JP7227879B2 - Surrounding Observation System, Surrounding Observation Program and Surrounding Observation Method - Google Patents

Description

The present invention relates to a surroundings observation system, a surroundings observation program, and a surroundings observation method.

In the technical field of railways, there is known a technique for detecting obstacles in front of the vehicle in order to improve safety. For example, Patent Literature 1 discloses that "an obstacle is detected by using a short-distance photographing unit that photographs a short distance provided in a vehicle, a long-distance photographing unit that photographs a long distance, and a LIDAR that irradiates a short distance. A technique to the effect that "to do" is disclosed.

With this type of obstacle detection technology, it is technically difficult to distinguish passengers waiting safely on station platforms and maintenance personnel safely performing maintenance work near the tracks from obstacles.
Therefore, every time an object that is not an obstacle is erroneously detected, there are cases where the railway operation is hindered, such as an emergency stop of the vehicle.

As a technique for preventing this type of false detection, for example, Patent Document 2 discloses that "a vehicle position of a train is determined based on the correlation between a base video image taken in advance in front of the train and a reference image in front of the running train. A virtual construction gauge frame is set in advance for the base video image, and the difference between the base video image and the reference video image taken at the same vehicle position on different dates and times is detected only within the virtual construction gauge frame. detects only obstacles within the virtual building gauge frame.” is disclosed.

JP 2016-088183 A JP 2017-001638 A

In a system for detecting the vehicle position of a train as in Patent Document 2, it is desired to further improve the detection accuracy of the vehicle position.

SUMMARY OF THE INVENTION Accordingly, it is an object of the present invention to provide a surrounding observation technique that increases the accuracy of vehicle position detection.

In order to solve the above problems, one typical peripheral observation system of the present invention comprises a peripheral environment observation section and a position estimation section. The surrounding environment observation unit observes the positions of surrounding objects from the position of the vehicle traveling on the track, and outputs the result as an observation result. The position estimating unit stores map data created by observing positions of the object group in advance, and stores the position of the vehicle in the observation result in a state where the position of the vehicle is limited to the trajectory of the map data. and the map data, and the vehicle position is estimated based on the correlation.

The present invention provides a surrounding observation technique that enhances the detection accuracy of the vehicle position.

Problems, configurations, and effects other than those described above will be clarified by the following description of the embodiments.

FIG. 1 is a diagram showing the configuration of an orbital transportation system (including a peripheral observation system). FIG. 2 is a diagram showing the configuration of the self-localization system. FIG. 3 is a flow chart showing the overall operation of the surroundings observation system. FIG. 4 is a diagram showing an example of a sensor for observing the surrounding environment. FIG. 5 is a diagram showing the lateral boundaries of the monitoring area during traveling on a turning track. FIG. 6 is a flow chart showing the operation of the self-localization system. FIG. 7 is a diagram showing an example of the surrounding environment of a running vehicle. FIG. 8 is a diagram explaining detection of a rail track by the self-position estimation system. FIG. 9 is a diagram showing an example of surrounding environment observation data. FIG. 10 is a diagram for explaining vehicle attitude estimation by the self-position estimation system. FIG. 11 is a flow chart showing the operation of the vehicle driving control unit. FIG. 12 is a diagram showing an example of a monitoring area in a station section. FIG. 13 is a diagram showing an example of a monitoring area in a maintenance work section. FIG. 14 is a diagram showing scan matching (during scanning) in the case of an automobile. FIG. 15 is a diagram showing scan matching (scan completion) in the case of an automobile. FIG. 16 is a diagram showing scan matching (during scanning) of the embodiment. FIG. 17 is a diagram showing scan matching (scan completion) of the embodiment.

Embodiments will be described below with reference to the drawings.

<<Configuration of Embodiment 1>>
FIG. 1 is a diagram showing the configuration of a rail transportation system 100 (including a peripheral observation system 100A) of Example 1. As shown in FIG.

The rail transportation system 100 includes a vehicle 102 and a surrounding observation system 100A.

