WO2010101393A2 - Apparatus and the method for distinguishing ground and obstacles for autonomous mobile vehicle - Google Patents
Apparatus and the method for distinguishing ground and obstacles for autonomous mobile vehicle Download PDFInfo
- Publication number
- WO2010101393A2 WO2010101393A2 PCT/KR2010/001300 KR2010001300W WO2010101393A2 WO 2010101393 A2 WO2010101393 A2 WO 2010101393A2 KR 2010001300 W KR2010001300 W KR 2010001300W WO 2010101393 A2 WO2010101393 A2 WO 2010101393A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- laser radar
- ground
- obstacle
- inclination
- distance data
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000007796 conventional method Methods 0.000 description 5
- 101100434480 Arabidopsis thaliana AFB2 gene Proteins 0.000 description 2
- 101100449517 Arabidopsis thaliana GRH1 gene Proteins 0.000 description 2
- 101100380517 Rattus norvegicus Atf3 gene Proteins 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- VJYFKVYYMZPMAB-UHFFFAOYSA-N ethoprophos Chemical compound CCCSP(=O)(OCC)SCCC VJYFKVYYMZPMAB-UHFFFAOYSA-N 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
- B60R1/02—Rear-view mirror arrangements
- B60R1/08—Rear-view mirror arrangements involving special optical features, e.g. avoiding blind spots, e.g. convex mirrors; Side-by-side associations of rear-view and other mirrors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/87—Combinations of systems using electromagnetic waves other than radio waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/87—Combinations of systems using electromagnetic waves other than radio waves
- G01S17/875—Combinations of systems using electromagnetic waves other than radio waves for determining attitude
Definitions
- the present invention relates to apparatus and a method for distinguishing ground and obstacles for an autonomous mobile vehicle such as a military vehicle, which is based on the 2 dimensional World Model using a cylindrical coordinate system with the vehicle at the center.
- the present method determines whether an object detected by a 2D laser radar is an obstacle that hinders the operation of the vehicle, or a plain ground.
- the cylindrical coordinate system with the vehicle at the center can be generated by using the distance data obtained by the 2D laser radar which is arranged in parallel with the horizontal plane of the vehicle or oriented to the front direction of the moving vehicle.
- the World Model means a 3 dimensional map including elevation information or a 2 dimensional map having marks of obstacles.
- the World Model is generated by using one or more sensors comprising one or more types of sensors such as CCD, IR, 2D laser radar, normal radar, or 3D laser radar to recognize surrounding environment, and by marking the recognized results in the Cartesian or cylindrical coordinate system.
- Conventional method for detecting obstacles for autonomous mobile vehicle uses various sensors such as CCD, 2D laser radar, etc. It also determines every detected object, which is not plain, is regarded as an obstacle (Documents 1 and 2) based on the assumption that the operating environment is relatively plain. This method of detecting obstacles is appropriate for use indoors or in the city environment, where the amount of data to be processed is small and the calculation time for the data is relatively short.
- the conventional method In non-paved roads or field areas, the conventional method generates a 3 dimensional World Model including elevation information by using sensors (CCD, IR, laser radar, radar, etc.). This method also detects an obstacle by analyzing drivability based on the World Model (Documents 3 and 4). In Addition, this method requires much calculation time since a lot of data from various sensors should be obtained and analyzed.
- the conventional methods are not appropriate for the autonomous mobile vehicle such as armored vehicle which performs an abrupt movement on a non-paved road or field area since only one 2D laser radar built in the autonomous mobile vehicle, or a plurality of 2D laser radars arranged in parallel with the base plane of the vehicle is used.
- the autonomous vehicle When lateral or longitudinal force acts on the vehicle due to an abrupt change of direction or speed, the autonomous vehicle is slanted by the lateral or longitudinal force in the right or left direction(roll direction), or in the front or rear direction (pitch direction). In this case, a relatively plain ground is erroneously recognized as an obstacle.
- Fig. 5 illustrates the radiation pattern of beam from the 2D laser radars, which are arranged in parallel with the base plane of the autonomous vehicle when the right and left suspension devices are pressed differently due to an abrupt change of direction of the vehicle. It can be seen from the figure that the distance data between left and right direction are different although the ground is plain when the autonomous vehicle is inclined in the roll direction. As a result, plain ground can be erroneously recognized as an obstacle when the autonomous vehicle is inclined in the roll direction. Therefore, the vehicle will make an avoidance action although there is no obstacle.
- the autonomous mobile vehicle is inclined in the right or left direction(roll direction) or in the front or rear direction (pitch direction) by the lateral or longitudinal force resulting from an abrupt change of direction or speed, thereby changing the orientation angle of the 2D laser radar.
- the distance (distance data) to the detected object for example, the obstacle or ground in front of the vehicle
- the distance detected when the vehicle is not inclined there have been cases where ground is erroneously recognized as an obstacle when the vehicle is autonomously operated on non-paved road or on field where the ground plane is not sufficiently plain.
- the objective of the present invention is to solve the problem that can occur when the autonomous mobile vehicle is operated on the non-paved road or field.
- distance data is obtained by using two 2D laser radars which are arranged at upper and lower position of a vertical line and oriented toward the front direction with different orientation angles. Then the actual inclination of the detected object is calculated by using the distance data obtained by the 2D laser radars, determination is made whether the detected object is an obstacle or ground based on the actual inclination calculated.
- the arbitrary maximum value of the distance that the corresponding 2D laser radar can have is stored as a changed distance data on the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar so that the relatively plain ground is not erroneously recognized as an obstacle.
