Information processing device, information processing method, and computer program

Abstract

This method estimates the global trajectory of a moving object without pre-preparing or updating map data for the entire range of movement of the moving object. [Solution] The information processing device includes an ambient information acquisition unit, a local trajectory estimation unit, a transformation information acquisition unit, and a coordinate transformation unit. The ambient information acquisition unit acquires ambient information from sensors that indicates the conditions around the moving object. The local trajectory estimation unit estimates the local trajectory, which is the trajectory of the moving object in the local coordinate system, based on the acquired ambient information. The transformation information acquisition unit acquires transformation information for a point on the local trajectory, to transform the coordinates in the local coordinate system to the coordinates in the global coordinate system. The coordinate transformation unit estimates the global trajectory, which is the trajectory of the moving object in the global coordinate system, by performing a coordinate transformation on the local trajectory using the acquired transformation information.

Description

Technical Field

[0001] The technology disclosed in this specification relates to an information processing apparatus, an information processing method, and a computer program.

Background Art

[0002] Conventionally, there is known a technique in which a map represented in a global coordinate system is created in advance, and the movement amount of a moving body (odometry) is estimated by accumulating local sensor data, and the self-position of the moving body is estimated from the map and the estimated movement amount (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the above conventional technology, it is necessary to prepare map data for the entire movable range of the moving body in advance. Therefore, there is a problem that the memory cost for storing the map data is large. Further, in the above conventional technology, when the environment changes, it is necessary to update the map data. Therefore, there is a problem that the management burden of the map data is large.

[0005] This specification discloses a technology capable of solving the above problems.

Means for Solving the Problems

[0006] The technology disclosed in this specification can be realized, for example, in the following forms.

[0007] (1) The information processing device disclosed herein includes an ambient information acquisition unit, a local trajectory estimation unit, a transformation information acquisition unit, and a coordinate transformation unit. The ambient information acquisition unit acquires ambient information from sensors that indicates the conditions around a moving object. The local trajectory estimation unit estimates a local trajectory, which is the trajectory of the moving object in a local coordinate system, based on the acquired ambient information. The transformation information acquisition unit acquires transformation information for a point on the local trajectory, for transforming the coordinates in the local coordinate system to coordinates in a global coordinate system. The coordinate transformation unit estimates a global trajectory, which is the trajectory of the moving object in a global coordinate system, by performing a coordinate transformation on the local trajectory using the acquired transformation information.

[0008] Thus, this information processing device can estimate a global trajectory by acquiring transformation information for a single point on the local trajectory and performing a coordinate transformation on the local trajectory using this transformation information. Therefore, there is no need to prepare or update map data for the entire range of movement of the moving object in advance, which significantly reduces memory costs and the burden of managing map data.

[0009] (2) The above information processing device further includes a map data acquisition unit that acquires partial or incomplete map data for the movable range of the moving object, and the conversion information acquisition unit may acquire the conversion information based on the surrounding information and the map data. With this configuration, conversion information can be acquired based on partial or incomplete map data, so that the process of associating a position on the local trajectory with a position in the global coordinate system can be realized at high speed and with high accuracy.

[0010] (3) The above information processing device further includes an estimated position information acquisition unit that acquires estimated position information indicating the estimated position of the moving object in the global coordinate system, and the transformation information acquisition unit may acquire the transformation information based on the estimated position information. With this configuration, since transformation information can be acquired based on the estimated position information, the process of associating a position on the local trajectory with a position in the global coordinate system can be realized at high speed and with high accuracy.

[0011] (4) The above-mentioned information processing device may further include an accuracy evaluation unit that evaluates the accuracy of the estimated location information based on the estimated global trajectory. With this configuration, the accuracy of the estimated location information can be evaluated easily and with high accuracy.

