the rotation region is included.
In the present embodiment, as shown in FIG. 6, the region generation unit 24 generates a counterclockwise rectangular rotation region 35, a counterclockwise rectangular rotation region 36, and a clockwise circular rotation region 37. To.

In this case, assuming that the outside of the region is an infinity point (rotation number 0), the occupancy information of the rectangular rotation region 35 (region 38 and region 39) on which the rectangular rotation region 36 and the circular rotation region 37 are not superimposed is rotated. It is expressed as +1 as a number.
Similarly, the occupancy rate information of the rectangular rotation region 36 (region 40 and region 41) on which the rectangular rotation region 35 and the circular rotation region 37 are not superimposed is expressed as +1 as the rotation speed.
Similarly, the occupancy rate information of the circular rotation region 37 (region 42 and region 43) on which the rectangular rotation region 35 and the quadrangular rotation region 36 are not superimposed is expressed as -1 as the rotation speed.

The occupancy information of the area 44, which is not superimposed on the circular rotation area 37 and is superimposed on the rectangular rotation area 35 and the rectangular rotation area 36, is counterclockwise in both directions, so by adding 1 to +1 It becomes +2.
Further, the occupancy information of the region 45 and the region 46, which are not superimposed on the rectangular rotation region 36 and are superimposed on the rectangular rotation region 35 and the circular rotation region 37, is 0 because the directions are opposite. Similarly, the rotation speed of the occupancy information of the region 47 that is not superimposed on the rectangular rotation region 35 and is superimposed on the rectangular rotation region 36 and the circular rotation region 37 is also 0.

The occupancy information of the area 48 on which the rectangular rotation area 35, the rectangular rotation area 36, and the circular rotation area 37 overlap is rotated because there is one clockwise rotation area and two counterclockwise rotation areas. The number becomes +1.

FIG. 7 is a schematic diagram showing another example of the rotation region.
In the example shown in FIG. 7, a state in which one rotation region intersects is shown.
In this embodiment, as shown in FIG. 7, the region generation unit 24 generates a counterclockwise rotation region 50. Further, in the rotation region 50, the line segment 51 and the line segment 52 intersect. That is, one rotation region 50 has two regions by a region 53 and a region 54 surrounded by a line segment.

In this case, assuming that the outside of the region is an infinity point (rotation speed 0), the occupancy rate information of the region 53 is counterclockwise and is expressed as +1 as the rotation speed. Further, the occupancy rate information of the area 54 is expressed as -1 as the rotation speed because the direction is clockwise.

As described above, the information processing apparatus 20 according to the present embodiment has a map generated by the detection result from the sensor unit 14 and including the occupancy rate information indicating the probability of the existence of the obstacle 1 at each position. A rotation region with one or more boundary representations is generated according to the occupancy rate information. This makes it possible to create a highly accurate map with a small amount of calculation.

In general, it is necessary to store map information when a robot or the like refers to a map created in advance to perform self-position estimation, or when performing SLAM or the like that simultaneously performs self-position estimation and map generation. Conventionally, the representation was performed with a grid-like data structure. For a grid-like data structure, it is necessary to determine the grid width at the time of generation, and in principle it is difficult to express a shape finer than the grid width. When the grid width is made finer, the required storage amount and the amount of calculation increase sharply, so there is a limit to improving the accuracy by making the grid width finer.

High-precision positioning is required depending on the task of the robot, such as when the robot grabs an object or when passing through a narrow passage. However, high-precision positioning requires high-precision self-position estimation, and when high real-time performance is required for high-speed operation of the robot or when a computer with low performance is used for edge processing, etc. Is required to reduce the amount of calculation.

Therefore, in the present technology, for a map including occupancy rate information indicating the probability of existence of an obstacle at each position generated by data acquired from a sensor, one or more boundary representations are expressed according to the occupancy rate information. A rotation area is generated by. This makes it possible to realize self-position estimation and SLAM that are resistant to disturbance with high accuracy and a small amount of calculation.
By including a part or all of a plurality of rotation regions, it is possible to efficiently express a small difference or a large difference in the occupancy rate information.