The vehicle 102 is a vehicle that transports passengers and cargo traveling along the track. The vehicle 102 is composed of a vehicle driving control section 105 and a vehicle driving section 106 . This vehicle 102 is provided with obstacle information 161 from the surroundings observation system 100A.

The vehicle driving control unit 105 has an internal function of detecting the position and speed of the vehicle 102 . Vehicle operation control unit 105 generates drive command 142 so that this position and speed follow the target running pattern. The target travel pattern is based on the previously known acceleration/deceleration of the vehicle 102 and the speed limit of the travel section. Then, the vehicle driving control unit 105 calculates the allowable maximum speed of the vehicle 102 from the position of the vehicle 102 and the maximum deceleration of the vehicle 102, and reflects it in the basic target travel pattern. An example of such a vehicle operation control unit 105 is an ATO device (automatic train operation device).

The vehicle drive unit 106 drives the vehicle 102 based on the given drive command 142 . Examples of specific devices for the vehicle drive unit 106 include an inverter, a motor, a friction brake, and the like.

On the other hand, the surroundings observation system 100A includes a surroundings environment observation unit 107 , a self-position estimation system 101 and an obstacle detection system 103 .

The surrounding environment observation unit 107 is a sensor that is installed in front of the vehicle 102 and acquires the position, shape, color, reflection intensity, and the like of objects around the vehicle 102 . For example, the surrounding environment observation unit 107 is a sensor such as a camera, LIDAR (Laser Imaging Detection and Ranging), laser radar, or millimeter wave radar.

Self-position estimation system 101 acquires surrounding environment observation data 151 from surrounding environment observation unit 107 , estimates the vehicle position and orientation of vehicle 102 , and outputs position/attitude information 153 .

The obstacle detection system 103 includes a detection range setting database 108 , a monitoring area setting processing section 109 , a detection target information database 110 , a side boundary monitoring section 111 , a front boundary monitoring section 112 and an obstacle detection section 113 .

The detection range setting database 108 stores the detection range 154 of the monitoring area in association with the position/orientation information 153 of the vehicle 102 . The detection range 154 includes range data based on the building gauge near the track, as well as information on non-detected areas such as the vicinity of station platforms and areas where maintenance work is performed.

The monitoring area setting processing unit 109 obtains a detection range 154 corresponding to the position/orientation information 153 by referring to the detection range setting database 108 for the position/orientation information 153 . The monitoring area setting processing unit 109 sequentially determines side boundaries 155 of the monitoring area based on the latest detection range 154 and sets them in the side boundary monitoring unit 111 . Also, the monitoring area setting processing unit 109 successively determines the front boundary 156 of the monitoring area based on the latest detection range 154 and sets it in the front boundary monitoring unit 112 .

The detection target information database 110 records information such as positions and reflectances of detection points (detection targets other than obstacles) as backgrounds observed in the monitoring area in association with vehicle positions and monitoring areas. The side boundary monitoring unit 111 and the front boundary monitoring unit 112 refer to the detection target information database 110 for the vehicle position and the monitoring area, and acquire information 157 and 158 regarding background detection points, respectively.

The side boundary monitoring unit 111 and the front boundary monitoring unit 112 use sensors such as cameras, LIDAR, laser radars, or millimeter wave radars to detect obstacles in areas set at the side boundaries and front boundaries of the monitoring area. have the function to Here, the side boundary monitoring unit 111 and the front boundary monitoring unit 112 may share the sensor of the surrounding environment observation unit 107 .

A monitoring result 159 of the side boundary monitoring unit 111 is transmitted to the obstacle detection unit 113 . Also, the monitoring result 160 of the front boundary monitoring unit 112 is transmitted to the obstacle detection unit 113 .

The obstacle information 161 from the obstacle detection unit 113 is transmitted to the vehicle 102 as an output of the surroundings observation system 100A.

FIG. 2 is a diagram showing the configuration of the self-localization system 101. As shown in FIG.