- the apparatus for distinguishing ground and obstacles for an autonomous mobile vehicle comprises an upper 2D laser radar 1 installed on the front upper portion of the autonomous mobile vehicle arranged with predetermined orientation angle ( ⁇ 1 ) with respect to the horizontal base plane of the vehicle (or ground), a lower 2D laser radar 2 installed on the front lower portion of the autonomous mobile vehicle at the location vertically below the upper 2D laser radar 1 with a predetermined vertical distance (d offset ) and arranged in parallel with the horizontal base plane of the vehicle, and a processing unit 10 installed on the autonomous mobile vehicle for carrying out predetermined data processing, the processing unit 10 comprising a distance data receiving part 11 which receives distance data r 1 , r 2 to the object which are detected by the upper 2D laser radar 1 and the lower 2D laser radar 2, an inclination calculating part 12 which calculates actual inclination (g) of the detected object based on the distance data r 1 , r 2 received from the distance data receiving part 11, the orientation angle ( ⁇ 1 ) and the vertical distance (d offset ), a distance data receiving part 11 which receive
- the method for distinguishing between ground and an obstacle for autonomous mobile vehicle comprises a step of obtaining distance data in which distance data r 1 , r 2 from the upper 2D laser radar 1 and the lower 2D laser radar 2 to the detected object is obtained by using the upper 2D laser radar 1 and the lower 2D laser radar 2 installed on front side of the autonomous mobile vehicle, a step of calculating inclination in which the actual inclination (g) of the detected object is calculated by the inclination calculating part 12 of the apparatus for distinguishing between ground and an obstacle for autonomous mobile vehicle by using the distance data r 1 , r 2 , the orientation angle ( ⁇ 1 ) of the upper 2D laser radar 1, and the vertical distance (d offset ) between the upper 2D laser radar 1 and the lower 2D laser radar 2, and a step of determining ground and an obstacle in which the ground and obstacle determining part 13 of the processing unit determines the detected object as an obstacle when the actual inclination (g) of the detected object is larger than the reference inclination, and determines the detected object as ground when the
- the minimum value of the obtained distance data (r 1 , r 2 ) is stored as a distance data at the angle of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar when the actual inclination (g) of the detected object at a certain angle is larger than predetermined reference inclination
- the arbitrary maximum value of the distance that the corresponding 2D laser radar can have is stored as a distance data at the angle of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar when the actual inclination (g) of the detected is smaller than predetermined reference inclination.
- distance data is obtained by two 2D laser radars arranged with different orientation angles and determination is made based on the distance data whether the detected object is an obstacle or not, thereby removing the phenomena that an object is erroneously determined as an obstacle due to abrupt change of direction or velocity.
- the performance of autonomous driving of the vehicle on non-paved roads or field can be enhanced by measuring the inclination of the driving road (for example, ground) and determining the irregularity as an obstacle when the bend curve is abrupt.
- the driving road for example, ground
- This measured inclination of the driving road can be used as information for analyzing the driving performance of the autonomous vehicle or as a parameter for controlling the speed of the vehicle depending on the driving environment of the autonomous vehicle.
- the apparatus for detecting ground and obstacle for autonomous mobile vehicle of the present invention is cost-effective since only two laser radars and one processing unit are required.
- Fig. 1 is a block diagram showing the apparatus for distinguishing ground and obstacles for an autonomous mobile vehicle according to the present invention.
- Fig. 2 is a front and side view showing the state in which two 2D laser radars comprising the apparatus for distinguishing ground and obstacles are installed on the autonomous vehicle.
- Fig. 3 is a flow chart showing the process of calculating the actual inclination of the detected object by the apparatus for distinguishing ground and obstacles for an autonomous mobile vehicle.
- Fig. 4 conceptually illustrates how the distance data needed for the apparatus for detecting ground and obstacles to calculate the actual inclination of the detected object is obtained.
- Fig. 5 illustrates the beam radiated from the 2D laser radars, which are arranged in parallel with the base plane of the autonomous vehicle, when the right and left suspension devices are pressed differently due to an abrupt change of direction of the vehicle.
- Fig. 1 is a block diagram showing the apparatus for distinguishing ground and obstacles for an autonomous mobile vehicle according to the present invention
- Fig. 2 is a front and side view showing the state in which two 2D laser radars comprising the apparatus for distinguishing ground and obstacles are installed on the autonomous vehicle
- Fig. 3 is a flow chart showing the process of calculating the actual inclination of the detected object by the apparatus for distinguishing ground and obstacles for an autonomous mobile vehicle
- Fig. 4 conceptually illustrates how the distance data needed for the apparatus for detecting ground and obstacles to calculate the actual inclination of the detected object is obtained.
- the apparatus for distinguishing ground and an obstacle for autonomous mobile vehicle of the present invention an upper 2D laser radar 1 installed on the front upper portion of the autonomous mobile vehicle arranged with predetermined orientation angle ( ⁇ 1 ) with respect to the horizontal base plane of the vehicle, a lower 2D laser radar 2 installed on the front lower portion of the autonomous mobile vehicle at the location vertically below the upper 2D laser radar 1 with a predetermined vertical distance (d offset ) and arranged in parallel with the horizontal base plane of the vehicle, and a processing unit 10 installed on the autonomous mobile vehicle for carrying out predetermined data processing.
- ⁇ 1 predetermined orientation angle
- d offset predetermined vertical distance
- the processing unit 10 comprises a distance data receiving part 11 which receives distance data r 1 , r 2 to the object which are detected by the upper 2D laser radar 1 and the lower 2D laser radar 2, an inclination calculating part 12 which calculates actual inclination (g) of the detected object based on the distance data r 1 , r 2 received from the distance data receiving part 11, the orientation angle ( ⁇ 1 ) and the vertical distance (d offset ), a ground and obstacle determining part 13 which determines whether the detected object is ground or an obstacle by comparing the actual inclination (g) of the detected object received from the inclination calculating part 12 and the predetermined reference inclination, and generates a distance data for a virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar, the distance data being the minimum value of the distance data r 1 , r 2 or the maximum value that corresponding 2D laser radar can have, and a transmitting part 14 which transmits the distance data for the virtual 2D laser radar which is assumed to
- the autonomous mobile vehicle can avoid collision through the control of the parts by the collision avoiding processing unit 20.