If O is an order, A is an area, and p is an accuracy, the memory usage is O (A / p ^ 2) in the case of a grid-like data structure. The processing time is O (A / p ^ 2).
In the case of boundary representation, the memory usage is O (A / p). The processing time is O (A / plowA / p).
That is, since the accuracy is not restricted by the grid width and the occupancy rate for each part can be expressed, highly accurate self-position estimation by accumulating time series data can be efficiently processed.

Also, the information on the map is often sparse. Therefore, since the boundary representation handles only the part where the numerical value changes, it is possible to shorten the processing time and save the memory for sparse information.

<Other embodiments>
The present technology is not limited to the embodiments described above, and various other embodiments can be realized.

In the above embodiment, the occupancy information in the rotation region is expressed as a constant. Not limited to this, the occupancy rate information may be changed according to the distance from the boundary of the rotation region (the line segment constituting the rotation region). Further, a parameter of a function indicating the relationship between the change of the occupancy rate information at the distance from the boundary may be set with respect to the set of the rotation areas, the rotation area, or the boundary of the rotation area. This makes it possible to express a smooth change in the occupancy rate.

In the above embodiment, one map area includes a region where an obstacle is likely to be present (counterclockwise rotation region) and a region where an obstacle is unlikely to be present (clockwise rotation region). Was expressed. Not limited to this, a map area representing an area where an obstacle is likely to exist and a map area representing an area where an obstacle is unlikely to exist may be processed separately.

In the above embodiment, the number of rotations at the point at infinity is expressed as 0. The occupancy rate at an infinity point or a predetermined point is stored, and the occupancy rate information of the rotation region may be changed based on the stored occupancy rate information. As a result, the occupancy rate information that occupies most of the entire map area can be efficiently expressed by different maps.

In the above embodiment, the rotation speed is added by including the rotation region. Not limited to this, various arithmetic processes may be performed. For example, sign inversion, four arithmetic operations, Booleans such as AND / OR / XOR, application of a function, and the like may be performed. Further, translation of the rotation region, enlargement / reduction of the rotation region, rotation of the rotation region, offset of the rotation region, and the like may be performed. As a result, the calculation can be performed with a smaller amount of calculation than the grid-shaped data structure.

In the above embodiment, the area map including the rotation area is output. Not limited to this, clipping processing may be performed to cut out only the part necessary for the processing. For example, clipping processing may be performed on a portion where a counterclockwise rotation region exists. As a result, the amount of processing can be reduced.

In the above embodiment, the rotation speed of the counterclockwise rotation region is expressed as +1 and the rotation speed of the clockwise rotation region is expressed as -1. Not limited to this, the number of rotations in the clockwise rotation region may be expressed as +1. Of course, the occupancy rate information may be expressed by expressions other than numbers.

In the above embodiment, an area map including occupancy rate information indicating the probability that an obstacle exists at each position is output. Not limited to this, for example, the possibility that a target being searched for a moving object may exist may be expressed by a boundary representation. That is, the present technology is applicable to data that can be expected to be sparse with respect to space, in addition to the occupancy rate.

FIG. 8 is a block diagram showing a hardware configuration example of the information processing apparatus 20.

The information processing apparatus 20 includes a CPU 201, a ROM 202, a RAM 203, an input / output interface 205, and a bus 204 connecting them to each other. A display unit 206, an input unit 207, a storage unit 208, a communication unit 209, a drive unit 210, and the like are connected to the input / output interface 205.

The display unit 206 is a display device using, for example, a liquid crystal display, an EL, or the like. The input unit 207 is, for example, a keyboard, a pointing device, a touch panel, or other operating device. When the input unit 207 includes a touch panel, the touch panel may be integrated with the display unit 206.

The storage unit 208 is a non-volatile storage device, for example, an HDD, a flash memory, or other solid-state memory. The drive unit 210 is a device capable of driving a removable recording medium 211 such as an optical recording medium or a magnetic recording tape.

The communication unit 209 is a modem, router, or other communication device for communicating with another device that can be connected to a LAN, WAN, or the like. The communication unit 209 may communicate using either wired or wireless. The communication unit 209 is often used separately from the information processing device 20.