[0012] Furthermore, the technologies disclosed herein can be implemented in various forms, for example, in the form of an information processing device, a mobile device, an information processing method, a trajectory estimation method, a computer program that implements these methods, or a non-temporary recording medium on which such a computer program is stored. [Brief explanation of the drawing]

[0013] [Figure 1] This is an explanatory diagram illustrating the configuration of the mobile body 100 in the first embodiment. [Figure 2] Flowchart showing the trajectory estimation process of the first embodiment [Figure 3] An explanatory diagram showing an example of an application scenario for the trajectory estimation process of the first embodiment. [Figure 4] This is an explanatory diagram illustrating the configuration of the mobile body 100a in the second embodiment. [Figure 5] Flowchart showing the trajectory estimation process of the second embodiment [Figure 6] An explanatory diagram showing an example of an application scenario for the trajectory estimation process of the second embodiment. [Modes for carrying out the invention]

[0014] (First Embodiment) (Configuration of mobile unit 100) Figure 1 is a schematic diagram illustrating the configuration of the mobile body 100 in the first embodiment. The mobile body 100 in the first embodiment is an autonomous mobile body that moves autonomously without requiring human operation. The mobile body 100 is an example of an information processing device.

[0015] The mobile body 100 includes a control unit 110, a memory unit 120, a LiDAR 130, a drive unit 150, and a communication unit 155.

[0016] The LiDAR 130 is a sensor that irradiates, for example, laser light and recognizes the surrounding situation (e.g., the position, shape, moving speed, etc. of surrounding objects) based on the reflected light. The LiDAR 130 outputs surrounding information indicating the above surrounding situation to the control unit 110.

[0017] The drive unit 150 is composed of, for example, a motor, a steering, a brake, etc. The drive unit 150 controls the movement of, for example, the tire 102 to perform the movement operations (acceleration, steering, braking, etc.) of the mobile body 100.

[0018] The communication unit 155 is a communication interface that communicates with other devices in a predetermined communication method via a communication network.

[0019] The memory unit 120 is composed of, for example, a ROM, a RAM, a hard disk drive (HDD), etc., and is used to store various programs and data, or as a working area and a temporary storage area for data when executing various programs. For example, an autonomous movement control program CP11 is stored in the memory unit 120. The autonomous movement control program CP11 includes a trajectory estimation program CP12.

[0020] The control unit 110 is composed of, for example, a CPU or the like, and controls the operation of the mobile body 100 by executing a computer program read from the storage unit 120. For example, by reading and executing the autonomous movement control program CP11 from the storage unit 120, the control unit 110 functions as an autonomous movement control unit 111 that controls the autonomous driving of the mobile body 100. Further, by reading and executing the trajectory estimation program CP12 from the storage unit 120, the control unit 110 functions as a trajectory estimation unit 112 that estimates the movement trajectory of the mobile body 100. The trajectory estimation unit 112 includes a surrounding information acquisition unit 113, a local trajectory estimation unit 114, a conversion information acquisition unit 115, a coordinate conversion unit 116, and a map data acquisition unit 117. The functions of these units will be described later.

[0021] (Trajectory Estimation Process) Next, the trajectory estimation process executed in the mobile body 100 of the first embodiment will be described. The trajectory estimation process is a process of estimating a global trajectory, which is the movement trajectory of the mobile body 100 in the global coordinate system. The global coordinate system is a coordinate system based on a reference point in a three-dimensional space. The global coordinate system is also called the world coordinate system or the absolute coordinate system.

[0022] FIG. 2 is a flowchart showing the trajectory estimation process of the first embodiment. FIG. 3 is an explanatory diagram showing an example of an application scene of the trajectory estimation process of the first embodiment. FIG. 3 shows a trajectory T1 when the mobile body 100 autonomously moves within the construction site 10 including the site office 12 and the buildings B1, B2, and B3 under construction. In the example of FIG. 3, only the map data for the site office 12 among the construction site 10 is prepared in advance, and the map data for other areas is not prepared. The mobile body 100 is assumed to autonomously drive inside and outside the site office 12 at the construction site 10.

[0023] In the trajectory estimation process of the first embodiment, the map data acquisition unit 117 (Figure 1) of the mobile body 100 acquires partial map data (S110). The partial map data is map data represented in a global coordinate system and is partial or incomplete map data with respect to the movable range of the mobile body 100. In the example of Figure 3, the partial map data is not map data representing the entire construction site 10, but map data representing only the site office 12. The partial map data is acquired, for example, via the communication unit 155 and stored in the storage unit 120.

