WO2019176278A1

WO2019176278A1 - Information processing device, information processing method, program, and mobile body

Info

Publication number: WO2019176278A1
Application number: PCT/JP2019/001369
Authority: WO
Inventors: 遼高橋; 雅貴豊浦; 倫之鈴鹿
Original assignee: ソニー株式会社
Priority date: 2018-03-12
Filing date: 2019-01-18
Publication date: 2019-09-19

Abstract

To achieve the objective of this invention, an information processing device according to an embodiment of the present technology comprises an acquisition part, a computation part, and an assessment part. The acquisition part acquires information relating to the height position of a sensor capable of detecting mobile body periphery information. The computation part uses the acquired sensor height position information to compute an assessment region for assessing a situation in the periphery of the mobile body. The assessment part assesses the situation in the periphery of the mobile body on the basis of the computed assessment region and the periphery information having been detected by the sensor.

Description

Information processing apparatus, information processing method, program, and moving object

The present technology relates to an information processing apparatus, an information processing method, a program, and a moving body that can be applied to autonomous movement control of the moving body.

In recent years, technologies for realizing autonomous movement of vehicles and robots have been developed. Patent Document 1 describes an obstacle determination device that enables a vehicle or the like that performs autonomous movement to avoid an obstacle. In this obstacle determination device, the shape of the measurement range (measurement space region) by the distance measuring device is changed based on the inclination (inclination) of the distance measuring device. This prevents erroneous determination of an obstacle (paragraphs [0041] to [0054] in FIG. 4 of Patent Document 1).

JP 2017-59150 A

In the future, systems using autonomous movement control for vehicles, robots, etc. are expected to become widespread, making it possible to easily and accurately determine the situation around a moving object without using complicated algorithms. Technology is required.

In view of the circumstances as described above, an object of the present technology is to provide an information processing apparatus, an information processing method, a program, and a moving body that can easily and accurately determine the situation around the moving body. is there.

In order to achieve the above object, an information processing apparatus according to an embodiment of the present technology includes an acquisition unit, a calculation unit, and a determination unit.
The acquisition unit acquires information related to a height position of a sensor capable of detecting peripheral information of the moving body.
The calculation unit calculates a determination region for determining a situation around the moving body based on the acquired information on the height position of the sensor.
The determination unit determines a state of the periphery of the moving body based on the calculated determination area and the peripheral information detected by the sensor.

In this information processing apparatus, a determination region for determining the situation around the moving body is calculated based on information on the height position of the sensor. This makes it possible to easily and accurately determine the situation around the moving body.

The calculation unit may determine whether there is an obstacle around the moving body.

The acquisition unit may acquire shape data related to the periphery of the moving body. In this case, the determination unit may determine a situation around the moving body based on the relationship between the detected shape data and the determination region.

The acquisition unit may acquire three-dimensional point cloud data related to the periphery of the moving body. In this case, the determination unit may determine the situation around the moving body by determining whether or not the point data included in the three-dimensional point cloud data is included in the determination region.

The calculation unit may change the height position of the determination region according to a change in the height position of the sensor.

The calculation unit may calculate one or more determination planes that define the determination area. In this case, the one or more determination surfaces may include at least one of a first determination surface corresponding to the ground and a second determination surface corresponding to the ceiling surface.

The calculation unit may change the height position of at least one of the first determination surface and the second determination surface according to a change in the height position of the sensor.

The calculation unit may calculate the determination area based on a predetermined reference determination area based on the acquired information on the height position of the sensor.

The calculation unit may calculate the determination region so that the height position is the same as the height position of the reference determination region.

The calculation unit may correct the size of the calculated determination area in the height direction based on the acquired information on the height position of the sensor.

The acquisition unit may acquire information related to the tilt of the sensor. In this case, the calculation unit may calculate the determination area based on information on the tilt of the sensor.

The calculation unit may change the inclination of the determination region according to a change in the inclination of the sensor.

An information processing method according to an embodiment of the present technology is an information processing method executed by a computer system, and includes acquiring information related to a height position of a sensor capable of detecting peripheral information of a moving object.
Based on the acquired information on the height position of the sensor, a determination region for determining a situation around the moving body is calculated.
Based on the calculated determination area and the surrounding information detected by the sensor, a situation around the moving body is determined.

A program according to an embodiment of the present technology causes a computer system to execute the following steps.
Obtaining information related to a height position of a sensor capable of detecting peripheral information of the moving body;
Calculating a determination region for determining a situation around the moving body based on the acquired information on the height position of the sensor;
A step of determining a situation around the moving body based on the calculated determination region and the peripheral information detected by the sensor;

A moving body according to an embodiment of the present technology includes a drive unit, a sensor, a detection unit, a calculation unit, and a drive control unit.
The sensor can detect surrounding information.
The said detection part detects the information regarding the height position of the said sensor.
The calculation unit calculates a determination region for determining a surrounding situation based on the detected information on the height position of the sensor.
The determination unit determines a surrounding situation based on the calculated determination region and the peripheral information detected by the sensor.
The drive control unit controls the drive unit based on a determination result by the determination unit.

The drive unit may be a leg having a multi-joint structure.

As described above, according to the present technology, it is possible to easily and accurately determine the situation around the moving body. Note that the effects described here are not necessarily limited, and may be any of the effects described in the present disclosure.

It is a block diagram which shows the structural example used as the outline | summary of the moving body which concerns on one Embodiment of this technique. It is a block diagram which shows the structural example of the schematic function of the mobile body control system which controls a mobile body. It is a schematic diagram which shows the external appearance of the robot which is an example of a mobile body. It is a block diagram which shows the functional structural example for performing the determination process of an obstruction. It is a flowchart which shows an example of the determination process of an obstruction. It is a schematic diagram which shows an example of the reference | standard state of a robot. It is a schematic diagram which shows an example of the fluctuation | variation of the height position of a distance sensor. It is a figure which shows typically an example of the change of the height position of the determination area | region according to the variation | change_quantity. It is a figure which shows typically an example of the change of the height position of the determination area | region according to the variation | change_quantity. It is a schematic diagram which shows an example of the height position of a distance sensor, and inclination fluctuation | variation. It is a schematic diagram which shows an example of the height position of a distance sensor, and inclination fluctuation | variation. It is a figure which shows typically an example of the setting of the determination area | region according to the variation | change_quantity and inclination amount. It is a figure which shows typically an example of the setting of the determination area | region according to the variation | change_quantity and inclination amount. It is an external view showing an example of composition of vehicles carrying an automatic operation control part concerning one embodiment of this art. It is a block diagram which shows the structural example of the vehicle control system which controls a vehicle.

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

[Outline of this disclosure]
FIG. 1 is a block diagram illustrating a configuration example that is an outline of a moving object 10 according to an embodiment of the present technology.

The moving body 10 is, for example, a robot, and includes a sensor group 11, an autonomous movement control unit 12, and an actuator group 13.

The sensor group 11 includes sensors 11a-1 to 11a-n that detect various kinds of information necessary for recognizing the inside of the moving body 10 and the surroundings of the moving body 10, and the detection result is transmitted to the autonomous movement control unit. 12 is output. Further, when there is no need to particularly distinguish the sensors 11a-1 to 11a-n, they are simply referred to as the sensor 11a, and the other configurations are also referred to in the same manner.

More specifically, the sensors 11a-1 to 11a-n are, for example, a camera that images the surroundings of the moving body 10, an acceleration sensor that detects the movement of the moving body 10, and objects existing around the moving body 10. LiDAR (Light Detection and Ranging, Laser 測定 Imaging Detection and Ranging), ToF (Time of Flight) sensor for measuring distance, geomagnetic sensor for detecting direction, gyro sensor, acceleration sensor, pressure sensor for detecting changes in ambient pressure, Contact sensor that detects presence or absence of contact, temperature sensor that detects temperature, humidity sensor that detects humidity, PSD (Position Sensitive Detector) distance sensor, GNSS (Global Navigation Satellite System) that detects the position on the earth, etc. including.

The autonomous movement control unit 12 recognizes the surrounding situation from various detection results of the sensor group 11, generates an action plan based on the recognition result, and various types of actuator groups 13 that drive the robot according to the action plan. Actuators 13a-1 to 13a-n are operated. In addition, when it is not necessary to distinguish the actuators 13a-1 to 13a-n, they are simply referred to as the actuator 13a, and the other configurations are also referred to in the same manner.

More specifically, the autonomous movement control unit 12 includes a recognition processing unit 14, an action plan processing unit 15, and an action control processing unit 16.

The recognition processing unit 14 executes recognition processing based on the detection result supplied from the sensor group 11, for example, an image, a person, an object, a facial expression type, a position, an attribute, and a position of itself or an obstacle. It recognizes and outputs to the action plan process part 15 as a recognition result. Further, the recognition processing unit 14 estimates the self position based on the detection result supplied from the sensor group 11. At this time, the recognition processing unit 14 estimates the self position using a predetermined model. Further, the recognition processing unit 14 is a model different from the predetermined model when the self-position cannot be estimated using the predetermined model based on the detection result supplied from the sensor group 11 due to the influence of the external force. Estimate self-position.