In the figure, the self-position estimation system 101 includes an observation data selection processing unit 114, a vehicle posture estimation processing unit 115, a surrounding environment data coordinate conversion processing unit 116, a surrounding environment map database 117, a 3D rail track database 118, and a scan matching self A position estimation unit 119 is provided.

Such a peripheral observation system 100A is composed of one or more computer systems including, for example, CPUs (Central Processing Units) and memories as hardware. Various functions of the peripheral observation system 100A are realized by the hardware executing the peripheral observation program. For part or all of this hardware, a dedicated device, general-purpose machine learning machine, DSP (Digital Signal Processor), FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit), PLD (Programmable Logic Device) etc. can be substituted. Also, by centralizing or distributing part or all of the hardware in a server on an external network and arranging it in the cloud, a plurality of peripheral observation systems 100A may be used in common via the network.

<<Overall operation of peripheral observation system 100A>>
FIG. 3 is a flowchart for explaining the overall operation of the surroundings observation system 100A.
In steps S201 to S205 shown in the figure, whether or not to instruct the vehicle 102 to stop is determined for each measurement cycle of the obstacle detection system 103. FIG.

Hereinafter, description will be made along the step numbers shown in FIG.

Step S<b>201 : The monitoring area setting processor 109 in the obstacle detection system 103 acquires the position/orientation information 153 calculated by the self-position estimation system 101 .

Step S202: The monitoring area setting processing unit 109 obtains the side boundary 155 and the front boundary 156 as boundaries of the monitoring area for monitoring obstacles by referring to the detection range setting database 108 for the position/orientation information 153 . For example, the left and right construction gauges of the track are set as side boundaries 155 of the obstacle monitoring area, and the stoppable distance of the vehicle is set as the front boundary 156 of the obstacle monitoring area.

Here, in order to quickly detect an obstacle on the boundary beyond the side boundary 155 and the front boundary 156, the side boundaries 155a and 155b and the front boundary 156 shown in FIG. A widened boundary detection area is set. This predetermined width takes into account the size and maximum movement speed of the obstacle expected to cross the boundary, and the sensing cycle of the side boundary monitoring unit 111 and the front boundary monitoring unit 112 (obstacle detection sensors). It is set to ensure a width that can be detected at least once when an object enters the boundary.

For example, in a station section, the predetermined width is narrowly set to several centimeters to several tens of centimeters (more specifically, 10 cm), assuming the size of passengers waiting on the platform and the maximum moving speed.
Further, for example, in the running section between stations (especially near railroad crossings), the predetermined width is set wide (for example, 1 m), assuming the size and maximum moving speed of a car or the like when it crosses. In this manner, the predetermined width of the boundary detection area is sequentially changed according to the vehicle position of the vehicle 102 .

Step S203: The side boundary monitoring unit 111 and the front boundary monitoring unit 112 monitor whether or not an obstacle has entered the track beyond the side boundary 155 and the front boundary 156, and use the monitoring results 159 and 160 as obstacles. It is given to the detection unit 113 .

As shown in FIG. 4, the boundary detection area of the left and right side boundaries 155a, 155b can be a rectangular area with a width of several tens of centimeters and a depth of more than 100 meters. In order to keep the rectangular area within the observation range, the detectors 201 and 202 of the side boundary monitoring unit 111 are two multi-layer LIDARs installed at high positions on the left and right sides of the vehicle 102 facing forward and downward. As the detectors 201, 201, one or a plurality of stereo cameras, millimeter wave radars, and laser rangefinders may be used. Alternatively, the sensor may be attached to the automatic pan head to scan the boundary detection area of the side boundary 155 .

Further, for example, the detector 203 of the front boundary monitoring unit 112 may be a monocular camera with a narrow angle of view, an infrared camera for dark field, or a stereo camera, considering that the boundary detection area of the front boundary 156 is far away. , millimeter-wave radar, multi-layer LIDAR, laser rangefinders, etc.