[0024] The surrounding information acquisition unit 113 (Figure 1) of the mobile body 100 acquires surrounding information from the LiDAR 130 indicating the conditions around the mobile body 100 (S120). The local trajectory estimation unit 114 estimates the local trajectory, which is the movement trajectory of the mobile body 100 in the local coordinate system, based on the acquired surrounding information (S130). The local coordinate system is a coordinate system fixed to the mobile body 100 located in three-dimensional space, and is used to represent how the surroundings appear from the perspective of the mobile body 100. The local coordinate system is also called the odometry coordinate system or the mobile body coordinate system. Estimation of the local trajectory based on surrounding information is achieved, for example, by repeatedly estimating the movement distance using SLAM (Simultaneous Localization and Mapping).

[0025] The transformation information acquisition unit 115 (Figure 1) of the mobile unit 100 acquires transformation information for a point on the local trajectory to convert the coordinates in the local coordinate system to the coordinates in the global coordinate system (S140). Specifically, the transformation information acquisition unit 115 refers to partial map data to identify the coordinates in the global coordinate system corresponding to a point on the local trajectory within the area where the partial map data exists (within the field office 12), and calculates a transformation matrix to convert the coordinates in the local coordinate system to the coordinates in the global coordinate system.

[0026] The coordinate transformation unit 116 (Figure 1) of the mobile body 100 estimates the global trajectory by performing a coordinate transformation on the local trajectory using the acquired transformation information (S150). This estimates the movement trajectory of the mobile body 100 in the global coordinate system (including the trajectory over areas where map data is not prepared in advance).

[0027] The trajectory estimation unit 112 of the mobile body 100 may output the estimated movement trajectory. For example, the trajectory estimation unit 112 may transmit the estimated movement trajectory to other devices on the network via the communication unit 155 for location information sharing. Alternatively, the trajectory estimation unit 112 may display the estimated movement trajectory on a display unit (not shown) of the mobile body 100 or other devices.

[0028] (Effects of the first embodiment) As described above, the mobile body 100 of the first embodiment includes a surrounding information acquisition unit 113, a local trajectory estimation unit 114, a transformation information acquisition unit 115, and a coordinate transformation unit 116. The surrounding information acquisition unit 113 acquires surrounding information from the LiDAR 130 that indicates the conditions around the mobile body 100. The local trajectory estimation unit 114 estimates the local trajectory, which is the trajectory of the mobile body 100 in the local coordinate system, based on the acquired surrounding information. The transformation information acquisition unit 115 acquires transformation information for a point on the local trajectory, to transform the coordinates in the local coordinate system to coordinates in the global coordinate system. The coordinate transformation unit 116 estimates the global trajectory, which is the trajectory of the mobile body 100 in the global coordinate system, by performing a coordinate transformation on the local trajectory using the acquired transformation information.

[0029] Thus, the mobile body 100 of this embodiment can estimate a global trajectory by acquiring transformation information for a point on its local trajectory and performing a coordinate transformation on the local trajectory using this transformation information. Therefore, there is no need to prepare or update map data for the entire range of movement of the mobile body 100 in advance, which can significantly reduce memory costs and the burden of managing map data.

[0030] The mobile body 100 of the first embodiment further includes a map data acquisition unit 117. The map data acquisition unit 117 acquires partial or incomplete map data for the mobile body 100's movable range. The conversion information acquisition unit 115 acquires conversion information based on the surrounding information acquired from the LiDAR 130 and the map data. In this way, the mobile body 100 of this embodiment can acquire conversion information based on partial or incomplete map data, enabling high-speed and high-precision processing of mapping a position on a local trajectory to a position in a global coordinate system.

[0031] (Second Embodiment) Figure 4 is an explanatory diagram schematically showing the configuration of the mobile body 100a in the second embodiment. In the following, for the configuration of the mobile body 100a in the second embodiment that is the same as that of the mobile body 100 in the first embodiment described above, the same reference numerals are used and their explanations will be omitted as appropriate.

[0032] The mobile body 100a of the second embodiment has a GPS receiver 132. The GPS receiver 132 estimates the position of the mobile body 100a in the global coordinate system based on signals received from GPS satellites and outputs estimated position information indicating the estimated position to the control unit 110.

[0033] Furthermore, in the mobile body 100a of the second embodiment, the trajectory estimation unit 112 includes an estimated position information acquisition unit 118 and an accuracy evaluation unit 119.