Based on the recognition result, the action plan processing unit 15 generates an action plan such as a trajectory of the movement of the device related to the movement of the moving body 10, a state change, and a speed or acceleration based on the recognition result. To the behavior control processing unit 16.

The behavior control processing unit 16 generates a control signal for controlling the specific movements of the actuators 13a-1 to 13a-n of the actuator group 13 based on the behavior plan supplied from the behavior plan processing unit 15. Then, the actuator group 13 is operated.

The actuator group 13 operates the actuators 13a-1 to 13a-n that specifically operate the moving body 10 based on the control signal supplied from the behavior control processing unit 16. More specifically, the actuators 13a-1 to 13a-n operate operations of a motor, a servo motor, a brake, and the like that realize a specific movement of the moving body 10 based on the control signal.

In addition, the actuators 13a-1 to 13a-n include a configuration that realizes an expansion / contraction motion, a bending / extension motion, a turning motion, or the like, and includes an LED (Light Emission Diode) or an LCD (Liquid Crystal Display) that displays information. It can further include a configuration such as a display unit and a speaker for outputting sound. Therefore, when the actuator group 13 is controlled based on the control signal, operations of various devices that drive the moving body 10 are realized, information is displayed, and sound is output.

That is, by controlling the actuators 13a-1 to 13a-n of the actuator group 13, the operation related to the movement of the moving body 10 is controlled, and various information such as information display and sound output are also presented. Be controlled.

[Configuration example of mobile control system]
A moving body control system for controlling the moving body 10 for realizing the functions described above will be described.

FIG. 2 is a block diagram illustrating a schematic configuration example of a function of the moving body control system 100 that controls the moving body 10 of the present disclosure. 2 is an example of a mobile body control system that controls the mobile body 10 including a robot to which the present technology can be applied, but other mobile bodies such as an aircraft, a ship, and a multi It can also be applied as a system for controlling a rotor copter (drone) or the like. Also, the robot may be a wheel type robot, an autonomous driving vehicle that can be boarded, or a multi-legged walking type robot. Of course, the present invention can also be applied to a robot having a leg portion having a multi-joint structure as a drive unit.

The mobile control system 100 includes an input unit 101, a data acquisition unit 102, a communication unit 103, a mobile internal device 104, an output control unit 105, an output unit 106, a drive system control unit 107, a drive system system 108, a storage unit 109, And an autonomous movement control unit 110. The input unit 101, data acquisition unit 102, communication unit 103, output control unit 105, drive system control unit 107, storage unit 109, and autonomous movement control unit 110 are connected to each other via a communication network 111. . The communication network 111 is, for example, a communication network conforming to any standard such as CAN (Controller Area Network), LIN (Local Interconnect Network), LAN (Local Area Network) such as IEEE 802.3, or FlexRay (registered trademark). Or a bus, or a non-standardized communication method. In addition, each part of the mobile body control system 100 may be directly connected without going through the communication network 111.

In the following, when each unit of the mobile control system 100 performs communication via the communication network 111, the description of the communication network 111 is omitted. For example, when the input unit 101 and the autonomous movement control unit 110 communicate via the communication network 111, it is simply described that the input unit 101 and the autonomous movement control unit 110 communicate.

The input unit 101 includes a device used by the passenger for inputting various data and instructions. For example, the input unit 101 includes an operation device such as a touch panel, a button, a microphone, a switch, and a lever, and an operation device that can be input by a method other than manual operation by voice, gesture, or the like. In addition, for example, the input unit 101 may be a remote control device using infrared rays or other radio waves, or an external connection device such as a mobile device or a wearable device corresponding to the operation of the mobile control system 100. The input unit 101 generates an input signal based on data and instructions input by the passenger and supplies the input signal to each unit of the mobile control system 100.

The data acquisition unit 102 includes various sensors that acquire data used for processing of the mobile body control system 100, and supplies the acquired data to each part of the mobile body control system 100.

For example, the data acquisition unit 102 includes various sensors for detecting the state of the moving body and the like, thereby configuring the sensor group 112, and the sensor group 11 including the sensors 11a-1 to 11a-n in FIG. Corresponding to Specifically, for example, the data acquisition unit 102 includes a gyro sensor, an acceleration sensor, an inertial measurement device (IMU), an acceleration input operation amount such as an accelerator, a deceleration input operation amount, a direction instruction input operation amount, A sensor or the like is provided for detecting the rotational speed, input / output energy / fuel amount of the driving device such as the engine or motor, the torque amount of the engine or motor, or the rotational speed or torque of the wheel or joint.

For example, the data acquisition unit 102 includes various sensors for detecting information outside the moving body. Specifically, for example, the data acquisition unit 102 includes an imaging device such as a ToF camera, a stereo camera, a monocular camera, an infrared camera, a polarization camera, and other cameras. Further, for example, the data acquisition unit 102 includes an environmental sensor for detecting weather or weather and a surrounding information detection sensor for detecting an object around the moving body. The environmental sensor includes, for example, a raindrop sensor, a fog sensor, a sunshine sensor, a snow sensor, and the like. The ambient information detection sensor includes, for example, a laser range sensor, an ultrasonic sensor, a radar, a LiDAR, a sonar, and the like.

Further, for example, the data acquisition unit 102 includes various sensors for detecting the current position of the moving object. Specifically, for example, the data acquisition unit 102 includes a GNSS receiver that receives a GNSS signal from a GNSS satellite.

The communication unit 103 communicates with the mobile device 104 and various devices, servers, base stations, and the like outside the mobile device, and transmits and receives data supplied from each unit of the mobile control system 100. Data is supplied to each part of the mobile control system 100. Note that the communication protocol supported by the communication unit 103 is not particularly limited, and the communication unit 103 can support a plurality of types of communication protocols.

For example, the communication unit 103 performs wireless communication with the mobile internal device 104 using a wireless LAN, Bluetooth (registered trademark), NFC (Near Field Communication), WUSB (Wireless USB), or the like. Further, for example, the communication unit 103 is connected to a USB (Universal Serial Bus), HDMI (High-Definition Multimedia Interface), or MHL (Mobile High-definition Link) via a connection terminal (and a cable if necessary). ) Or the like to perform wired communication with the mobile internal device 104.

Further, for example, the communication unit 103 communicates with a device (for example, an application server or a control server) that exists on an external network (for example, the Internet, a cloud network, or an operator-specific network) via a base station or an access point. I do. In addition, for example, the communication unit 103 communicates with a terminal (for example, a pedestrian or a store terminal or an MTC (Machine Type Communication) terminal) that exists in the vicinity of the mobile body using P2P (Peer To To Peer) technology. I do. Further, for example, when the mobile body 10 is a vehicle, the communication unit 103 performs vehicle-to-vehicle (Vehicle to Vehicle) communication, road-to-vehicle (Vehicle to Infrastructure) communication, communication between the mobile body and the house (Vehicle to Home), In addition, V2X communication such as vehicle-to-pedestrian communication is performed. In addition, for example, the communication unit 103 includes a beacon receiving unit, receives radio waves or electromagnetic waves transmitted from a wireless station or the like installed on the road, and acquires information such as a current position, traffic jam, traffic regulation, or required time. To do.

The mobile internal device 104 includes, for example, a mobile device or wearable device possessed by a passenger, an information device that is carried in or attached to the mobile body, and a navigation device that searches for a route to an arbitrary destination.

The output control unit 105 controls the output of various information to the passenger of the moving body or the outside of the moving body. For example, the output control unit 105 generates an output signal including at least one of visual information (for example, image data) and auditory information (for example, audio data), and supplies the output signal to the output unit 106, thereby outputting the output unit The output of visual information and auditory information from 106 is controlled. Specifically, for example, the output control unit 105 synthesizes image data captured by different imaging devices of the data acquisition unit 102 to generate an overhead image or a panoramic image, and outputs an output signal including the generated image. This is supplied to the output unit 106. Further, for example, the output control unit 105 generates sound data including a warning sound or a warning message for a danger such as a collision, contact, or entry into a dangerous zone, and outputs an output signal including the generated sound data to the output unit 106. Supply.

The output unit 106 includes a device that can output visual information or auditory information to a passenger of the moving body or the outside of the moving body. For example, the output unit 106 includes a display device, an instrument panel, an audio speaker, headphones, a wearable device such as a glasses-type display worn by a passenger, a projector, a lamp, and the like. In addition to a device having a normal display, the display device included in the output unit 106 may display visual information in the driver's field of view, such as a head-up display, a transmissive display, and a device having an AR (Augmented Reality) display function. It may be a display device. Note that the output control unit 105 and the output unit 106 are not essential components for the autonomous movement process, and may be omitted as necessary.

The drive system control unit 107 controls the drive system 108 by generating various control signals and supplying them to the drive system 108. Further, the drive system control unit 107 supplies a control signal to each unit other than the drive system 108 as necessary, and notifies the control state of the drive system 108 and the like.

The drive system 108 includes various devices related to the drive system of the moving body. For example, the drive system 108 includes a servo motor that can specify the angle and torque of each joint of four legs, a motion controller that disassembles and replaces the movement movement of the robot itself into four leg movements, and Provided with a feedback control device using sensors in each motor and sensors on the back of the foot.