- the 2D laser radar 1, 2 when using 2D laser radar 1, 2 on the autonomous mobile vehicle that can operate on the non-paved road or field, the 2D laser radar 1, 2 are installed on the same vertical axis.
- the 2D laser radar 1, 2 are oriented in the same direction (front) but with different orientation angle. This is for calculating the actual inclination of the detected object by using the distance data r 1 , r 2 obtained by each 2D laser radar 1, 2.
- 2D laser radar that can scan more than 100° sidewise is used here.
- the apparatus for distinguishing between ground and an obstacle for autonomous mobile vehicle as described above determines whether an object is an obstacle or not as follows.
- distance data r 1 , r 2 from the upper and lower 2D laser radar 1, 2 installed on the vehicle to the detected object is obtained (step of obtaining distance data).
- the actual inclination (g) of the detected object is calculated by the inclination calculating part 12 of the apparatus for distinguishing between ground and an obstacle for autonomous mobile vehicle by using the distance data r 1 , r 2 , the orientation angle ( ⁇ 1 ) of the upper 2D laser radar 1, and the vertical distance (d offset ) between the upper 2D laser radar 1 and the lower 2D laser radar 2 (step of calculating inclination).
- the ground and obstacle determining part 13 of the processing unit determines the detected object as an obstacle when the actual inclination (g) of the detected object is larger than the reference inclination, and determines the detected object as ground when the actual inclination (g) of the detected object is smaller than the reference inclination (step of determining ground and an obstacle).
- unprocessed front distance data is obtained by two 2D laser radars 1, 2 which are installed on the autonomous mobile vehicle.
- the distance data obtained by the 2D laser radars are transferred to the processing unit 10 for predetermined data processing.
- the processing unit 10 checks whether distance data has been received from each of the 2D laser radar 1, 2, and generates variables for storing distance data per angle from each 2D laser radar 1, 2, and variables for storing processed data for the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar.
- the distance data per angle of the upper 2D laser radar 1 is stored as LRF1
- the distance data per angle of the lower 2D laser radar 2 as LRF2
- the variable for the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar as LRF0 the distance data per angle of the upper 2D laser radar 1 is stored as LRF1
- the distance data per angle of the lower 2D laser radar 2 as LRF2
- the variable for the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar as LRF0.
- the actual inclination of the detected object is calculated by comparing distance data of the same angel of LRF1 and LRF2.
- r 1 is the distance data received by the upper 2D laser radar 1
- r 2 the distance data received by the lower 2D laser radar 2
- ⁇ 1 the angle of the upper 2D laser radar 1 in the Pitch direction (the angle of orientation toward the ground)
- d offset the difference of height of the two 2D laser radars 1, 2 in vertical direction.
- the actual inclination of the detected object (g) is calculated by the following formula.
- the minimum value of the obtained distance data (r 1 , r 2 ) is stored as a distance data at the angle of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar.
- the arbitrary maximum value of the distance that the corresponding 2D laser radar can have is stored as a distance data at the angle of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar.
- the detected object is determined to be an obstacle and the variable LRF0 of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar is given the minimum value of the distance data at the corresponding angle.
- the detected object is determined to be the ground and the variable LRF0 of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar is given, as a distance data at the corresponding angle, the arbitrary maximum value of the distance that the corresponding 2D laser radar can have.
Abstract
Disclosed is apparatus for distinguishing between ground and an obstacle for autonomous mobile vehicle, comprising an upper 2D laser radar 1, a lower 2D laser radar 2, and a processing unit 10, the processing unit 10 comprising a distance data receiving part 11, an inclination calculating part 12, a ground and obstacle determining part 13, and a transmitting part. Also disclosed is a method for distinguishing between ground and an obstacle for autonomous mobile vehicle by using the apparatus for distinguishing between ground and an obstacle for autonomous mobile vehicle of claim 1, in which the detected object is determined as an obstacle when the actual inclination (g) of the detected object is larger than the reference inclination, and as ground when the actual inclination (g) of the detected object is smaller than the reference inclination.
Description
The present invention relates to apparatus and a method for distinguishing ground and obstacles for an autonomous mobile vehicle such as a military vehicle, which is based on the 2 dimensional World Model using a cylindrical coordinate system with the vehicle at the center. The present method determines whether an object detected by a 2D laser radar is an obstacle that hinders the operation of the vehicle, or a plain ground.
The cylindrical coordinate system with the vehicle at the center can be generated by using the distance data obtained by the 2D laser radar which is arranged in parallel with the horizontal plane of the vehicle or oriented to the front direction of the moving vehicle.
The World Model means a 3 dimensional map including elevation information or a 2 dimensional map having marks of obstacles. The World Model is generated by using one or more sensors comprising one or more types of sensors such as CCD, IR, 2D laser radar, normal radar, or 3D laser radar to recognize surrounding environment, and by marking the recognized results in the Cartesian or cylindrical coordinate system.
Conventional method for detecting obstacles for autonomous mobile vehicle uses various sensors such as CCD, 2D laser radar, etc. It also determines every detected object, which is not plain, is regarded as an obstacle (Documents 1 and 2) based on the assumption that the operating environment is relatively plain. This method of detecting obstacles is appropriate for use indoors or in the city environment, where the amount of data to be processed is small and the calculation time for the data is relatively short.
In non-paved roads or field areas, the conventional method generates a 3 dimensional World Model including elevation information by using sensors (CCD, IR, laser radar, radar, etc.). This method also detects an obstacle by analyzing drivability based on the World Model (Documents 3 and 4). In Addition, this method requires much calculation time since a lot of data from various sensors should be obtained and analyzed.
Additionally, in the case of application where detecting and avoiding obstacles that emerge suddenly at a short distance, obstacles are detected by using one or more of 2D laser radars and avoidance is carried out for a fast response on the assumption that the driving environment is relatively plain (Documents 5 and 6).