Information processing by the information processing apparatus 20 having the hardware configuration as described above is realized by the cooperation between the software stored in the storage unit 208 or the ROM 202 and the hardware resources of the information processing apparatus 20. Specifically, the information processing method according to the present technology is realized by loading the program constituting the software stored in the ROM 202 or the like into the RAM 203 and executing the program.

The program is installed in the information processing apparatus 20 via, for example, the recording medium 211. Alternatively, the program may be installed in the information processing apparatus 20 via a global network or the like. In addition, any non-transient storage medium that can be read by a computer may be used.

The information processing device, information processing method, and program related to this technology are executed by linking the computer mounted on the communication terminal with another computer that can communicate via a network or the like, and the information processing device related to this technology. May be constructed.

That is, the information processing apparatus, information processing method, and program according to the present technology can be executed not only in a computer system composed of a single computer but also in a computer system in which a plurality of computers operate in conjunction with each other. In the present disclosure, the system means a set of a plurality of components (devices, modules (parts), etc.), and it does not matter whether or not all the components are in the same housing. Therefore, a plurality of devices housed in separate housings and connected via a network, and one device in which a plurality of modules are housed in one housing are both systems.

The information processing device, information processing method, and program related to this technology are executed by a computer system, for example, when the occupancy rate information is generated, the rotation area is generated, and the area map is output by a single computer. , And when each process is performed by a different computer. Further, the execution of each process by a predetermined computer includes having another computer execute a part or all of the process and acquiring the result.

That is, the information processing device, information processing method, and program according to the present technology can be applied to a cloud computing configuration in which one function is shared by a plurality of devices via a network and jointly processed. ..

Each configuration of the occupancy rate information generation unit, area generation unit, area map output unit, etc., the control flow of the communication system, etc. described with reference to each drawing are merely embodiments, and are within the scope of the present technology. , Can be transformed arbitrarily. That is, other arbitrary configurations, algorithms, and the like for implementing the present technology may be adopted.

It should be noted that the effects described in the present disclosure are merely examples and are not limited, and other effects may be used. The description of the plurality of effects described above does not necessarily mean that the effects are exerted at the same time. It means that at least one of the above-mentioned effects can be obtained depending on the conditions and the like, and of course, there is a possibility that an effect not described in the present disclosure may be exhibited.

It is also possible to combine at least two feature portions among the feature portions of each form described above. That is, the various characteristic portions described in each embodiment may be arbitrarily combined without distinction between the respective embodiments.

In addition, this technology can also adopt the following configurations.
(1) The obstacle is estimated based on the occupancy rate information on the map including the occupancy rate information indicating the probability of whether or not the obstacle exists at each position generated by the detection result from the sensor. An information processing device including a generation unit that generates one or more areas by a boundary representation for the purpose.
(2) The information processing apparatus according to (1).
The generation unit is an information processing device that generates one or more regions based on the occupancy rate information expressed as a rotation speed.
(3) The information processing apparatus according to (1) or (2).
The one or more regions are a plurality of regions.
The generation unit is an information processing device that changes the occupancy rate information based on the distance between the plurality of regions.
(4) The information processing apparatus according to (3).
The generation unit is an information processing device that changes the occupancy rate information based on the distance between a predetermined point in the one or more regions and a boundary constituting the one or more regions.
(5) The information processing apparatus according to any one of (1) to (4).
The generation unit is an information processing device that superimposes one or more regions based on the occupancy rate information.
(6) The information processing apparatus according to any one of (1) to (5).
The sensor includes a distance measuring sensor.
The generation unit is an information processing device that generates each of the one or more regions based on the distance information from the distance measuring sensor.
(7) The information processing apparatus according to (6).
The generation unit is an information processing device that determines boundaries constituting the one or more regions based on the distance information.
(8) The information processing apparatus according to any one of (1) to (7).
The sensor is mounted on a moving body and is mounted on a moving body.
The information processing device is further provided with an estimation unit for estimating the position of the moving body.
(9) The information processing apparatus according to any one of (1) to (8).
The sensor is mounted on a moving body and is mounted on a moving body.
The information processing device is further provided with a determination unit for determining whether or not the amount of calculation required for estimating the position of the moving body exceeds a predetermined threshold value.
(10) The information processing apparatus according to (9).
The generation unit is an information processing device that controls one or more regions based on the boundary representation based on the determination result of the determination unit.
(11) The information processing apparatus according to (9) or (10).
The generation unit is an information processing device that deletes an area based on the boundary representation based on the determination result of the determination unit and the position of the moving body.
(12) The information processing apparatus according to (9) or (11).
The generation unit is an information processing device that deletes an area based on the boundary representation based on the determination result of the determination unit and the path of the moving body.
(13) The information processing apparatus according to any one of (1) to (12).
An information processing apparatus including a route generation unit that generates a route for a moving body having the sensor based on a map in which one or more regions are generated.
(14) The information processing apparatus according to any one of (1) to (13).
The sensor is an information processing device including LiDAR (Light Detection and Ranging).
(15)
Boundary for estimating the obstacle based on the occupancy information for a map containing occupancy information indicating the probability of presence of an obstacle at each position generated by the detection result from the sensor. An information processing method in which a computer system executes to generate one or more areas by expression.
(16)
A boundary for estimating the obstacle based on the occupancy information for a map containing occupancy information indicating the probability of presence or absence of an obstacle at each position generated by the detection result from the sensor. A program that causes a computer system to perform steps to generate one or more areas of representation.