In another example, the drive system 108 includes a motor having four or six propellers facing upward, and a motion controller that disassembles and replaces the movement of the robot itself into the rotation amount of each motor.

In another example, the drive system 108 includes a driving force generator for generating a driving force such as an internal combustion engine or a driving motor, a driving force transmission mechanism for transmitting the driving force to the wheels, and a steering angle. A steering mechanism for adjusting, a braking device for generating braking force, an ABS (AntilocktiBrakeSystem), an ESC (ElectronicElectroStability Control), an electric power steering device, and the like are provided. The output control unit 105, the output unit 106, the drive system control unit 107, and the drive system 108 constitute an actuator group 113 and correspond to the actuator group 13 including the actuators 13a-1 to 13a-n in FIG. .

In this embodiment, the drive system control unit 107 and the drive system system (actuator group 13) function as a drive unit.

The storage unit 109 includes, for example, a magnetic storage device such as ROM (Read Only Memory), RAM (Random Access Memory), and HDD (Hard Disc Drive), a semiconductor storage device, an optical storage device, a magneto-optical storage device, and the like. . The storage unit 109 stores various programs and data used by each unit of the mobile control system 100. For example, the storage unit 109 is a map data such as a three-dimensional high-accuracy map such as a dynamic map, a global map that is less accurate than a high-accuracy map and covers a wide area, and a local map that includes information around a moving object. Remember.

The autonomous movement control unit 110 performs control related to autonomous movement such as automatic driving or driving support. Specifically, for example, the autonomous movement control unit 110 aims to realize a function of collision avoidance or impact mitigation of a moving object, follow-up movement based on the distance between moving objects, movement speed maintaining movement, or collision warning of the moving object. Coordinated control is performed. Further, for example, the autonomous movement control unit 110 performs cooperative control for the purpose of autonomous movement that moves autonomously without depending on the operation of the operator / user.

The autonomous movement control unit 110 corresponds to the information processing apparatus according to the present embodiment, and includes hardware necessary for a computer such as a CPU, a RAM, and a ROM. The information processing method according to the present technology is executed when the CPU loads a program according to the present technology recorded in advance in the ROM into the RAM and executes the program.

The specific configuration of the autonomous movement control unit 110 is not limited, and a device such as PLD (Programmable Logic Device) such as FPGA (Field Programmable Gate Array) or other ASIC (Application Specific Specific Integrated Circuit) may be used.

2, the autonomous movement control unit 110 includes a detection unit 131, a self-position estimation unit 132, a situation analysis unit 133, a planning unit 134, and an operation control unit 135. Among these, the detection part 131, the self-position estimation part 132, and the condition analysis part 133 comprise the recognition process part 121, and respond | correspond to the recognition process part 14 of FIG. Moreover, the plan part 134 comprises the action plan process part 122, and respond | corresponds to the action plan process part 15 of FIG. Further, the operation control unit 135 constitutes the behavior control processing unit 123 and corresponds to the behavior control processing unit 16 of FIG.

The detecting unit 131 detects various information necessary for controlling autonomous movement. The detection unit 131 includes a mobile body external information detection unit 141, a mobile body internal information detection unit 142, and a mobile body state detection unit 143.

The mobile object external information detection unit 141 performs a process of detecting information outside the mobile object based on data or signals from each part of the mobile object control system 100. For example, the mobile object external information detection unit 141 performs detection processing, recognition processing, tracking processing, and distance detection processing for an object around the mobile object. Examples of objects to be detected include moving objects, people, obstacles, structures, roads, traffic lights, traffic signs, road markings, and the like. In addition, for example, the mobile object external information detection unit 141 performs an environment detection process around the mobile object. The surrounding environment to be detected includes, for example, weather, temperature, humidity, brightness, road surface condition, and the like. The moving body external information detection unit 141 supplies data indicating the detection processing result to the self-position estimation unit 132, the map analysis unit 151 of the situation analysis unit 133, the situation recognition unit 152, the operation control unit 135, and the like. .

The mobile body internal information detection unit 142 performs a process of detecting information inside the mobile body based on data or signals from each part of the mobile body control system 100. For example, the mobile body internal information detection unit 142 performs driver authentication processing and recognition processing, driver state detection processing, passenger detection processing, environment detection processing inside the mobile body, and the like. The state of the driver to be detected includes, for example, physical condition, arousal level, concentration level, fatigue level, gaze direction, and the like. Examples of the environment inside the moving object to be detected include temperature, humidity, brightness, smell, and the like. The mobile object internal information detection unit 142 supplies data indicating the result of the detection process to the situation recognition unit 152 of the situation analysis unit 133, the operation control unit 135, and the like.

The moving body state detection unit 143 performs a state detection process of the moving body based on data or signals from each part of the moving body control system 100. The state of the mobile object to be detected includes, for example, speed, acceleration, steering angle, presence / absence and content of abnormality, driving operation state, power seat position and tilt, door lock state, and other mobile body mounting The status of the device is included. The moving body state detection unit 143 supplies data indicating the result of the detection process to the situation recognition unit 152 of the situation analysis unit 133, the operation control unit 135, and the like.

The self-position estimation unit 132 is based on data or signals from each part of the mobile control system 100 such as the mobile external information detection unit 141 and the situation recognition unit 152 of the situation analysis unit 133. Etc. are estimated. In addition, the self-position estimation unit 132 generates a local map (hereinafter referred to as a self-position estimation map) used for self-position estimation as necessary. The self-position estimation map is, for example, a highly accurate map using a technique such as SLAM (SimultaneousultLocalization and Mapping). The self-position estimation unit 132 supplies data indicating the result of the estimation process to the map analysis unit 151 of the situation analysis unit 133, the situation recognition unit 152, and the like. In addition, the self-position estimating unit 132 stores the self-position estimating map in the storage unit 109.

Furthermore, the self-position estimation unit 132 accumulates time-series information supplied in time series in the database based on the detection result supplied from the sensor group 112, and based on the accumulated time-series information, Is output as the time-series information self-position. Further, the self-position estimation unit 132 estimates the self-position based on the current detection result supplied from the sensor group 112, and outputs it as the current information self-position. Then, the self-position estimation unit 132 outputs the self-position estimation result by integrating or switching the time-series information self-position and the current information self-position. Furthermore, the self-position estimation unit 132 detects the posture of the moving body 10 based on the detection result supplied from the sensor group 112, detects a change in the posture, changes the self-position greatly, and the time-series information self When the position estimation accuracy is considered to be lowered, the self-position is estimated only from the current information self-position. In addition, for example, when the moving body 10 is mounted on another moving body and moves, the self-position estimation unit 132 changes the posture of the moving body 10 based on the detection result supplied from the sensor group 112. Even if it is not detected, since the self-position changes greatly, it is assumed that the estimation accuracy of the time-series information self-position is lowered, and the self-position is estimated only from the current information self-position. For example, the moving body 10 may be a vehicle and mounted on a car ferry boat to move. By doing this, the self-position is estimated from only the current information self-position even when there is a change in posture that cannot be predicted in advance and the self-position changes greatly regardless of the influence of external force. Therefore, the self position can be estimated with a predetermined accuracy.

The situation analysis unit 133 performs analysis processing of the moving body and the surrounding situation. The situation analysis unit 133 includes a map analysis unit 151, a situation recognition unit 152, and a situation prediction unit 153.

The map analysis unit 151 uses various data or signals from each part of the mobile control system 100 such as the self-position estimation unit 132 and the mobile external information detection unit 141 as necessary, and stores various data stored in the storage unit 109. The map is analyzed, and a map including information necessary for the autonomous movement process is constructed. The map analysis unit 151 supplies the constructed map to the situation recognition unit 152, the situation prediction unit 153, the route plan unit 161, the action plan unit 162, the action plan unit 163, and the like of the plan unit 134.

The situation recognition unit 152 is a part of the mobile body control system 100 such as a self-position estimation unit 132, a mobile body external information detection unit 141, a mobile body internal information detection unit 142, a mobile body state detection unit 143, and a map analysis unit 151. Based on the data or signal from, the recognition process of the situation regarding a moving body is performed. For example, the situation recognition unit 152 performs recognition processing such as the situation of the moving body, the situation around the moving body, and the situation of the driver of the moving body. In addition, the situation recognition unit 152 generates a local map (hereinafter referred to as a situation recognition map) used for recognition of the situation around the moving object, as necessary. The situation recognition map is, for example, an occupation grid map (OccupancyccMap Map), a road map (Lane Map), or a point cloud map (Point Cloud Map).

The situation of the moving body to be recognized includes, for example, the position, posture, movement (for example, speed, acceleration, moving direction, etc.) of the moving body, presence / absence and contents of the abnormality. The situation around the moving object to be recognized includes, for example, the type and position of the surrounding stationary object, the type and position of the surrounding moving object (for example, speed, acceleration, moving direction, etc.), the surrounding road Configuration, road surface conditions, ambient weather, temperature, humidity, brightness, etc. are included. The state of the driver to be recognized includes, for example, physical condition, arousal level, concentration level, fatigue level, line of sight movement, and driving operation.