The conventional methods, however, are not appropriate for the autonomous mobile vehicle such as armored vehicle which performs an abrupt movement on a non-paved road or field area since only one 2D laser radar built in the autonomous mobile vehicle, or a plurality of 2D laser radars arranged in parallel with the base plane of the vehicle is used. When lateral or longitudinal force acts on the vehicle due to an abrupt change of direction or speed, the autonomous vehicle is slanted by the lateral or longitudinal force in the right or left direction(roll direction), or in the front or rear direction (pitch direction). In this case, a relatively plain ground is erroneously recognized as an obstacle.
Fig. 5 illustrates the radiation pattern of beam from the 2D laser radars, which are arranged in parallel with the base plane of the autonomous vehicle when the right and left suspension devices are pressed differently due to an abrupt change of direction of the vehicle. It can be seen from the figure that the distance data between left and right direction are different although the ground is plain when the autonomous vehicle is inclined in the roll direction. As a result, plain ground can be erroneously recognized as an obstacle when the autonomous vehicle is inclined in the roll direction. Therefore, the vehicle will make an avoidance action although there is no obstacle.
<Prior Art Document of the invention>
[Document 1] Badal, S., Ravela, S., Draper, B. and Hanson, A., "A Practical Obstacle Detection and Avoidance System", In 2nd IEEE Workshop on Application of Computer Vision, 1994.
[Document 2] Broggi, A., Bertozzi, M., Fascioli, A., Guarino Lo Bianco, C. and Piazzi, A., "Visual Perception of Obstacles and Vehicles for Platooning", IEEE Trans. Intell. Transport. Sys. 1(3), 2000.
[Document 3] Lacaze, A., Murphy, K. and Del Giorno, M., "Autonomous Mobility for the DEMO III Experimental Unmanned Vehicle.", Association for Unmanned Vehicle Systems - Unmanned Vehicle, 2002.
[Document 4] Hong, T., Abrams, M., Chang, T. and Shneirer, M. O., "An intelligent World Model for Autonomous Off-Road Driving", Computer Vision and Image Understanding, 2000.
[Document 5] Kim, Jaewhan, “Detection of Obstacle and Generation of Path for Unmanned Vehicle by using a plurality of laser scanners”, Kookmin Univ. Graduate School of Vehicle Engineering, Paper for Master’s degree, 2008.
[Document 6] Won-Jong Sohn, Keum-Shik Hong, "Moving Obstacle Avoidance Using a LRF Sensor", SICE-ICASE 2006 International Joint Conference, pp 5957-5962, 18-21 Oct. 2006.
As described above regarding the conventional method of detecting obstacles, the autonomous mobile vehicle is inclined in the right or left direction(roll direction) or in the front or rear direction (pitch direction) by the lateral or longitudinal force resulting from an abrupt change of direction or speed, thereby changing the orientation angle of the 2D laser radar. As a result, when the autonomous mobile vehicle is inclined, the distance (distance data) to the detected object (for example, the obstacle or ground in front of the vehicle) becomes shorter than the distance detected when the vehicle is not inclined. So, in the conventional method of detecting obstacles, there have been cases where ground is erroneously recognized as an obstacle when the vehicle is autonomously operated on non-paved road or on field where the ground plane is not sufficiently plain.
Therefore, the objective of the present invention is to solve the problem that can occur when the autonomous mobile vehicle is operated on the non-paved road or field.
According to the features of present invention, distance data is obtained by using two 2D laser radars which are arranged at upper and lower position of a vertical line and oriented toward the front direction with different orientation angles. Then the actual inclination of the detected object is calculated by using the distance data obtained by the 2D laser radars, determination is made whether the detected object is an obstacle or ground based on the actual inclination calculated. When the object is determined as ground, the arbitrary maximum value of the distance that the corresponding 2D laser radar can have is stored as a changed distance data on the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar so that the relatively plain ground is not erroneously recognized as an obstacle.
More specifically, the apparatus for distinguishing ground and obstacles for an autonomous mobile vehicle according to the present invention comprises an upper 2D laser radar 1 installed on the front upper portion of the autonomous mobile vehicle arranged with predetermined orientation angle (θ1) with respect to the horizontal base plane of the vehicle (or ground), a lower 2D laser radar 2 installed on the front lower portion of the autonomous mobile vehicle at the location vertically below the upper 2D laser radar 1 with a predetermined vertical distance (doffset) and arranged in parallel with the horizontal base plane of the vehicle, and a processing unit 10 installed on the autonomous mobile vehicle for carrying out predetermined data processing, the processing unit 10 comprising a distance data receiving part 11 which receives distance data r1, r2 to the object which are detected by the upper 2D laser radar 1 and the lower 2D laser radar 2, an inclination calculating part 12 which calculates actual inclination (g) of the detected object based on the distance data r1, r2 received from the distance data receiving part 11, the orientation angle (θ1) and the vertical distance (doffset), a ground and obstacle determining part 13 which determines whether the detected object is ground or an obstacle by comparing the actual inclination (g) of the detected object received from the inclination calculating part 12 and the predetermined reference inclination, and generates a distance data for a virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar, and a transmitting part 14 which transmits the distance data for the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar, generated by the ground and obstacle determining part 13, to a collision avoiding processing unit 20 of the autonomous mobile vehicle. Here, the predetermined reference inclination is obtained from actually measured inclinations on artificial obstacles which are dangerous to the autonomous vehicle.
The method for distinguishing between ground and an obstacle for autonomous mobile vehicle comprises a step of obtaining distance data in which distance data r1, r2 from the upper 2D laser radar 1 and the lower 2D laser radar 2 to the detected object is obtained by using the upper 2D laser radar 1 and the lower 2D laser radar 2 installed on front side of the autonomous mobile vehicle, a step of calculating inclination in which the actual inclination (g) of the detected object is calculated by the inclination calculating part 12 of the apparatus for distinguishing between ground and an obstacle for autonomous mobile vehicle by using the distance data r1, r2, the orientation angle (θ1) of the upper 2D laser radar 1, and the vertical distance (doffset) between the upper 2D laser radar 1 and the lower 2D laser radar 2, and a step of determining ground and an obstacle in which the ground and obstacle determining part 13 of the processing unit determines the detected object as an obstacle when the actual inclination (g) of the detected object is larger than the reference inclination, and determines the detected object as ground when the actual inclination (g) of the detected object is smaller than the reference inclination.