[0034] Figure 5 is a flowchart of the trajectory estimation process of the second embodiment. Figure 6 is an explanatory diagram showing an example of an application scenario for the trajectory estimation process of the second embodiment. Figure 6 shows the trajectory T2 and the estimated position Sp of the mobile body 100a estimated by the GPS receiver 132 when the mobile body 100a autonomously moves within the site including buildings B1 to B5. In the example of Figure 6, no map data is prepared. The mobile body 100a is assumed to autonomously travel inside and outside the buildings within the site. Inside the buildings, the GPS receiver 132 cannot receive GPS signals, and therefore the position estimation of the mobile body 100a based on GPS signals cannot be performed.

[0035] In the trajectory estimation process of the second embodiment, the acquisition of surrounding information (S120) and estimation of the local trajectory (S130) are performed, similar to the trajectory estimation process of the first embodiment.

[0036] The estimated position information acquisition unit 118 (Figure 4) for the moving object 100a acquires estimated position information from the GPS receiver 132, indicating the estimated position of the moving object 100a in the global coordinate system (S132). Then, the transformation information acquisition unit 115 (Figure 4) for the moving object 100a acquires transformation information based on the acquired estimated position information (S142). As described above in the first embodiment, the transformation information is information for converting the coordinates in the local coordinate system to the coordinates in the global coordinate system for a point on the local trajectory. The transformation information acquisition unit 115 refers to the estimated position information acquired from the GPS receiver 132 to identify the coordinates in the global coordinate system corresponding to a point on the local trajectory, and calculates a transformation matrix for converting the coordinates in the local coordinate system to the coordinates in the global coordinate system.

[0037] Subsequently, similar to the trajectory estimation process in the first embodiment, the coordinate transformation unit 116 (Figure 4) of the moving body 100a estimates the global trajectory by performing a coordinate transformation on the local trajectory using the acquired transformation information (S150).

[0038] Furthermore, the accuracy evaluation unit 119 (Figure 4) of the mobile body 100a evaluates the accuracy of the estimated position information based on the estimated global trajectory (S160). As shown in Figure 6, the accuracy of position estimation based on GPS signals is not always high, and position estimation based on GPS signals cannot be performed in situations where GPS signals cannot be received (for example, when inside a building). In this embodiment, the accuracy of the estimated position information is evaluated by comparing the estimated position Sp of the mobile body 100a estimated by the GPS receiver 132 with the global trajectory estimated by the trajectory estimation unit 112. As an index value representing the accuracy of the estimated position information, for example, the sum of the deviation amounts of each estimated position Sp from the estimated global trajectory can be used.

[0039] (Effects of the second embodiment) As described above, the mobile body 100a of the second embodiment, like the mobile body 100 of the first embodiment, includes a surrounding information acquisition unit 113, a local trajectory estimation unit 114, a conversion information acquisition unit 115, and a coordinate transformation unit 116. Therefore, it is possible to acquire conversion information for one point on the local trajectory and estimate the global trajectory by performing a coordinate transformation on the local trajectory using the said conversion information. This eliminates the need to prepare or update map data for the entire range of movement of the mobile body 100a in advance, significantly reducing memory costs and the burden of managing map data.

[0040] The mobile body 100a of the second embodiment further includes an estimated position information acquisition unit 118. The estimated position information acquisition unit 118 acquires estimated position information indicating the estimated position of the mobile body 100a in the global coordinate system. The transformation information acquisition unit 115 acquires transformation information based on the estimated position information. In this way, since the mobile body 100a of this embodiment can acquire transformation information based on the estimated position information, it can realize the process of mapping the position on the local trajectory to the position in the global coordinate system at high speed and with high accuracy.

[0041] The mobile body 100a of the second embodiment further includes an accuracy evaluation unit 119. The accuracy evaluation unit 119 evaluates the accuracy of the estimated position information based on the estimated global trajectory. According to the mobile body 100a of this embodiment, the accuracy of the estimated position information can be evaluated easily and with high accuracy.

[0042] (modified version) The technologies disclosed herein are not limited to the embodiments described above and can be modified in various forms without departing from their essence, for example, the following modifications are possible.