The situation recognition unit 152 supplies data indicating the result of recognition processing (including a situation recognition map as necessary) to the self-position estimation unit 132, the situation prediction unit 153, and the like. Further, the situation recognition unit 152 stores the situation recognition map in the storage unit 109.

The situation prediction unit 153 performs a process for predicting a situation related to the moving body based on data or signals from each part of the moving body control system 100 such as the map analysis unit 151 and the situation recognition unit 152. For example, the situation prediction unit 153 performs prediction processing such as the situation of the moving body, the situation around the moving body, and the situation of the driver.

The situation of the mobile object to be predicted includes, for example, the behavior of the mobile object, the occurrence of an abnormality, and the movable distance. The situation around the moving object to be predicted includes, for example, the behavior of the moving object around the moving object, the change in the signal state, the change in the environment such as the weather, and the like. The situation of the driver to be predicted includes, for example, the behavior and physical condition of the driver.

The situation prediction unit 153 supplies the data indicating the result of the prediction process and the data from the situation recognition unit 152 to the route planning unit 161, the action planning unit 162, the action planning unit 163, and the like of the planning unit 134.

The route planning unit 161 plans a route to the destination based on data or signals from each part of the mobile control system 100 such as the map analysis unit 151 and the situation prediction unit 153. For example, the route planning unit 161 sets a route from the current position to the designated destination based on the global map. In addition, for example, the route planning unit 161 changes the route as appropriate based on conditions such as traffic jams, accidents, traffic restrictions, construction, and the physical condition of the driver. The route planning unit 161 supplies data indicating the planned route to the action planning unit 162 and the like.

Based on data or signals from each part of the mobile control system 100 such as the map analysis unit 151 and the situation prediction unit 153, the action plan unit 162 can safely route the route planned by the route plan unit 161 within the planned time. Plan the behavior of the moving body to move to. For example, the action planning unit 162 performs plans such as start, stop, traveling direction (for example, forward, backward, left turn, right turn, direction change, etc.), moving speed, and overtaking. The behavior planning unit 162 supplies data indicating the planned behavior of the moving body to the motion planning unit 163 and the like.

More specifically, the action plan unit 162 generates, as action plan candidates, action plan candidates of moving bodies for safely moving within the planned time for each route planned by the route plan unit 161. To do. More specifically, the action planning unit 162 divides the environment into a grid, for example, A * algorithm (A star search algorithm) that optimizes arrival determination and route weight to generate the best path, road center Generating action plan candidates with Lane algorithm that sets the route according to the line and RRT (Rapidly-exploring Random Tree) algorithm that stretches while properly pruning the path from the self position to the place where it can reach incrementally .

The motion planning unit 163 is based on data or signals from each part of the mobile control system 100 such as the map analysis unit 151 and the situation prediction unit 153, and the motion planning unit 162 realizes the behavior planned by the behavior planning unit 162. Plan for action. For example, the motion planning unit 163 performs planning such as acceleration, deceleration, and movement trajectory. The motion planning unit 163 supplies data indicating the planned motion of the moving body to the motion control unit 135 and the like.

The operation control unit 135 controls the operation of the moving object.

More specifically, the operation control unit 135 detects collision, contact, or danger zone based on the detection results of the mobile body external information detection unit 141, the mobile body internal information detection unit 142, and the mobile body state detection unit 143. Detects emergency situations such as approach, driver abnormality, and moving body abnormality. When the occurrence of an emergency situation is detected, the operation control unit 135 plans the operation of the moving body to avoid an emergency situation such as a sudden stop or a sudden turn.

Also, the operation control unit 135 performs acceleration / deceleration control for realizing the operation of the moving object planned by the operation planning unit 163. For example, the operation control unit 135 calculates a control target value of a driving force generator or a braking device for realizing planned acceleration, deceleration, or sudden stop, and drives a control command indicating the calculated control target value. This is supplied to the system control unit 107.

The motion control unit 135 performs direction control for realizing the motion of the moving body planned by the motion planning unit 163. For example, the operation control unit 135 calculates a control target value of the steering mechanism for realizing the moving trajectory or the sudden turn planned by the operation planning unit 163, and outputs a control command indicating the calculated control target value to the drive system control unit It supplies to 107.

[Judgment of obstacles]
The obstacle determination process by the autonomous movement control unit 110 will be described. FIG. 3 is a schematic diagram illustrating an appearance of a robot 20 that is an example of the moving body 10. FIG. 4 is a block diagram illustrating a functional configuration example for executing an obstacle determination process.

As shown in FIG. 3, in the present embodiment, as the robot 20, a quadruped walking type robot having an articulated leg 21 is taken as an example. In FIG. 3, the illustration of the multi-joint structure is simplified.

A distance sensor 25 (not shown in FIG. 3) is disposed on the front side of the head 22 of the robot 20, and it is possible to measure the distance to an object existing in the measurement range M extending on the front side. ing. In this embodiment, LiDAR is used as the distance sensor 25, and the distance to the object existing in the measurement range M is acquired as three-dimensional point cloud data. The shape within the measurement range M can be determined from the three-dimensional point cloud data.

As the distance sensor 25, for example, other sensors such as a laser distance sensor, an ultrasonic sensor, a radar, and a sonar may be used. For example, if it is possible to determine how far the pixel of the image acquired by the imaging apparatus is present from the robot 20, stereo matching using a stereo camera, distance measurement using an IR camera, laser range finder Any type of sensor may be used. Further, any sensor that can determine the shape within the measurement range M may be used.

In FIG. 3, a measurement range M is set on the front side which is a part of the periphery of the robot 20. However, the present invention is not limited to this, and an arbitrary range around the robot 20 can be set as the measurement region D. For example, it is possible to set the entire circumference of 360 degrees around the robot 20 as the measurement range M, for example. A distance sensor 25 is disposed at a position serving as a base point of the measurement range M.

In the present embodiment, the distance sensor 25 corresponds to a sensor that can detect the peripheral information of the robot 20. The three-dimensional point cloud data in the measurement range M corresponds to the peripheral information of the robot 20 and shape data related to the periphery of the robot 20.

As shown in FIG. 4, the robot 20 has a height position sensor 26 (not shown in FIG. 3). The height position sensor 26 detects information related to the height position of the distance sensor 25. The height position of the distance sensor 25 is typically calculated based on a predetermined reference position. That is, the amount of displacement in the height direction from the reference position is calculated as the height position.

For example, the relative position from the floor surface 1 may be calculated using the position of the floor surface (ground) 1 on which the robot 20 is placed as a reference position. Alternatively, the surface of another object that actually exists such as the ceiling surface 2 (see FIG. 5 and the like) may be adopted as the reference position.

Alternatively, when the robot 20 is in a predetermined state (predetermined posture), the height position of the distance sensor 25 calculated in the reference state is set as the reference position. Then, the relative position from the reference position may be calculated as the height position of the distance sensor 25. Which state of the robot 20 is set as the reference state may be arbitrarily set. For example, the initial state of the robot 20 arranged on the floor 1 and the standard state of the robot 20 can be set as the reference state.

As the height position sensor 26, for example, a pressure sensor (atmospheric pressure sensor) is used. However, the relative position from the floor surface 1 may be calculated using the Doppler effect of the ultrasonic sensor. It is also possible to calculate the height position by integrating the detection results of the acceleration sensor or the like. The information on the height position includes various information that can calculate the height position, and includes, for example, a detection signal included in the output result of the sensor. The information on the height position includes information on the calculated height position itself.

Further, as shown in FIG. 4, the robot 20 has an internal sensor 27 (not shown in FIG. 3). The internal sensor 27 is a generic name for an acceleration sensor, a gyro sensor, an inertial measurement device (IMU), a geomagnetic sensor, and the like, and can detect the acceleration, angle, angular velocity, geomagnetic direction, and the like of the robot 20.

In the present embodiment, the distance sensor 25, the height position sensor 26, and the inner world sensor 27 are included in the sensor group 11 (112) shown in FIGS.

Further, as shown in FIG. 4, the robot 20 includes a height position calculation unit 30, a posture calculation unit 31, a determination region calculation unit 32, and an obstacle determination unit 33. These blocks are configured in the autonomous movement control unit 110 corresponding to the information processing apparatus according to the present embodiment. Typically, it is configured as a part of the recognition processing unit 14 shown in FIG. 1 and the recognition processing unit 121 shown in FIG. Of course, it is not limited to this.

FIG. 5 is a flowchart showing an example of an obstacle determination process. 6 to 9 are diagrams for explaining each step shown in FIG. By executing the processing shown in FIG. 5, it is possible to determine whether there is an obstacle around the robot 20. The cycle for executing the flow is not limited and may be set arbitrarily.

The height position calculation unit 30 calculates the height position of the distance sensor 25 based on the detection result of the height position sensor 26 (step 101). The determination area calculation unit 32 calculates the determination area D based on the calculated height position of the distance sensor 25 (step 102).

The determination area D is an area for determining the situation around the robot 20, and is an area that serves as an identification reference when executing an obstacle determination process. In FIGS. 3 and 6 to 9, the area of the space illustrated in gray is the determination area D.