Also in the above method, it is preferable that the minimum value of the obtained distance data (r1, r2) is stored as a distance data at the angle of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar when the actual inclination (g) of the detected object at a certain angle is larger than predetermined reference inclination, and the arbitrary maximum value of the distance that the corresponding 2D laser radar can have is stored as a distance data at the angle of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar when the actual inclination (g) of the detected is smaller than predetermined reference inclination.
According to the present invention, distance data is obtained by two 2D laser radars arranged with different orientation angles and determination is made based on the distance data whether the detected object is an obstacle or not, thereby removing the phenomena that an object is erroneously determined as an obstacle due to abrupt change of direction or velocity.
Also, the performance of autonomous driving of the vehicle on non-paved roads or field can be enhanced by measuring the inclination of the driving road (for example, ground) and determining the irregularity as an obstacle when the bend curve is abrupt.
This measured inclination of the driving road can be used as information for analyzing the driving performance of the autonomous vehicle or as a parameter for controlling the speed of the vehicle depending on the driving environment of the autonomous vehicle.
Also, the apparatus for detecting ground and obstacle for autonomous mobile vehicle of the present invention is cost-effective since only two laser radars and one processing unit are required.
Fig. 1 is a block diagram showing the apparatus for distinguishing ground and obstacles for an autonomous mobile vehicle according to the present invention.
Fig. 2 is a front and side view showing the state in which two 2D laser radars comprising the apparatus for distinguishing ground and obstacles are installed on the autonomous vehicle.
Fig. 3 is a flow chart showing the process of calculating the actual inclination of the detected object by the apparatus for distinguishing ground and obstacles for an autonomous mobile vehicle.
Fig. 4 conceptually illustrates how the distance data needed for the apparatus for detecting ground and obstacles to calculate the actual inclination of the detected object is obtained.
Fig. 5 illustrates the beam radiated from the 2D laser radars, which are arranged in parallel with the base plane of the autonomous vehicle, when the right and left suspension devices are pressed differently due to an abrupt change of direction of the vehicle.
Description on the numerals in the drawings
1. upper 2D laser radar
2. lower 2D laser radar
10. processing unit
11. distance data receiving part
12. inclination calculating part
13. ground and obstacle determining part
14. transmitting part
20. collision avoiding unit
The apparatus and method for detecting ground and obstacle for autonomous mobile vehicle of the present invention will now be described in detail with reference to the drawings attached.
Fig. 1 is a block diagram showing the apparatus for distinguishing ground and obstacles for an autonomous mobile vehicle according to the present invention, Fig. 2 is a front and side view showing the state in which two 2D laser radars comprising the apparatus for distinguishing ground and obstacles are installed on the autonomous vehicle, Fig. 3 is a flow chart showing the process of calculating the actual inclination of the detected object by the apparatus for distinguishing ground and obstacles for an autonomous mobile vehicle, and Fig. 4 conceptually illustrates how the distance data needed for the apparatus for detecting ground and obstacles to calculate the actual inclination of the detected object is obtained.
As can be seen in the figures, the apparatus for distinguishing ground and an obstacle for autonomous mobile vehicle of the present invention an upper 2D laser radar 1 installed on the front upper portion of the autonomous mobile vehicle arranged with predetermined orientation angle (θ1) with respect to the horizontal base plane of the vehicle, a lower 2D laser radar 2 installed on the front lower portion of the autonomous mobile vehicle at the location vertically below the upper 2D laser radar 1 with a predetermined vertical distance (doffset) and arranged in parallel with the horizontal base plane of the vehicle, and a processing unit 10 installed on the autonomous mobile vehicle for carrying out predetermined data processing.
And the processing unit 10 comprises a distance data receiving part 11 which receives distance data r1, r2 to the object which are detected by the upper 2D laser radar 1 and the lower 2D laser radar 2, an inclination calculating part 12 which calculates actual inclination (g) of the detected object based on the distance data r1, r2 received from the distance data receiving part 11, the orientation angle (θ1) and the vertical distance (doffset), a ground and obstacle determining part 13 which determines whether the detected object is ground or an obstacle by comparing the actual inclination (g) of the detected object received from the inclination calculating part 12 and the predetermined reference inclination, and generates a distance data for a virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar, the distance data being the minimum value of the distance data r1, r2 or the maximum value that corresponding 2D laser radar can have, and a transmitting part 14 which transmits the distance data for the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar, generated by the ground and obstacle determining part 13, to a collision avoiding processing unit 20 of the autonomous mobile vehicle.
Therefore, when the detected object is determined to be an obstacle, the autonomous mobile vehicle can avoid collision through the control of the parts by the collision avoiding processing unit 20.
As shown in Fig. 2, when using 2D laser radar 1, 2 on the autonomous mobile vehicle that can operate on the non-paved road or field, the 2D laser radar 1, 2 are installed on the same vertical axis. The 2D laser radar 1, 2 are oriented in the same direction (front) but with different orientation angle. This is for calculating the actual inclination of the detected object by using the distance data r1, r2 obtained by each 2D laser radar 1, 2. 2D laser radar that can scan more than 100° sidewise is used here.
The apparatus for distinguishing between ground and an obstacle for autonomous mobile vehicle as described above determines whether an object is an obstacle or not as follows.
First, distance data r1, r2 from the upper and lower 2D laser radar 1, 2 installed on the vehicle to the detected object is obtained (step of obtaining distance data).