The detection results of these detectors 201 to 203 are compared with background detection points (detection targets other than obstacles) recorded in the detection target information database 110 . Based on this comparison, it is determined that an obstacle exists in the boundary detection area when any one of the following conditions 1 to 3 is satisfied.

(Condition 1) A detection point in the boundary detection area is not detected.

(Condition 2) The positions of the detection points of the boundary detection areas are different.

(Condition 3) The reflection intensities of detection points in the boundary detection area are different.

Here, as the speed of the vehicle increases, the distance required for the transport vehicle to stop increases, and the front and side boundary detection areas expand farther. At this time, if the reflectance of the laser at a distant detection point (road surface, installed object, etc.) is extremely low, it is erroneously determined that an obstacle has entered according to Condition 1. In order to avoid such misjudgment, the running speed of the vehicle must be suppressed.

Therefore, the following countermeasures 1 and 2 are added in order to avoid erroneous judgments without lowering the running speed.

(Countermeasure 1) Only the positions of existing objects (rails, signs, etc.) having a reflectance higher than a certain value in the boundary detection area are set as detection points.

(Countermeasure 2) A marker having a reflectance of a certain value or more is set in advance as a detection point in the boundary detection area.

In either case, the position of the detection target and its reflectance are recorded in the detection target information database 110 in advance, and only when the position of the detection point is included in the boundary detection area at the current vehicle position, the detection point is detected as an obstacle. Used to judge intrusion.

FIG. 5 shows the use of multi-layer LIDAR as the surrounding environment observer 107 and the detectors 201-203, as indicated by a plurality of straight lines. By using the detection points on the boundary detection area that spans multiple layers, it is possible to determine whether an obstacle has entered even if the boundary is curved.

In FIG. 5, dotted lines indicate road surface detection points by each detection layer irradiated from the multi-layer LIDAR. The detection layers passing over the side boundaries 155a, 155b vary with distance from the vehicle, and detection points in those multiple layers are monitored to determine the entry of an obstacle.

At this time, even if the detection point of the LIDAR is in the boundary detection area, if the straight line connecting the detection point and the LIDAR (laser optical path) passes outside the boundary detection area, it is not used to determine whether an obstacle has entered. . This is to prevent erroneous detection due to an object outside the boundary detection area.

A plurality of sensors of different types may be used as the detectors 201 to 203 to increase the probability of detecting an obstacle, thereby raising the obstacle detection rate. Also, the false detection rate may be reduced by using the logical product (AND) of the detected detection results.

When an obstacle enters the track beyond the side boundary 155 and the front boundary 156, the obstacle detection unit 113 shifts the operation to step S204. Otherwise, the obstacle detection unit 113 moves the operation to step S205.

Step S204: If it is determined in step S203 that an obstacle exists, the obstacle detection unit 113 creates obstacle information 161 to stop the vehicle 102. FIG.

Step S<b>205 : The obstacle detection unit 113 transmits the obstacle information 161 to the vehicle 102 .

The above is the description of the overall operation of the surroundings observation system 100A.
Next, the operation of self-position estimation system 101 will be described in detail.

<<Operation of self-localization system 101>>
FIG. 6 is a flowchart for explaining the operation of the self-localization system 101. As shown in FIG.

Steps S401 to S408 shown in the figure are operations for estimating the vehicle position of the vehicle 102, and are repeatedly executed for each measurement cycle of the obstacle detection system 103. FIG.

Step S<b>401 : The observation data selection processing unit 114 acquires the surrounding environment observation data 151 observed by the surrounding environment observation unit 107 . For example, when the surrounding environment of the vehicle 102 shown in FIG. 7 is observed by multi-layer LIDAR, rail observation data 162a to 162f and the like are acquired as three-dimensional point cloud data as shown in FIG.

Step S402: The observation data selection processing unit 114 sorts the acquired surrounding environment observation data into rail observation data 162a to f shown in FIG.

Such rail observation data 162a-f are selected based on their shape, reflectance, and the fact that the rail detection data forms one track surface (flat or curved surface).