In the example shown in FIGS. 3 and 6 to 9, a range of a substantially quadrangular pyramid shape having the apex at the front side of the head 22 of the robot 20 where the distance sensor 25 is arranged is illustrated as the measurement range D. . The determination area D is calculated as an area included in the measurement range M.

In the present embodiment, the determination area D is defined by the first identification surface 35 set on the floor surface 1 side and the second identification surface 36 set on the ceiling surface 2 side. In other words, in the measurement range M, a space area from the first identification surface 35 to the second identification surface 36 is set as the determination region D. The first and second identification surfaces 35 and 26 correspond to first and second determination surfaces.

As schematically shown in FIG. 6, a sensor coordinate system is set with the position of the distance sensor 25 as the origin and the direction of the detection axis L (detection direction) of the distance sensor 25 as the axial direction (Y-axis in FIG. 6). The Each axial direction can be calculated by the internal sensor 27. The method for setting the sensor coordinate system is not limited. The first and second identification surfaces 35 and 36 are set based on the sensor coordinate system.

FIG. 6 illustrates a state (attitude) in which the detection axis L of the distance sensor 25 extends in the horizontal direction toward the front side. In the present embodiment, this state is the reference state, and the height position H0 of the distance sensor 25 is the reference position.

The determination area calculation unit 32 sets the first and second identification surfaces 35 and 36 to be parallel to the XY plane (that is, the horizontal plane) based on the sensor coordinate system. A region sandwiched between the first and second identification surfaces 35 and 36 is calculated as a determination region D. Hereinafter, the determination area D in the reference state will be described as the reference determination area D0.

As shown in FIG. 6, in the reference state, the first identification surface 35 is set at a position higher than the floor surface 1 by an offset h _floor (hereinafter referred to as hf). The second identification surface 36 is set at a position lower than the ceiling surface 2 by an offset h _ceiling (hereinafter referred to as hc). The positions of the floor surface 1 and the ceiling surface 2 can be calculated by the internal sensor 27.

The specific values of the offsets hf and hc are not limited and may be set as appropriate. For example, by setting the distance sensor 25 to be larger than the maximum error amount, it is possible to improve the obstacle determination accuracy.

When the height of an object to be determined as an obstacle is specified, the offset hf is set at a position lower than the specified height. When the height of an object that does not need to be determined as an obstacle is specified, the offset hf is set at a position higher than the specified height. For example, the offset hf may be set according to a height that cannot be overcome by the robot 20, a height that can be sufficiently overcome, and the like.

Similarly, when the height of the object determined as an obstacle from the ceiling surface 2 is defined on the ceiling surface 2 side, the offset hc is set at a position higher than the defined height. When the height from the ceiling surface 2 of an object that does not need to be determined as an obstacle is specified, the offset hc is set at a position lower than the specified height. For example, the offset hc may be set according to the maximum height of the head 22 of the robot 20 during walking.

Thus, typically, the heights of the first and second identification surfaces 35 and 36 are set based on the moving environment, the performance of the robot 20, and the like so as to be advantageous for autonomous movement. For example, the heights of the first and second identification surfaces 35 and 36 are set so that an object to be avoided in movement can be extracted as an obstacle. Of course, the first identification surface 35 may be set at a position substantially equal to the position of the floor surface 1, and the first identification surface 36 may be set at a position substantially equal to the ceiling surface 2 (both offsets hf and hc are substantially zero). ).

Note that when the calculation of the first and second identification surfaces 35 and 36 in the reference state (calculation of the reference determination area D0) is executed, the process may be temporarily executed with a high calculation amount and with high accuracy. Thereby, the reference determination area D0 can be set with high accuracy. The setting of the reference determination area D0 may be executed by a user operation or may be automatically executed.

The obstacle determination unit 33 acquires three-dimensional point cloud data detected by the distance sensor 25 (step 103). The obstacle determination unit 33 determines an obstacle based on the calculated determination region D and the detected three-dimensional point cloud data (step 104).

The obstacle determination unit 33 determines an obstacle based on the relationship between the three-dimensional point cloud data and the determination area D. Specifically, it is determined whether or not an obstacle exists by determining whether or not the point data included in the three-dimensional point cloud data is included in the determination region D.

As shown in FIG. 6, for example, points included in the determination area D (D0) are determined as points constituting an obstacle. Then, an object including a point constituting the obstacle is determined as the obstacle 3. In the example shown in FIG. 6, the object 4 a existing on the floor surface 1 and the object 4 b installed on the ceiling surface 2 are both determined as the obstacle 3.

That is, in this embodiment, the three-dimensional point cloud data obtained from the distance sensor 25 is filtered based on the first and second identification surfaces 35 and 26. And when at least one part is contained in the determination area | region D (D0), it determines with the obstruction 3. FIG. Note that only points included in the determination region D (D0) may be determined as the obstacle 3.

When it is determined that the obstacle 3 exists, for example, an avoidance operation such as detour or stop, and output of a warning sound or a warning message are executed. These processes are executed, for example, by the cooperation of the action plan processing unit 15 and the action control processing unit 16 illustrated in FIG. Moreover, the situation analysis unit 133, the planning unit 134, and the operation control unit 135 illustrated in FIG. In the present embodiment, these blocks correspond to a drive control unit that controls the drive unit based on the determination result by the determination unit.

In the present embodiment, the height position calculation unit 30 functions as an acquisition unit that acquires information about the height position of the sensor that can detect the peripheral information of the moving object. The posture calculation unit 31 functions as an acquisition unit that acquires information regarding the tilt of the sensor. The attitude of the sensor will be described later. The determination region calculation unit 32 functions as a calculation unit that calculates a determination region for determining the situation around the moving body based on the acquired information on the height position of the sensor. The obstacle determination unit 33 functions as a determination unit that determines the situation around the moving body based on the calculated determination region and the peripheral information detected by the sensor.

7 and 8 are diagrams illustrating an example in which the leg 21 having a multi-joint structure is driven and the robot 20 moves. Four legs spread back and forth, and the height position of the head 22 of the robot 20, that is, the height position of the distance sensor 25 is lowered. The height position of the distance sensor 25 in this state is H1, and the amount of variation from the reference position H0 is Δt. As shown in FIGS. 7 and 8, the height position of the measurement range M is also lowered by the amount of variation Δt.

As shown in FIG. 7, it is assumed that a determination area D ′ similar to the reference determination area D0 shown in FIG. 6 is set in the sensor coordinate system based on the height position H1 of the distance sensor 25. That is, it is assumed that the plane defined by the same plane equation is set as the first and second identification surfaces 35 ′ and 36 ′. Then, the determination area D ′ and the first and second identification surfaces 35 ′ and 36 ′ are positions lower by the variation amount Δt than the reference determination area D0, the first and second identification surfaces 35 and 36 shown in FIG. Set to

As a result, as shown in FIG. 7, the first identification surface 35 ′ becomes lower than the floor surface 1, and the floor surface 1 is included in the determination region D ′. As a result, the floor surface 1 is determined as the obstacle 3. In addition, an object that can be traversed and should be ignored may be determined as the obstacle 3.

In addition, the second identification surface 36 ′ is significantly lower than the ceiling surface 2, and the object 4b existing on the ceiling surface 2 deviates from the determination region D ′. As a result, the object 4b that should be determined as an obstacle cannot be seen, and an obstacle is lost.

As a result, for example, an avoidance operation such as sudden braking is inadvertently performed, and proper autonomous movement is hindered. Further, the head 22 may collide with an object and the robot 20 may be damaged.

As shown in FIG. 8, in the obstacle determination process according to the present embodiment, in step 102, the determination region D is calculated based on the height position H1 of the distance sensor 25. Specifically, the height position of the determination region D is changed according to the change in the height position of the distance sensor 25.

In this embodiment, the determination area D is calculated so that the height position is the same as the height position of the reference determination area D0 with reference to the reference determination area D0 shown in FIG. That is, the first identification surface 35 is calculated so as to have the same height position as the height position of the first identification surface 35 in the reference determination region D0. Similarly, the second identification surface 36 is calculated so as to have the same height position as the height position of the second identification surface 36 in the reference determination region D0.

Therefore, as shown in FIG. 8, the first identification surface 35 is set at a position higher than the floor surface 1 by the offset hf. The second identification surface 36 is set at a position lower than the ceiling surface 2 by the offset hc. The plane expression of the first and second identification surfaces 35 and 36 is different from the first and second identification surfaces 35 and 36 in the reference state.

Thus, compared with the state shown in FIG. 7, the first and second identification surfaces 35 and 36 are offset upward along the vertical direction by the amount of variation Δt of the distance sensor 25. Thereby, in the obstacle determination process in step 104, the

objects

4a and 4b can be appropriately determined as the obstacle 3 as in the reference state shown in FIG. As a result, the influence of the swing of the distance sensor 25 in the height direction is sufficiently prevented, and an object that does not obstruct the movement, such as the floor surface 1 and the ceiling surface 2, and an object that obstructs the movement (obstacle 3). Can be identified.

Further, since the height position of the determination region D (first and second identification surfaces 35 and 36) may be changed based on the height position of the distance sensor 25, a complicated algorithm is not required, and the calculation amount is small. It is possible to easily determine the obstacle 3.