Then the actual inclination (g) of the detected object is calculated by the inclination calculating part 12 of the apparatus for distinguishing between ground and an obstacle for autonomous mobile vehicle by using the distance data r1, r2, the orientation angle (θ1) of the upper 2D laser radar 1, and the vertical distance (doffset) between the upper 2D laser radar 1 and the lower 2D laser radar 2 (step of calculating inclination).
Finally, the ground and obstacle determining part 13 of the processing unit determines the detected object as an obstacle when the actual inclination (g) of the detected object is larger than the reference inclination, and determines the detected object as ground when the actual inclination (g) of the detected object is smaller than the reference inclination (step of determining ground and an obstacle).
<Example>
One example of the method for distinguishing between ground and an obstacle for autonomous mobile vehicle using the above construction will be described in detail.
First, as shown Fig.3, unprocessed front distance data is obtained by two 2D laser radars 1, 2 which are installed on the autonomous mobile vehicle.
The distance data obtained by the 2D laser radars are transferred to the processing unit 10 for predetermined data processing.
The processing unit 10 checks whether distance data has been received from each of the 2D laser radar 1, 2, and generates variables for storing distance data per angle from each 2D laser radar 1, 2, and variables for storing processed data for the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar. For example, the distance data per angle of the upper 2D laser radar 1 is stored as LRF1, the distance data per angle of the lower 2D laser radar 2 as LRF2, and the variable for the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar as LRF0.
Next, in the process of calculating the actual inclination of the detected object by using the distance data per angle of the each 2D laser radar 1, 2, orientation angle toward the ground of the upper 2D laser radar 1, and the difference of height of the upper and lower 2D laser radars 1, 2, the actual inclination of the detected object is calculated by comparing distance data of the same angel of LRF1 and LRF2.
The method of calculating the actual inclination of the detected object will be described in more detail with reference to Fig. 4.
The difference in vertical direction of the detected objects, dv, is represented by the following formula:
dv = doffset - r1sinθ1 (1)
And the difference in horizontal direction of the detected objects, dh, is represented by the following formula:
dh = r1cosθ1 - r2 (2)
where r1 is the distance data received by the upper 2D laser radar 1, r2 the distance data received by the lower 2D laser radar 2, θ1 the angle of the upper 2D laser radar 1 in the Pitch direction (the angle of orientation toward the ground), and doffset the difference of height of the two 2D laser radars 1, 2 in vertical direction.
The actual inclination of the detected object (g) is calculated by the following formula.
When the actual inclination (g) of the detected object at a certain angle is larger than predetermined reference inclination, the minimum value of the obtained distance data (r1, r2) is stored as a distance data at the angle of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar. When the actual inclination (g) of the detected is smaller than predetermined reference inclination, however, the arbitrary maximum value of the distance that the corresponding 2D laser radar can have is stored as a distance data at the angle of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar.
Also, when the actual inclination (g) of the detected object is larger than predetermined reference inclination, the detected object is determined to be an obstacle and the variable LRF0 of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar is given the minimum value of the distance data at the corresponding angle. On the contrary, when the actual inclination (g) of the detected object is smaller than predetermined reference inclination, the detected object is determined to be the ground and the variable LRF0 of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar is given, as a distance data at the corresponding angle, the arbitrary maximum value of the distance that the corresponding 2D laser radar can have.
Claims (3)
- Apparatus for distinguishing between ground and an obstacle for autonomous mobile vehicle, which comprises:an upper 2D laser radar 1 installed on the front upper portion of the autonomous mobile vehicle arranged with predetermined orientation angle (θ1) with respect to the horizontal base plane of the vehicle,a lower 2D laser radar 2 installed on the front lower portion of the autonomous mobile vehicle at the location vertically below the upper 2D laser radar 1 with a predetermined vertical distance (doffset) and arranged in parallel with the horizontal base plane of the vehicle, anda processing unit 10 installed on the autonomous mobile vehicle for carrying out predetermined data processing,the processing unit 10 comprising:a distance data receiving part 11 which receives distance data r1, r2 to the object which are detected by the upper 2D laser radar 1 and the lower 2D laser radar 2,an inclination calculating part 12 which calculates actual inclination (g) of the detected object based on the distance data r1, r2 received from the distance data receiving part 11, the orientation angle (θ1) and the vertical distance (doffset),a ground and obstacle determining part 13 which determines whether the detected object is ground or an obstacle by comparing the actual inclination (g) of the detected object received from the inclination calculating part 12 and the predetermined reference inclination, and generates a distance data for a virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar, anda transmitting part 14 which transmits the distance data for the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar, generated by the ground and obstacle determining part 13, to a collision avoiding processing unit 20 of the autonomous mobile vehicle.
- A method for distinguishing between ground and an obstacle for autonomous mobile vehicle by using the apparatus for distinguishing between ground and an obstacle for autonomous mobile vehicle of claim 1, which comprises:a step of obtaining distance data in which distance data r1, r2 from the upper 2D laser radar 1 and the lower 2D laser radar 2 to the detected object is obtained by using the upper 2D laser radar 1 and the lower 2D laser radar 2 installed on front side of the autonomous mobile vehicle;a step of calculating inclination in which the actual inclination (g) of the detected object is calculated by the inclination calculating part 12 of the apparatus for distinguishing between ground and an obstacle for autonomous mobile vehicle by using the distance data r1, r2, the orientation angle (θ1) of the upper 2D laser radar 1, and the vertical distance (doffset) between the upper 2D laser radar 1 and the lower 2D laser radar 2; anda step of determining ground and an obstacle in which the ground and obstacle determining part 13 of the processing unit determines the detected object as an obstacle when the actual inclination (g) of the detected object is larger than the reference inclination, and determines the detected object as ground when the actual inclination (g) of the detected object is smaller than the reference inclination.