Step S403: The vehicle attitude estimation processing unit 115 determines the temporary position of the vehicle 102 on the rail track in the map data of the surrounding environment map database 117 and the 3D rail track database 118. FIG. This temporary position is determined based on the communication between the rail ground coil and the vehicle 102, GPS information, the speed cumulative value of the vehicle 102, and the like.

Step S404: The vehicle attitude estimation processing unit 115 acquires rail position information (three-dimensional point cloud data defining the rail surface) at the temporary position by referring to the 3D rail track database 118 for the temporary position on the rail track. .

The vehicle attitude estimation processing unit 115 performs geometric operations on the surface R formed by the rail surface obtained from the rail observation data 162 shown in FIG. Estimate information.

Step S<b>405 : Surrounding environment observation data of the surrounding environment observation unit 107 are observed by the sensors mounted on the vehicle 102 , so they are observed values in the vehicle coordinate system _ΣT fixed to the vehicle 102 .

On the other hand, the surrounding environment map database 117 and the 3D rail track database 118 record map data and 3D rail track data in the external coordinate system _ΣO .

Surrounding environment data coordinate conversion processing unit 116 converts the surrounding environment observation data into a vehicle coordinate system fixed to vehicle 102 based on the temporary position of vehicle 102 on the rail track and the attitude information of vehicle 102 estimated in step S404. Coordinate conversion is performed from _ΣT to an external coordinate system _ΣO , and output as peripheral environment data after coordinate conversion.

Step S<b>406 : The scan matching self-position estimation unit 119 performs scan matching between the surrounding environment data after coordinate conversion and the map data recorded in the surrounding environment map database 117 . This scan matching is performed while the sensor position (vehicle position) in the surrounding environment data is constrained on the rail track of the map data. In this case, the scan range is set to a width that can maintain the validity of the orientation estimation in step S404 and the coordinate transformation in step S405.
Within this scan range, a scan position is searched for where the residual between the surrounding environment data and the map data (such as the sum of the absolute differences between the two data) is the minimum residual.

Step S407: The scan matching self-position estimation unit 119 determines whether or not the minimum residual calculated in scan matching is smaller than the allowable value. This tolerance is appropriately set based on the required accuracy of vehicle position.

Here, when the minimum residual exceeds the allowable value, the scan matching self-position estimation unit 119 shifts the operation to step S408.

Also, when the minimum residual is within the allowable value, the scan matching self-position estimation unit 119 shifts the operation to step S409.

Step S408: The scan matching self-position estimator 119 displaces the temporary position by the increment distance along the rail track. This step distance is a distance exceeding the range scanned in step S406. Further, the displacement direction (positive or negative of the step distance) of the provisional position is determined in the direction in which the residual error of matching becomes smaller, based on the change tendency of the residual error during the scan matching in step S406.

After displacing the temporary position in this way, the scan matching self-position estimation unit 119 returns the operation to step S404.

Step S409: By repeating steps S404 to S408, the minimum residual of scan matching is reduced to below the allowable value. The scan matching self-position estimation unit 119 estimates the scan position on the rail track at which the minimum residual error equal to or less than the allowable value is obtained as the vehicle position of the vehicle 102 .

<<Operation of Vehicle Operation Control Unit 105>>
Next, the operation of the vehicle driving control section 105 will be described.

FIG. 11 is a flowchart for explaining the operation of the vehicle operation control section 105. As shown in FIG.
The operation shown in the figure is repeatedly executed at regular intervals.
Step S500: The vehicle operation control unit 105 acquires information on the location of the vehicle 102 based on the operation schedule of the vehicle 102 or the like.

Step S501: The vehicle operation control unit 105 determines whether or not the vehicle 102 is stopped at a station. The determination is made from the on-track position and speed of the vehicle 102 . For example, if the vehicle 102 is near the station platform and the speed is zero, it is determined that the vehicle is stopped at the station. When it is determined that the train is stopped at the station, the vehicle operation control unit 105 shifts the operation to step S502. Otherwise, the vehicle operation control unit 105 moves the operation to step S511.