FIG. 9 is a diagram schematically illustrating another example of changing the height position of the determination region D according to the variation Δt. For example, when the measurement range M is sufficiently large, it is possible to change only the height position while maintaining the shape of the determination region D. That is, as shown in FIG. 9, when the height position of the head 22 (the height position of the distance sensor 25) is lowered, it is assumed that the reference determination region D0 is included in the measurement range M. In this case, the reference determination area D0 may be calculated as the determination area D as it is. This is processing that can be said to have changed the height position of the determination region D in accordance with the fluctuation amount Δt.

As shown in FIG. 4, in the present embodiment, the posture calculation unit 31 can calculate the posture of the robot 20 based on the detection result of the internal sensor 27. In the present embodiment, the inclination of the distance sensor 25 (the inclination of the head 22) is detected as the posture of the robot 20.

Specifically, the inclination of the detection axis L of the distance sensor 25 and the rotation angle about the detection axis L are calculated as the inclination of the distance sensor 25. That is, when the X axis schematically shown in FIG. 6 is the pitch axis, the Y axis (detection axis) is the roll axis, and the Z axis is the yaw axis, the pitch angle, roll angle, and yaw angle are the inclinations of the distance sensor 25. Is calculated as

The inclination of the distance sensor 25 is not limited to these parameters. Any parameter that defines the relative posture with the floor surface 1 can be calculated as the inclination of the distance sensor 25. Hereinafter, the detection axis L of the distance sensor 25 may be described as the position reference axis of the determination region D.

In the calculation process of the determination area D in step 102 shown in FIG. 4, the determination area D may be calculated based on the inclination of the distance sensor 25 in addition to the height position of the distance sensor 25. In this case, a step of acquiring the inclination of the distance sensor 25 is added.

10 to 12 show the case where the height position of the head 22 (the height position of the distance sensor 25) of the robot 20 is low and the inclination of the head 22 (inclination of the distance sensor 25) varies from the horizontal direction. It is a figure which shows an example. 10 to 12, the head 22 (distance sensor 25) is inclined downward from the horizontal direction (pitch angle varies).

As shown in FIGS. 10 to 12, the measurement range M is lowered by the amount of fluctuation Δt in the height direction, and is inclined downward by the amount of inclination Δθ with respect to the horizontal direction. The tilt amount Δθ can also be referred to as a posture displacement Δθ.

As shown in FIG. 10, it is assumed that a determination area D ′ similar to the reference determination area D0 shown in FIG. 6 is set in the sensor coordinate system based on the height position H2 of the distance sensor 25. In this case, the first and second identification surfaces 35 ′ and 36 ′ are also lowered by the variation amount Δt and further tilted downward by the tilt amount Δθ.

As a result, as shown in FIG. 10, the floor surface 1 is included in the determination region D ′ and is determined as an obstacle. In addition, the object 4b existing on the ceiling surface 2 deviates from the determination area D ′, and an obstacle is lost.

As shown in FIG. 11, based on the inclination amount Δθ, the first and second identification surfaces 35 ″ and 36 ″ are corrected so that each is a horizontal plane, and the determination region D ″ is calculated. To do. Even in this case, the floor surface 1 is included in the determination region D ′ and is determined as an obstacle. In addition, the object 4b existing on the ceiling surface 2 deviates from the determination area D ′, and an obstacle is lost. That is, erroneous detection due to the fluctuation amount Δt in the height direction remains.

As shown in FIG. 12, the determination region D is calculated based on the height position H2 of the distance sensor 25 and the inclination of the distance sensor 25. That is, the height position and the inclination of the determination region D are changed according to the change in the height position and the inclination of the distance sensor 25. The inclination of the determination area D corresponds to the inclination of the position reference axis of the determination area D (the same axis as the detection axis L of the distance sensor 25).

For example, with reference to the reference determination area D0 shown in FIG. 6, the determination area D is set to have the same height position as the height position of the reference determination area D0 and the same inclination as the inclination of the reference determination area D0. Calculated.

That is, the first identification surface 35 is calculated so as to coincide with the height position and inclination of the first identification surface 35 in the reference determination area D0. Similarly, the second identification surface 36 is calculated so as to coincide with the height position and inclination of the second identification surface 36 in the reference determination region D0.

As a result, as shown in FIG. 12, the first identification surface 35 is set at a position higher than the floor surface 1 by the offset hf. The second identification surface 36 is set at a position lower than the ceiling surface 2 by the offset hc. The plane formula of the first and second identification surfaces 35 and 36 is different from the first and second identification surfaces 35 and 36 in the reference state.

Thus, compared with the state shown in FIG. 10, the first and second identification surfaces 35 and 36 are offset upward by the fluctuation amount Δt of the distance sensor 25, and the reverse rotation direction (−θ direction) by the inclination amount Δθ. ). Thereby, in the obstacle determination process in step 104, the

objects

4a and 4b can be appropriately determined as the obstacle 3 as in the reference state shown in FIG. As a result, the influence of the swing of the distance sensor 25 in the height direction can be sufficiently prevented, and the floor surface 1, the ceiling surface 2, and the obstacle 3 can be identified with high accuracy.

Further, since the height position and inclination of the determination region D (first and second identification surfaces 35 and 36) may be changed based on the height position of the distance sensor 25, a complicated algorithm is not required, and the amount of calculation is small. Thus, the obstacle 3 can be easily determined.

FIG. 13 is a diagram schematically showing another example of changing the height position and inclination of the determination region D according to the variation amount Δt and the inclination amount Δθ. For example, when the measurement range M is sufficiently large, the height position and inclination of the determination area D can be changed while the shape of the determination area D is maintained. That is, as shown in FIG. 13, when the height position and inclination of the head 22 (height position and inclination of the distance sensor 25) fluctuate, it is assumed that the reference determination region D0 is included in the measurement range M. . In this case, the reference determination area D0 may be calculated as the determination area D as it is. This is a process that can be said to have changed the height position and inclination of the determination region D in accordance with the fluctuation amount Δt.

Note that the calculation of the determination region D based on the height position and inclination of the distance sensor 25 is not limited to the case where the calculation is performed with the reference determination region D as a reference. Even when the calculation is based on the reference determination area D0, the calculation is not limited to the case where the determination area D is calculated so as to have the same height position and the same inclination as the reference determination area D.

For example, the size of the determination region D in the height direction may be corrected based on the height position of the distance sensor 25. For example, for the determination region D shown in FIG. 8, the size in the height direction, that is, the distance between the first and second identification surfaces 35 and 36 may be corrected according to the variation Δt in the height position. . For example, the correction amount for the determination region D is increased as the variation amount Δt increases. Thereby, the influence of the detection error of each sense can be suppressed. Whether the size of the determination region D in the height direction is to be increased or decreased is determined to be effective for autonomous movement according to the moving environment, the performance and use of the robot 20, and the safety design is realized. It may be set as appropriate.

Based on the inclination of the distance sensor 25, the size of the determination region D in the height direction may be corrected. For example, the correction amount for the determination region D is increased as the inclination amount Δθ is larger. Thereby, the influence of the detection error of each sense can be suppressed.

As described above, in the moving body control system 100 according to the present embodiment, the determination region D for determining the situation around the robot 20 is calculated based on the information regarding the height position of the distance sensor 25. As a result, the situation around the robot 20 can be easily and accurately determined, and the obstacle 3 can be determined.

In other words, by using this technology, an autonomous mobile robot that uses a distance sensor to recognize obstacles in the outside world can identify the floor / ceiling surface and obstacles even if the height / posture of the distance sensor changes during movement. Can be performed stably.

In order for autonomous mobile robots to move around obstacles, it is common to measure the environment with a distance sensor. The distance sensor allows the robot to know the distance to the external object centered on itself. A distance sensor generally measures the linear distance from an object using reflection of a wave phenomenon with straightness such as sound and light, so an object that becomes an obstacle to movement and a floor -Both objects that do not obstruct movement such as the ceiling surface will be detected. An autonomous mobile robot needs to distinguish obstacles from movement and floor / ceiling surfaces from signals obtained from distance sensors.

If the robot can always move while maintaining a posture parallel to the ground, it is easy to identify the floor / ceiling surface and obstacles. From the obtained sensor signal, only the information in the area surrounded by the plane of appropriate height fixed to the sensor coordinate system may be identified as an obstacle.

However, for mobile robots with feet, the distance sensor swings when the robot moves (walks), and its posture and height change with respect to the ground. In particular, a distance sensor corresponding to an “eye” in a robot is often installed at a high position in the robot body in order to take a wide field of view, and the position / posture is greatly moved by swinging accompanying movement.

In the identification method in which the obstacle determination is performed using the determination area fixed in the sensor coordinate system described above, there is a possibility of erroneous recognition for a sensor whose posture and height change. For example, in the case where the height of the sensor is lower than normal, the floor is erroneously recognized as an obstacle (see FIG. 7). Conversely, if the sensor position is higher than normal, the ceiling surface may be erroneously recognized as an obstacle. The same kind of problem occurs when the sensor is tilted in addition to the change in height (see FIGS. 10 and 11).