- The method for distinguishing between ground and an obstacle for autonomous mobile vehicle of claim 2, which further comprises the step which the minimum value of the obtained distance data (r1, r2) is stored as a distance data at the angle of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar when the actual inclination (g) of the detected object at a certain angle is larger than predetermined reference inclination, and the arbitrary maximum value of the distance that the corresponding 2D laser radar can have is stored as a distance data at the angle of the virtual 2D laser radar which is assumed to be arranged on the same location as the lower 2D laser radar when the actual inclination (g) of the detected is smaller than predetermined reference inclination.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/254,099 US8736820B2 (en) | 2009-03-03 | 2010-03-03 | Apparatus and method for distinguishing ground and obstacles for autonomous mobile vehicle |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020090018131A KR100899820B1 (en) | 2009-03-03 | 2009-03-03 | The discriminative apparatus and method of ground/obstacle for autonomous mobile vehicle |
KR10-2009-0018131 | 2009-03-03 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2010101393A2 true WO2010101393A2 (en) | 2010-09-10 |
WO2010101393A3 WO2010101393A3 (en) | 2010-11-04 |
Family
ID=40862588
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2010/001300 WO2010101393A2 (en) | 2009-03-03 | 2010-03-03 | Apparatus and the method for distinguishing ground and obstacles for autonomous mobile vehicle |
Country Status (3)
Country | Link |
---|---|
US (1) | US8736820B2 (en) |
KR (1) | KR100899820B1 (en) |
WO (1) | WO2010101393A2 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102963299A (en) * | 2012-10-31 | 2013-03-13 | 樊红娟 | High-reliability and low-false alarm rate highway automobile anti-collision system and method |
EP2897014A1 (en) * | 2014-01-16 | 2015-07-22 | Volvo Car Corporation | A vehicle adapted for autonomous driving and a method for detecting obstructing objects |
CN105291978A (en) * | 2015-11-27 | 2016-02-03 | 安徽工程大学 | Lane changing assistance early warning system and control method thereof |
Families Citing this family (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101207903B1 (en) | 2010-10-11 | 2012-12-04 | 국방과학연구소 | Apparatus and method for providing the obstacle information of autonomous mobile vehicle |
KR101133037B1 (en) | 2011-12-01 | 2012-04-04 | 국방과학연구소 | Path updating method for collision avoidance of autonomous vehicle and the apparatus |
KR101273245B1 (en) * | 2013-02-26 | 2013-06-11 | 국방과학연구소 | Autonomous vehicle system and path decision method for the same |
US9256852B1 (en) * | 2013-07-01 | 2016-02-09 | Google Inc. | Autonomous delivery platform |
US8825260B1 (en) * | 2013-07-23 | 2014-09-02 | Google Inc. | Object and ground segmentation from a sparse one-dimensional range data |
JP2015106254A (en) * | 2013-11-29 | 2015-06-08 | トヨタ自動車株式会社 | Autonomous moving vehicle, and control method and control program of the same |
JP5962689B2 (en) * | 2014-02-14 | 2016-08-03 | トヨタ自動車株式会社 | Autonomous mobile body and failure determination method thereof |
CN105898003A (en) * | 2014-05-15 | 2016-08-24 | 聚晶半导体股份有限公司 | Anti-collision caution method and system |
KR101610502B1 (en) * | 2014-09-02 | 2016-04-07 | 현대자동차주식회사 | Apparatus and method for recognizing driving enviroment for autonomous vehicle |
JP6365140B2 (en) * | 2014-09-04 | 2018-08-01 | 株式会社Soken | In-vehicle device, in-vehicle system |
JP6270746B2 (en) * | 2015-01-06 | 2018-01-31 | オムロンオートモーティブエレクトロニクス株式会社 | Object detection device and vehicle collision prevention control device |
KR101698130B1 (en) * | 2015-06-11 | 2017-01-20 | 서울대학교산학협력단 | Obstacle detecting apparatus and method using it |
US10093312B2 (en) * | 2015-07-27 | 2018-10-09 | Sharp Kabushiki Kaisha | Obstacle determining apparatus, moving body, and obstacle determining method |
CN108431715B (en) * | 2016-07-21 | 2021-08-10 | 苏州宝时得电动工具有限公司 | Self-moving equipment for automatically identifying front object and identification method thereof |
JP6658413B2 (en) * | 2016-09-07 | 2020-03-04 | 株式会社デンソー | Object detection device |
US10514690B1 (en) | 2016-11-15 | 2019-12-24 | Amazon Technologies, Inc. | Cooperative autonomous aerial and ground vehicles for item delivery |
JP6757676B2 (en) * | 2017-02-14 | 2020-09-23 | 日立建機株式会社 | Transport vehicle and road surface estimation method |
US20180330325A1 (en) | 2017-05-12 | 2018-11-15 | Zippy Inc. | Method for indicating delivery location and software for same |
US10807660B2 (en) | 2018-05-30 | 2020-10-20 | Waymo Llc | Systems and methods for automatic air and electrical connections on autonomous cargo vehicles |
US11643154B2 (en) | 2018-05-30 | 2023-05-09 | Waymo Llc | Systems and methods for automatic air and electrical connections on autonomous cargo vehicles |
CN109669191A (en) * | 2018-11-27 | 2019-04-23 | 河南科技大学 | To landform construction method before vehicle based on single line laser radar |
US11392130B1 (en) | 2018-12-12 | 2022-07-19 | Amazon Technologies, Inc. | Selecting delivery modes and delivery areas using autonomous ground vehicles |
JP7257814B2 (en) * | 2019-02-21 | 2023-04-14 | 日立Astemo株式会社 | Driving path recognition device |
US11560153B2 (en) | 2019-03-07 | 2023-01-24 | 6 River Systems, Llc | Systems and methods for collision avoidance by autonomous vehicles |
US10796562B1 (en) | 2019-09-26 | 2020-10-06 | Amazon Technologies, Inc. | Autonomous home security devices |
WO2021061810A1 (en) | 2019-09-26 | 2021-04-01 | Amazon Technologies, Inc. | Autonomous home security devices |
KR20210061200A (en) | 2019-11-19 | 2021-05-27 | 삼성전자주식회사 | LiDAR device and operating method of the same |