10 ... Moving body 14 ... Sensor unit 20 ... Information processing device 22 ... Self-position estimation unit 23 ... Occupancy rate information generation unit 24 ... Area generation unit 25 ... Judgment unit 26 ... Area map output unit 27 ... Route generation unit 100 ... Map generation system

Claims (16)

Boundary point for estimating the obstacle based on the occupancy information for the map including the occupancy rate information indicating the probability of the existence of the obstacle at each position generated by the detection result from the sensor. An information processing device including a generator that generates one or more regions by representation. The information processing apparatus according to claim 1.
The generation unit is an information processing device that generates one or more regions based on the occupancy rate information expressed as a rotation speed. The information processing apparatus according to claim 1.
The one or more regions are a plurality of regions.
The generation unit is an information processing device that changes the occupancy rate information based on the distance between the plurality of regions. The information processing apparatus according to claim 3.
The generation unit is an information processing device that changes the occupancy rate information based on the distance between a predetermined point in the one or more regions and a boundary constituting the one or more regions. The information processing apparatus according to claim 1.
The generation unit is an information processing device that superimposes one or more regions based on the occupancy rate information. The information processing apparatus according to claim 1.
The sensor includes a distance measuring sensor.
The generation unit is an information processing device that generates each of the one or more regions based on the distance information from the distance measuring sensor. The information processing apparatus according to claim 6.
The generation unit is an information processing device that determines boundaries constituting the one or more regions based on the distance information. The information processing apparatus according to claim 1.
The sensor is mounted on a moving body and is mounted on a moving body.
The information processing device is further provided with an estimation unit for estimating the position of the moving body. The information processing apparatus according to claim 1.
The sensor is mounted on a moving body and is mounted on a moving body.
The information processing device is further provided with a determination unit for determining whether or not the amount of calculation required for estimating the position of the moving body exceeds a predetermined threshold value. The information processing apparatus according to claim 9.
The generation unit is an information processing device that controls one or more regions based on the boundary representation based on the determination result of the determination unit. The information processing apparatus according to claim 9.
The generation unit is an information processing device that deletes an area based on the boundary representation based on the determination result of the determination unit and the position of the moving body. The information processing apparatus according to claim 9.
The generation unit is an information processing device that deletes an area based on the boundary representation based on the determination result of the determination unit and the path of the moving body. The information processing apparatus according to claim 1, further
An information processing apparatus including a route generation unit that generates a route for a moving body having the sensor based on a map in which one or more regions are generated. The information processing apparatus according to claim 1.
The sensor is an information processing device including LiDAR (Light Detection and Ranging). Boundary for estimating the obstacle based on the occupancy information for a map containing occupancy information indicating the probability of presence of an obstacle at each position generated by the detection result from the sensor. An information processing method in which a computer system executes to generate one or more areas by expression. A boundary for estimating the obstacle based on the occupancy information for a map containing occupancy information indicating the probability of presence or absence of an obstacle at each position generated by the detection result from the sensor. A program that causes a computer system to perform steps to generate one or more areas of representation.

Images