[0043] The configuration of the mobile body 100 in the above embodiment is merely an example and can be modified in various ways. For example, the mobile body 100 may have other sensors (e.g., a visible light camera, a far-infrared camera, an ultrasonic sensor, a radar, etc.) that can recognize the surrounding environment of the mobile body 100, either in place of or in conjunction with the LiDAR 130.

[0044] In the second embodiment described above, the mobile body 100a may have, in place of the GPS receiver 132, or together with the GPS receiver 132, other devices capable of acquiring estimated position information indicating the estimated position of the mobile body 100a in a global coordinate system (for example, other GNSS devices such as GLONASS, Galileo, QZSS, or a reader capable of reading AR markers).

[0045] In the above embodiment, some of the configuration implemented by hardware may be replaced with software, and conversely, some of the configuration implemented by software may be replaced with hardware.

[0046] The technologies disclosed herein are applicable not only to construction sites and building sites, but also to farms, factories and workshops where equipment such as forklifts are used. Furthermore, the technologies disclosed herein are applicable not only to the mobile device 100, but also to other information processing devices. For example, they can be applied to a device having only the functions of the control unit 110 and storage unit 120 in the above embodiment, or to a device that includes at least one of the LiDAR 130, GPS receiver 132, and communication unit 155. [Explanation of Symbols]

[0047] 10: Construction site 12: Site office 100: Mobile unit 102: Tires 110: Control unit 111: Autonomous movement control unit 112: Trajectory estimation unit 113: Surrounding information acquisition unit 114: Local trajectory estimation unit 115: Transformation information acquisition unit 116: Coordinate transformation unit 117: Map data acquisition unit 118: Estimated position information acquisition unit 119: Accuracy evaluation unit 120: Memory unit 130: LiDAR 132: GPS receiver 150: Drive unit 155: Communication unit

Claims

1. An information processing device, An ambient information acquisition unit that acquires ambient information indicating the surrounding conditions of a moving object from a sensor, A local trajectory estimation unit estimates the local trajectory, which is the trajectory of the moving object in the local coordinate system, based on the surrounding information. A conversion information acquisition unit acquires conversion information for converting the coordinates in the local coordinate system to the coordinates in the global coordinate system for a point on the local trajectory. A coordinate transformation unit that estimates the global trajectory, which is the trajectory of the moving object in the global coordinate system, by performing a coordinate transformation on the local trajectory using the transformation information, An information processing device equipped with the following features.

2. The information processing apparatus according to claim 1, further, The system includes a map data acquisition unit that acquires partial or incomplete map data for the movable range of the aforementioned moving body. The conversion information acquisition unit is an information processing device that acquires the conversion information based on the surrounding information and the map data.

3. The information processing apparatus according to claim 1, further, The system includes an estimated position information acquisition unit that acquires estimated position information indicating the estimated position of the moving object in a global coordinate system, The conversion information acquisition unit is an information processing device that acquires the conversion information based on the estimated position information.

4. The information processing apparatus according to claim 3, further, An information processing device comprising an accuracy evaluation unit that evaluates the accuracy of the estimated location information based on the estimated global trajectory.

5. Information processing method, A process of acquiring ambient information from a sensor that shows the conditions around a moving object, A step of estimating the local trajectory, which is the trajectory of the moving object in the local coordinate system, based on the surrounding information, For a point on the local trajectory, the process involves obtaining transformation information to convert the coordinates in the local coordinate system to the coordinates in the global coordinate system. The process involves estimating the global trajectory, which is the trajectory of the moving object in the global coordinate system, by performing a coordinate transformation on the local trajectory using the transformation information. An information processing method comprising:

6. It is a computer program, On the computer, The process involves acquiring ambient information from sensors that indicates the conditions around a moving object, Based on the surrounding information, a process is performed to estimate the local trajectory, which is the trajectory of the moving object in the local coordinate system. For a point on the local trajectory, a process is performed to obtain transformation information for converting the coordinates in the local coordinate system to coordinates in the global coordinate system. A process to estimate the global trajectory, which is the trajectory of the moving object in the global coordinate system, by performing a coordinate transformation on the local trajectory using the aforementioned transformation information, A computer program that executes something.

Images