When a floor or ceiling is misrecognized as an obstacle while moving, it is necessary to bypass a place where it can be originally moved, and a robot that misrecognizes that an obstacle suddenly occurred in the vicinity may cause an unnecessary sudden stop. Leads to. Therefore, it has become very important to devise a new floor / ceiling surface-obstacle identification method that is not affected by changes in the position / posture of the distance sensor.

For example, a method of extracting a plane from a three-dimensional point group obtained from a distance sensor and recognizing an object other than the plane as an obstacle is conceivable. By extracting the floor / ceiling surface from only the sensor signal, the floor surface can be removed only from the signal without depending on the posture of the sensor with respect to the outside world. However, this method requires a complicated procedure for detecting the floor surface from the point cloud, and is difficult to apply to a small robot with a scarce computer resource.

A method of discriminating between the floor and the obstacle based on the reflected light intensity of the distance sensor can be considered. In a distance sensor that measures distance using reflection of light or the like, the reflection intensity of the obstacle directly facing is stronger than the reflection intensity of the floor / ceiling surface parallel to the sensor optical axis. This is a technique using this. However, with this method, the reflection intensity is affected by the degree of light scattering due to the surface properties of the object and the light absorption rate by the material, so the identification accuracy in an environment surrounded by objects of various materials is low. End up. In addition, when the distance sensor is greatly directed up and down and directly faces the floor surface, the reflection intensity from the floor surface is better than that of the obstacle, so this method cannot be used.

A method is conceivable in which the distance sensor output of the outside world when there is no obstacle is acquired in advance, and the difference compared with the current observation value is identified as an obstacle. However, this method has a problem in that it requires calculation to match the sensor signal acquired in advance and the coordinates of the current sensor output, and cannot be used in a case where an unknown area is to be searched.

That is, the above method increases the calculation cost and cannot cope with the height change of the distance sensor.

Small mobile robots do not have sufficient computer resources, and there is a need for a method that can identify floor / ceiling surfaces and obstacles with lower load. In particular, leg robots and the like need to reduce obstacle recognition due to changes in sensor height.

As described in the above embodiment, the present technology can be implemented only by coordinate comparison processing in a simple three-dimensional space as long as an inexpensive height sensor / attitude sensor is provided. Compared to high-load processing such as detection, it can be realized at low cost. Thus, the present technology can also be applied to a small object such as a domestic pet robot that has a limited calculation capability. In addition, this technology demonstrates robust identification capability against high-speed rocking of any three-dimensional sensor including height position and orientation by adding height position information from the height measurement unit. Is possible.

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

In the above, the determination area is defined by the first and second identification surfaces (determination surfaces). The determination area is not limited to this, and the determination area may be defined by one identification plane or three or more identification planes. For example, the case where only the 1st discriminating surface according to a floor surface is set, and the case where only the 2nd discriminating surface according to a ceiling surface is set up are mentioned. Further, the shape of the determination area is not limited. The determination area may be defined by a curved identification surface. Further, the shape of the determination region (the shape of the identification surface) may be set according to the shape of the floor surface or the ceiling surface. Note that the identification surface (determination surface) can also be said to be a threshold for determination.

In the above, the determination of the presence or absence of obstacles was performed as a determination of the surrounding situation. The present technology is not limited to r, and the present technology may also be applied to counting a predetermined object existing in the vicinity, detecting a change in the size of an object, and the like. That is, any determination process may be executed as a determination of the surrounding situation.

FIG. 14 is an external view showing a configuration example of a vehicle equipped with an automatic driving control unit according to an embodiment of the present technology. FIG. 14A is a perspective view illustrating a configuration example of the vehicle 290, and FIG. 1B is a schematic view when the vehicle 290 is viewed from above. The vehicle 290 has an automatic driving function capable of automatic traveling (autonomous movement) to a destination. The vehicle 290 is an example of a moving body.

The vehicle 290 includes various sensors 291 used for automatic driving. As an example, for example, FIG. 14A schematically illustrates an imaging device 292 and a distance sensor 293 that are directed to the front of the vehicle 290. The imaging device 292 and the distance sensor 293 function as an external sensor. FIG. 14B schematically shows a wheel encoder 294 that detects the rotation and the like of each wheel. The wheel encoder 294 functions as an internal sensor. In addition, various sensors 291 are mounted on the vehicle 290, and movement control of the vehicle 290 is performed based on the output from the sensor 291.

FIG. 15 is a block diagram illustrating a configuration example of the vehicle control system 200 that controls the vehicle 290. The vehicle control system 200 is a system that is provided in the vehicle 290 and performs various controls of the vehicle 290.

The input unit 201, data acquisition unit 202, communication unit 203, in-vehicle device 204, output control unit 205, output unit 206, drive system control unit 207, drive system system 208, storage unit 209, and automatic operation control unit shown in FIG. 210 includes an input unit 101, a data acquisition unit 102, a communication unit 103, a mobile internal device 104, an output control unit 105, an output unit 106, a drive system control unit 107, a drive system system 108, a storage unit 109, And a block corresponding to the autonomous movement control unit 110.

Further, the detection unit 231, the self-position estimation unit 232, the situation analysis unit 233, the planning unit 234, and the operation control unit 135 in the automatic driving control unit 210 illustrated in FIG. 15 are included in the autonomous movement control unit 110 illustrated in FIG. 2. It corresponds to the detection unit 131, the self-position estimation unit 132, the situation analysis unit 133, the planning unit 134, and the operation control unit 135.

Hereinafter, the difference from the autonomous movement control unit 110 shown in FIG. 2 will be mainly described. First, the data acquisition unit 202 may include an imaging device that images the driver, a biological sensor that detects the driver's biological information, a microphone that collects sound in the passenger compartment, and the like. The biometric sensor is provided, for example, on a seat surface or a steering wheel, and detects biometric information of a passenger sitting on the seat or a driver holding the steering wheel.

The body system control unit 280 controls the body system 281 by generating various control signals and supplying them to the body system 281. Further, the body system control unit 280 supplies a control signal to each unit other than the body system 281 as necessary, and notifies the control state of the body system 281 and the like.

The body system 281 includes various body-related devices mounted on the vehicle body. For example, the body system 281 includes a keyless entry system, a smart key system, a power window device, a power seat, a steering wheel, an air conditioner, and various lamps (for example, a head lamp, a back lamp, a brake lamp, a blinker, a fog lamp, etc.) Etc.

The traffic rule recognition unit 282 determines traffic rules around the vehicle 290 based on data or signals from each part of the vehicle control system 200 such as the self-position estimation unit 232, the vehicle outside information detection unit 241, and the map analysis unit 251. Perform recognition processing. By this recognition processing, for example, the position and state of signals around the vehicle 290, the contents of traffic restrictions around the vehicle 290, and the lanes that can travel are recognized. The traffic rule recognition unit 282 supplies data indicating the result of the recognition process to the situation prediction unit 253 and the like.

The operation control unit 235 controls the operation of the vehicle 290. The operation control unit 235 includes an emergency situation avoiding unit 283, an acceleration / deceleration control unit 284, and a direction control unit 285.

The emergency situation avoiding unit 283 is configured to detect collision, contact, approach to a dangerous zone, driver abnormality, vehicle 290 based on the detection results of the vehicle outside information detecting unit 241, the vehicle interior information detecting unit 242, and the vehicle state detecting unit 243. Detects emergency situations such as abnormalities. When the emergency avoidance unit 283 detects the occurrence of an emergency, the emergency avoidance unit 283 plans the operation of the vehicle 290 to avoid an emergency such as a sudden stop or a sudden turn. The emergency avoidance unit 283 supplies data indicating the planned operation of the vehicle 290 to the acceleration / deceleration control unit 284, the direction control unit 285, and the like.

The acceleration / deceleration control unit 284 performs acceleration / deceleration control for realizing the operation of the vehicle 290 planned by the operation planning unit 263 or the emergency situation avoiding unit 283. For example, the acceleration / deceleration control unit 284 calculates a control target value of a driving force generator or a braking device for realizing planned acceleration, deceleration, or sudden stop, and drives a control command indicating the calculated control target value. This is supplied to the system control unit 207.

The direction control unit 285 performs direction control for realizing the operation of the vehicle 290 planned by the operation planning unit 263 or the emergency situation avoiding unit 283. For example, the direction control unit 285 calculates the control target value of the steering mechanism for realizing the traveling track or the sudden turn planned by the motion planning unit 263 or the emergency situation avoiding unit 283, and the control indicating the calculated control target value The command is supplied to the drive system control unit 207.

The present technology can be applied to the vehicle 290 and the vehicle control system 200 having the above-described configuration. That is, it is possible to cause the vehicle control system 200 to function as an information processing apparatus according to the present technology and to execute a determination process for the situation around the vehicle 290 including determination of an obstacle.

In addition, the technology according to the present disclosure can be applied to various products. For example, the technology according to the present disclosure may be any kind of movement such as an automobile, an electric vehicle, a hybrid electric vehicle, a motorcycle, a bicycle, personal mobility, an airplane, a drone, a ship, a robot, a construction machine, and an agricultural machine (tractor). You may implement | achieve as an apparatus mounted in a body.