CN110928315A (en) * | 2019-12-20 | 2020-03-27 | 深圳市杉川机器人有限公司 | Autonomous robot and control method thereof |
CN115356747B (en) * | 2022-10-19 | 2023-01-24 | 成都朴为科技有限公司 | Multi-line laser radar obstacle identification method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0687377A (en) * | 1992-09-04 | 1994-03-29 | Yazaki Corp | Monitor for vehicle periphery |
JPH1059120A (en) * | 1996-06-11 | 1998-03-03 | Toyota Motor Corp | Obstruction detecting device and occupant protective device using device thereof |
JP2003057340A (en) * | 2001-08-14 | 2003-02-26 | Denso Corp | Obstacle detecting device |
JP2007178183A (en) * | 2005-12-27 | 2007-07-12 | Mazda Motor Corp | Obstacle detection device for vehicle |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08122060A (en) * | 1994-10-21 | 1996-05-17 | Mitsubishi Electric Corp | Vehicle surrounding monitoring system |
US6963661B1 (en) * | 1999-09-09 | 2005-11-08 | Kabushiki Kaisha Toshiba | Obstacle detection system and method therefor |
US6888622B2 (en) * | 2002-03-12 | 2005-05-03 | Nissan Motor Co., Ltd. | Method for determining object type of reflective object on track |
KR20050054632A (en) * | 2003-12-05 | 2005-06-10 | 기아자동차주식회사 | A back warning system of vehicle and method thereof |
FR2915304B1 (en) * | 2007-04-20 | 2009-06-05 | Thales Sa | METHOD OF CALCULATING APPROACH TRACK FOR AIRCRAFT |
-
2009
- 2009-03-03 KR KR1020090018131A patent/KR100899820B1/en active IP Right Grant
-
2010
- 2010-03-03 US US13/254,099 patent/US8736820B2/en active Active
- 2010-03-03 WO PCT/KR2010/001300 patent/WO2010101393A2/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0687377A (en) * | 1992-09-04 | 1994-03-29 | Yazaki Corp | Monitor for vehicle periphery |
JPH1059120A (en) * | 1996-06-11 | 1998-03-03 | Toyota Motor Corp | Obstruction detecting device and occupant protective device using device thereof |
JP2003057340A (en) * | 2001-08-14 | 2003-02-26 | Denso Corp | Obstacle detecting device |
JP2007178183A (en) * | 2005-12-27 | 2007-07-12 | Mazda Motor Corp | Obstacle detection device for vehicle |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102963299A (en) * | 2012-10-31 | 2013-03-13 | 樊红娟 | High-reliability and low-false alarm rate highway automobile anti-collision system and method |
EP2897014A1 (en) * | 2014-01-16 | 2015-07-22 | Volvo Car Corporation | A vehicle adapted for autonomous driving and a method for detecting obstructing objects |
CN104787044A (en) * | 2014-01-16 | 2015-07-22 | 沃尔沃汽车公司 | Vehicle adapted for autonomous driving and method for detecting obstructing objects |
US9802624B2 (en) | 2014-01-16 | 2017-10-31 | Volvo Car Corporation | Vehicle adapted for autonomous driving and a method for detecting obstructing objects |
CN104787044B (en) * | 2014-01-16 | 2019-04-30 | 沃尔沃汽车公司 | Method suitable for the vehicle of automatic Pilot and for detecting barrier |
CN105291978A (en) * | 2015-11-27 | 2016-02-03 | 安徽工程大学 | Lane changing assistance early warning system and control method thereof |
CN105291978B (en) * | 2015-11-27 | 2016-09-14 | 安徽工程大学 | Vehicle lane change auxiliary early warning system and control method thereof |
Also Published As
Publication number | Publication date |
---|---|
WO2010101393A3 (en) | 2010-11-04 |
KR100899820B1 (en) | 2009-05-27 |
US8736820B2 (en) | 2014-05-27 |
US20110309967A1 (en) | 2011-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2010101393A2 (en) | Apparatus and the method for distinguishing ground and obstacles for autonomous mobile vehicle | |
US7362881B2 (en) | Obstacle detection system and method therefor | |
WO2012050305A2 (en) | Apparatus and method for providing obstacle information in autonomous mobile vehicle | |
US6812831B2 (en) | Vehicle surroundings monitoring apparatus | |
EP1394761B1 (en) | Obstacle detection device and method therefor | |
EP2400315B1 (en) | Travel distance detection device and travel distance detection method | |
CN107991671A (en) | A kind of method based on radar data and vision signal fusion recognition risk object | |
EP1251032A2 (en) | Apparatus and method of recognizing vehicle travelling behind | |
EP1909064A1 (en) | Object detection device | |
CN112567264A (en) | Apparatus and method for acquiring coordinate transformation information | |
JP2007264955A (en) | Lane position detector | |
JP5682735B2 (en) | Three-dimensional object detection device | |
WO2019031137A1 (en) | Roadside object detection device, roadside object detection method, and roadside object detection system | |
CN109901193A (en) | The light of short distance barrier reaches arrangement for detecting and its method | |
JP2012159469A (en) | Vehicle image recognition device | |
CN109522779B (en) | Image processing apparatus and method | |
WO2022114455A1 (en) | Device for correcting position signal of autonomous vehicle by using road surface image information | |
JP2008059323A (en) | Wall detection device | |
JP3925285B2 (en) | Road environment detection device | |
JP3612821B2 (en) | In-vehicle distance measuring device | |
CN109919139B (en) | Road surface condition rapid detection method based on binocular stereo vision | |
JP2012159470A (en) | Vehicle image recognition device | |
JP3586938B2 (en) | In-vehicle distance measuring device | |
US20240054656A1 (en) | Signal processing device, signal processing method, and signal processing system | |
CN109947108B (en) | Method for predicting road condition in front of mobile robot |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10748935 Country of ref document: EP Kind code of ref document: A2 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13254099 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 10748935 Country of ref document: EP Kind code of ref document: A2 |