Step S<b>502 : The vehicle operation control unit 105 acquires the scheduled departure time of the vehicle 102 based on the operation schedule of the vehicle 102 .

Step S503: The vehicle operation control unit 105 determines whether or not the current time has reached the scheduled departure time. If the current time has not reached the scheduled departure time, the vehicle operation control unit 105 exits this processing flow. When the current time reaches the scheduled departure time, the vehicle operation control unit 105 advances the operation to step S504.

Step S504: The vehicle operation control unit 105 determines whether or not the vehicle 102 is ready to depart. An example of preparing for departure is checking whether the vehicle door is closed. If not completed, exit from this processing flow. When preparations for departure have been completed, the vehicle operation control unit 105 advances the operation to step S505.

Step S<b>505 : The vehicle operation control section 105 acquires the obstacle information 161 from the obstacle detection system 103 . In this case, as shown in FIG. 12, based on the highly accurate vehicle position by the self-position estimation system 101, the obstacle monitoring area 500 is set so as to exclude the range of the station platform. By using the highly accurate vehicle position, the obstacle monitoring area 500 includes the inside of the white line of the station platform and the vicinity of the platform door (unsafe area for the vehicle 102 to pass nearby). is also fully possible. Furthermore, based on highly accurate vehicle positions in station sections, it is possible to narrow the monitoring area 500 so that vehicles on adjacent rails (vehicles on another platform of the station) are not detected as obstacles.

Step S506: The vehicle operation control unit 105 determines from the obstacle information 161 whether or not an obstacle exists. If no obstacle exists, the vehicle operation control unit 105 advances the operation to step S507. If an obstacle exists, the vehicle operation control unit 105 exits this processing flow while generating or maintaining a stop command.

Step S<b>507 : The vehicle driving control section 105 generates the driving command 142 and transmits it to the vehicle driving section 106 . Specifically, here, a power running command is transmitted to depart the station.

Step S508: The vehicle operation control unit 105 calculates the estimated time of arrival at the next station based on the timing at which the vehicle 102 departs and the scheduled running time between stations to be run from now on, and informs the operation control center of the vehicle 102 ( (operation management system).

Next, the processing (steps S511 to S515) when it is determined that the vehicle 102 is not stopped at the station in step S501 will be described.

Step S<b>311 : The vehicle operation control unit 105 acquires the obstacle information 161 within the monitored area from the obstacle detection system 103 . As shown in FIG. 13, the obstacle monitoring area 600 is set wide because the vehicle is traveling between stations. However, if there is a section in which maintenance work is in progress between stations, based on the highly accurate vehicle position by the self-position estimation system 101, the area where maintenance personnel can work safely should be excluded from the obstacle monitoring area 600. is set to

Step S512: The vehicle operation control unit 105 determines whether braking of the vehicle 102 is necessary based on the obstacle information 161 within the monitoring area. If the obstacle does not exist and braking is unnecessary, the vehicle operation control unit 105 proceeds to step S513. If there is an obstacle and braking is required, the vehicle operation control unit 105 proceeds to step S514.

Step S<b>513 : The vehicle driving control section 105 generates the driving command 142 and transmits it to the vehicle driving section 106 . Specifically, here, a driving command such as proportional control is transmitted so that the speed of the vehicle 102 becomes a predetermined target speed. After transmission, the vehicle operation control unit 105 advances the operation to step S515.

Step S514: The vehicle operation control unit 105 transmits a braking command for the vehicle 102 to the vehicle driving unit 106 in response to the detection of the obstacle. Specifically, a braking command is generated to decelerate and stop the vehicle 102 at maximum deceleration. After transmitting the braking command, the vehicle operation control unit 105 proceeds to step S515.

Step S515: The vehicle operation control unit 105 estimates the arrival time of the vehicle 102 at the next station from the current position, speed, and operation status, and transmits the estimated arrival time to the operation management center (operation management system) of the vehicle 102 .