In the above embodiment, the information processing method according to the present technology including determination of an obstacle and the like is executed by the autonomous movement control unit mounted on the moving body. However, the information processing method according to the present technology may be executed by the cloud server. In this case, the cloud server operates as an information processing apparatus according to the present technology.

In addition, an information processing method and a program according to the present technology are executed by interlocking a computer mounted on a vehicle with another computer (cloud server) capable of communicating via a network or the like. A processing device may be constructed.

That is, the information processing method and the program according to the present technology can be executed not only in a computer system configured by 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 all the components are in the same housing. Accordingly, a plurality of devices housed in separate housings and connected via a network and a single device housing a plurality of modules in one housing are all systems.

The information processing method and the program according to the present technology by the computer system are executed when, for example, acquisition of information on the sensor height position, calculation of a determination region, determination of a surrounding situation, and the like are executed by a single computer, and This includes both cases where each process is executed by a different computer. The execution of each process by a predetermined computer includes causing another computer to execute a part or all of the process and acquiring the result.

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

Each structure such as a moving body (robot, vehicle), autonomous movement control unit, automatic driving control unit, etc. described with reference to each drawing, a control flow of the autonomous movement control unit, and the like are only one embodiment, and Any modification can be made without departing from the spirit of the invention. That is, any other configuration, algorithm, or the like for carrying out the present technology may be employed.

In the present disclosure, “same height position”, “same inclination”, “center”, “equal position”, “equal axis”, “parallel”, etc. are “substantially the same height position”, “substantially the same inclination”, “substantially the same”. ”Center”, “substantially equal position”, “substantially equal axis”, and “substantially parallel”. For example, a predetermined range (for example, ± 10%) based on “completely the same height position”, “completely the same inclination”, “completely center”, “completely equal position”, “completely equal axis”, “completely parallel”, etc. The range included in the range of (1) is also included.

Of the characteristic parts according to the present technology described above, it is possible to combine at least two characteristic parts. That is, the various characteristic parts described in each embodiment may be arbitrarily combined without distinction between the embodiments. The various effects described above are merely examples and are not limited, and other effects may be exhibited.

In addition, this technique can also take the following structures.
(1) an acquisition unit that acquires information about the height position of a sensor capable of detecting peripheral information of the moving body;
Based on the acquired information on the height position of the sensor, a calculation unit that calculates a determination region for determining a situation around the moving body;
An information processing apparatus comprising: a determination unit configured to determine a situation around the moving body based on the calculated determination region and the peripheral information detected by the sensor.
(2) The information processing apparatus according to (1),
The calculation unit determines whether there is an obstacle around the moving body.
(3) The information processing apparatus according to (1) or (2),
The acquisition unit acquires shape data related to the periphery of the moving body,
The determination unit determines a situation around the moving body based on a relationship between the detected shape data and the determination area.
(4) The information processing apparatus according to (3),
The acquisition unit acquires three-dimensional point cloud data related to the periphery of the moving object,
The determination unit determines a situation around the moving object by determining whether or not point data included in the three-dimensional point cloud data is included in the determination region.
(5) The information processing apparatus according to any one of (1) to (4),
The calculation unit changes a height position of the determination region according to a change in a height position of the sensor.
(6) The information processing apparatus according to any one of (1) to (5),
The calculation unit calculates one or more determination planes that define the determination region;
The one or more determination surfaces include at least one of a first determination surface corresponding to the ground and a second determination surface corresponding to a ceiling surface.
(7) The information processing apparatus according to (6),
The information processing apparatus, wherein the calculation unit changes a height position of at least one of the first determination surface and the second determination surface according to a change in a height position of the sensor.
(8) The information processing apparatus according to any one of (1) to (7),
The calculation unit calculates the determination region based on a predetermined reference determination region based on the acquired information on the height position of the sensor.
(9) The information processing apparatus according to (8),
The information processing apparatus calculates the determination region so that the calculation unit has the same height position as a height position of the reference determination region.
(10) The information processing apparatus according to any one of (1) to (9),
The information processing apparatus corrects a size of the calculated determination region in a height direction based on the acquired information on the height position of the sensor.
(11) The information processing apparatus according to any one of (1) to (10),
The acquisition unit acquires information on the tilt of the sensor,
The information processing apparatus that calculates the determination area based on information related to the tilt of the sensor.
(12) The information processing apparatus according to (11),
The calculation unit changes an inclination of the determination region according to a change in inclination of the sensor.
(13) Obtain information about the height position of the sensor that can detect the peripheral information of the moving body,
Based on the acquired information on the height position of the sensor, a determination region for determining the situation around the moving body is calculated,
An information processing method in which a computer system executes determination of a situation around the moving body based on the calculated determination area and the peripheral information detected by the sensor.
(14) obtaining information related to the height position of the sensor capable of detecting peripheral information of the moving body;
Calculating a determination region for determining a situation around the moving body based on the acquired information on the height position of the sensor;
A program for causing a computer system to execute a step of determining a situation around the moving body based on the calculated determination area and the peripheral information detected by the sensor.
(15) a drive unit;
A sensor capable of detecting surrounding information;
A detection unit for detecting information on a height position of the sensor;
A calculation unit for calculating a determination region for determining a surrounding situation based on the detected information on the height position of the sensor;
A determination unit for determining a surrounding situation based on the calculated determination region and the peripheral information detected by the sensor;
A moving body comprising: a drive control unit that controls the drive unit based on a determination result by the determination unit.
(16) The moving object according to (15),
The driving unit is a leg having a multi-joint structure.

D: Determination region D0: Reference determination region 1 ... Floor surface 2 ... Ceiling surface 3 ... Obstacle 10 ... Moving body 20 ... Robot 21 ... Leg 25 ... Distance sensor 26 ... Height position sensor 27 ... Inner world sensor 30 ... Position Calculation unit 31 ... Posture calculation unit 32 ... Determination region calculation unit 33 ... Obstacle determination unit 35 ... First identification surface 36 ... Second identification surface 100 ... Mobile body control system 200 ... Vehicle control system 290 ... Vehicle 293 ... Distance Sensor

Claims

An acquisition unit for acquiring information related to the height position of the sensor capable of detecting peripheral information of the moving object;
Based on the acquired information on the height position of the sensor, a calculation unit that calculates a determination region for determining a situation around the moving body;
An information processing apparatus comprising: a determination unit configured to determine a situation around the moving body based on the calculated determination region and the peripheral information detected by the sensor.
The information processing apparatus according to claim 1,
The calculation unit determines whether there is an obstacle around the moving body.
The information processing apparatus according to claim 1,
The acquisition unit acquires shape data related to the periphery of the moving body,
The determination unit determines a situation around the moving body based on a relationship between the detected shape data and the determination area.
The information processing apparatus according to claim 3,
The acquisition unit acquires three-dimensional point cloud data related to the periphery of the moving object,
The determination unit determines a situation around the moving object by determining whether or not point data included in the three-dimensional point cloud data is included in the determination region.
The information processing apparatus according to claim 1,
The calculation unit changes a height position of the determination region according to a change in a height position of the sensor.
The information processing apparatus according to claim 1,
The calculation unit calculates one or more determination planes that define the determination region;
The one or more determination surfaces include at least one of a first determination surface corresponding to the ground and a second determination surface corresponding to a ceiling surface.
The information processing apparatus according to claim 6,
The information processing apparatus, wherein the calculation unit changes a height position of at least one of the first determination surface and the second determination surface according to a change in a height position of the sensor.
The information processing apparatus according to claim 1,
The calculation unit calculates the determination region based on a predetermined reference determination region based on the acquired information on the height position of the sensor.
The information processing apparatus according to claim 8,
The information processing apparatus calculates the determination region so that the calculation unit has the same height position as a height position of the reference determination region.
The information processing apparatus according to claim 1,
The information processing apparatus corrects a size of the calculated determination region in a height direction based on the acquired information on the height position of the sensor.
The information processing apparatus according to claim 1,
The acquisition unit acquires information on the tilt of the sensor,
The information processing apparatus that calculates the determination area based on information related to the tilt of the sensor.
The information processing apparatus according to claim 11,
The calculation unit changes an inclination of the determination region according to a change in inclination of the sensor.
Get information about the height position of the sensor that can detect the surrounding information of the moving body,
Based on the acquired information on the height position of the sensor, a determination region for determining the situation around the moving body is calculated,
An information processing method in which a computer system executes determination of a situation around the moving body based on the calculated determination area and the peripheral information detected by the sensor.
Obtaining information related to the height position of a sensor capable of detecting peripheral information of the moving body;
Calculating a determination region for determining a situation around the moving body based on the acquired information on the height position of the sensor;
A program for causing a computer system to execute a step of determining a situation around the moving body based on the calculated determination area and the peripheral information detected by the sensor.
A drive unit;
A sensor capable of detecting surrounding information;
A detection unit for detecting information on a height position of the sensor;
A calculation unit for calculating a determination region for determining a surrounding situation based on the detected information on the height position of the sensor;
A determination unit for determining a surrounding situation based on the calculated determination region and the peripheral information detected by the sensor;
A moving body comprising: a drive control unit that controls the drive unit based on a determination result by the determination unit.
The moving body according to claim 15,
The driving unit is a leg having a multi-joint structure.