The above is the description of the operation of the vehicle driving control unit 105 .

<<Effects of Example 1, etc.>>
In the first embodiment, the range along the track is scanned for matching (correlation) between the observation result of the surrounding environment observation unit 107 and the map data in the surrounding environment map database.

In the case of a vehicle such as an automobile that does not normally run along a specific track, as shown in FIGS. The position with the highest correlation value (FIG. 15) is obtained as the vehicle position. In this case, since the degree of freedom in scanning is high, a position where the matching residual happens to be minimal is likely to be erroneously determined as the vehicle position, and it is difficult to improve the detection accuracy of the vehicle position.

Furthermore, since scanning in multiple directions is required, there is also the problem that the processing load required for scan matching is heavy and the processing takes time.

However, in the process of estimating the vehicle position in the first embodiment, the matching (correlation) between the surrounding environment data 168 and the map data 166 is the highest while scanning one-dimensionally while constrained to the trajectory L as shown in FIG. is estimated as the vehicle position (see FIG. 17). Therefore, since the scanning range is limited to the track L, it is possible to improve the detection accuracy of the vehicle position without erroneously determining a position off the track L as the vehicle position.

Further, in the first embodiment, since the scan range is limited by the trajectory L, the processing load of scan matching is lightened, and the processing time can be shortened.

Furthermore, in the first embodiment, the attitude of the vehicle 102 with respect to the track is obtained based on the observation result of the track by the surrounding environment observation unit 107 . Even if the vehicle 102 is traveling on a track, the attitude of the vehicle 102 with respect to the track changes from moment to moment due to the effects of acceleration/deceleration, curve travel, and the like. In Example 1, it is possible to acquire information about the attitude of the vehicle 102 that changes in this way.

In addition, in the first embodiment, the observation result of the surrounding environment observation unit 107 is coordinate-transformed based on the attitude of the vehicle 102 . By this coordinate transformation, tilt fluctuations in the observation result of the surrounding environment observation unit 107 caused by the attitude of the vehicle 102 are correctly calibrated. Therefore, the accuracy of matching between the observation result after the coordinate conversion and the map data is increased, and it is possible to further increase the accuracy of vehicle position detection.

Furthermore, in the first embodiment, the detection accuracy of the vehicle position is high, so it becomes possible to change the monitoring area of the obstacle detection system 103 at an appropriate timing according to the vehicle position. Therefore, it is possible to reliably detect only obstacles within the monitoring area to be monitored. Also, an object positioned outside the monitoring area that should not be monitored is not erroneously detected as an obstacle.

For example, in a station section, by narrowing the monitoring area, passengers waiting in a safe position on the station platform (or outside the white line of the station platform) will not be erroneously detected as an obstacle.

Further, for example, in a maintenance work section, by narrowing the monitoring area, it is possible to prevent a maintenance worker working safely from being erroneously detected as an obstacle.

Further, in the first embodiment, a boundary detection area having a predetermined width is provided at the boundary of the monitoring area (left and right side boundaries, front boundary, etc.) for the purpose of quickly and reliably detecting obstacles. In the first embodiment, the detection accuracy of the vehicle position is high, so it becomes possible to change the predetermined width of the boundary detection area at an appropriate timing according to the vehicle position.

For example, in a station section, by narrowing the predetermined width of the boundary detection area, it becomes possible to intensively detect passengers who enter the white line on the track or on the station platform.

Further, for example, in a running section between stations, by expanding the predetermined width of the boundary detection area, the fast movement of a relatively large moving object (such as an automobile) entering the railroad track can be reliably detected in a relatively wide field of view. becomes possible.

In addition, the present invention is not limited to the above-described embodiments, and includes various modifications. For example, the above-described embodiments have been described in detail in order to explain the present invention in an easy-to-understand manner, and are not necessarily limited to those having all the described configurations.

Moreover, it is also possible to add, delete, or replace a part of the configuration of the embodiment with another configuration.

For example, in the embodiment, the operation of intensively detecting obstacles in the boundary detection area of the monitored area has been described, but the present invention is not limited to this. For example, obstacles may be detected all or part of the monitored area.

DESCRIPTION OF SYMBOLS 100... Rail transportation system, 100A... Periphery observation system, 101... Self-position estimation system, 102... Vehicle, 103... Obstacle detection system, 105... Vehicle operation control part, 106... Vehicle drive part, 107... Surrounding environment observation part, 108...Detection range setting database, 109...Monitoring area setting processing unit, 110...Detection object information database, 111...Side boundary monitoring unit, 112...Front boundary monitoring unit, 113...Obstacle detection unit, 114...Observation data selection processing Unit 115 Vehicle posture estimation processing unit 116 Surrounding environment data coordinate conversion processing unit 117 Surrounding environment map database 118 3D rail track database 119 Scan matching self-position estimation unit 142 Drive command 151 Surrounding environment observation data 153 Position/attitude information 154 Detection range 155 Side boundary 156 Front boundary 159 Monitoring result 160 Monitoring result 161 Obstacle information

Claims (9)

a surrounding environment observation unit that observes the positions of surrounding objects from the position of the vehicle traveling on the track and outputs the observation results;
Map data created by observing the positions of the object group in advance is stored, and the observation results and the map data are combined in a state where the position of the vehicle in the observation results is limited to the trajectory of the map data. a position estimator that calculates the correlation of and estimates the vehicle position based on the correlation ,
The surrounding environment observation unit observes the trajectory,
The position estimation unit obtains the attitude of the vehicle with respect to the trajectory based on the observation result of the trajectory.
A peripheral observation system characterized by: The peripheral observation system according to claim 1,
The position estimation unit performs coordinate transformation on the observation result of the surrounding environment observation unit based on the attitude of the vehicle, and calculates the correlation of the object group between the observation result after the coordinate transformation and the map data. at a position limited to the trajectory and estimate the vehicle position based on the correlation
A peripheral observation system characterized by: The peripheral observation system according to any one of claims 1 and 2,
an obstacle detection unit that detects obstacles present in a monitoring area set for the trajectory;
a boundary setting unit that changes the monitoring area based on the vehicle position estimated by the position estimation unit;
A peripheral observation system comprising: The peripheral observation system according to claim 3,
the monitoring area includes a boundary detection area with a predetermined width for detecting obstacles at the boundary of the monitoring area;
The boundary setting section changes the predetermined width of the boundary detection area based on the vehicle position estimated by the position estimating section.
A peripheral observation system characterized by: The peripheral observation system according to any one of claims 3 and 4,
The monitoring area is defined by side boundaries set on the left and right of the track and front boundaries set on the front of the track in the traveling direction.
A peripheral observation system characterized by: The peripheral observation system according to any one of claims 3 to 5,
The boundary setting unit changes the monitoring area in the station section based on the positional relationship between the vehicle position estimated by the position estimation unit and the station section.
A peripheral observation system characterized by: The peripheral observation system according to any one of claims 3 to 6,
The boundary setting unit changes the monitoring area in the maintenance work section based on the positional relationship between the vehicle position estimated by the position estimation unit and the track maintenance work section.
A peripheral observation system characterized by: A computer system functions as the peripheral observation system according to any one of claims 1 to 7
A peripheral observation program characterized by: a surrounding environment observation step of observing the position of a group of surrounding objects and the track from the position of the vehicle traveling on the track, and obtaining an observation result;
Map data created by observing the positions of the object group in advance is stored, and the observation results and the map data are combined in a state where the position of the vehicle in the observation results is limited to the trajectory of the map data. a position estimation step of calculating the correlation of and estimating the vehicle position based on the correlation;
an attitude estimation step of obtaining an attitude of the vehicle with respect to the trajectory based on the observation result of the trajectory;
Perimeter observation method with

Images