Method of generating optimum parking path of unmanned driving vehicle, and unmanned driving vehicle adopting the method

• US 9,254,870 B2
• Filed: 05/13/2014
• Issued: 02/09/2016
• Est. Priority Date: 11/08/2013
• Status: Active Grant

• Current Assignee: Hanwha Aerospace Co., Ltd. (Hanwha Corporation)
• Original Assignee: Hanwha Techwin Co., Ltd. (Hanwha Corporation)
• Inventors: Lee, Jin Han
• Primary Examiner(s): Black, Thomas G
• Assistant Examiner(s): LI, CE LI
• Application Number:
  US14/276,089
• Publication Number:
  US 20150134185A1
• Time in Patent Office: 637 Days
• US Class Current: 1/1
• CPC Class Codes: B62D 15/0285 Parking performed automatically
• CPC Class Codes: G05D 1/0214 in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13

Abstract

A method of generating an optimum parking path of an unmanned driving vehicle which is performed by a controller in the unmanned driving vehicle, wherein the controller changes a moving distance for a plurality of operations in a reference parking path, finds a parking path in which an average obstacle distance, which is an average distance between at least one near-to-path obstacle and the unmanned driving vehicle, is longest among a plurality of candidate parking paths, and sets the parking path having the longest average obstacle distance, as an optimum parking path in response to the longest average obstacle distance being longer than a predetermined limited distance.

Claims

1. A method of generating an optimum parking path of an unmanned driving vehicle, which is performed by a controller in the unmanned driving vehicle, the method comprising:

generating a reference parking path by selectively combining a plurality of operations which comprise head-in straight driving, head-out straight driving, head-in left turning, head-out left turning, head-in right turning, and head-out right turning;

changing a moving distance in the reference parking path to find a parking path in which an average obstacle distance, which is an average distance between at least one near-to-path obstacle and the unmanned driving vehicle, is longest among a plurality of candidate parking paths;

setting the parking path having the longest average obstacle distance, as the optimum parking path in response to the longest average obstacle distance being longer than a predetermined limited distance; and

controlling the unmanned driving vehicle to perform a parking operation based on the optimum parking path,

wherein the changing the moving distance further comprises;

obtaining the average distance between the at least one near-to-path obstacle and the unmanned driving vehicle in one parking path,

wherein the obtaining the average distance between the at least one near-to-path obstacle and the unmanned driving vehicle in one parking path comprises;

calculating a shortest distance between the at least one near-to-path obstacle and the unmanned driving vehicle in respective positions when assuming that the positions of the unmanned driving vehicle are disposed to overlap each other along the parking path; and

totaling results of the calculated shortest distance, and setting a value which is obtained by the totaling of the results as the average distance.

2. The method of claim 1, wherein in the calculating the shortest distance between the at least one near-to-path obstacle and the unmanned driving vehicle when assuming that the positions of the unmanned driving vehicle are disposed to overlap each other along the parking path, and

wherein the shortest distance has a negative value and is a shortest distance between an outer surface of the unmanned driving vehicle and the at least one near-to-path obstacle in response to the at least one near-to-path obstacle being present inside the unmanned driving vehicle in a location.

3. A method of generating an optimum parking path of an unmanned driving vehicle, which is performed by a controller in the unmanned driving vehicle, the method comprising:

generating a reference parking path by selectively combining a plurality of operations which comprise head-in straight driving, head-out straight driving, head-in left turning, head-out left turning, head-in right turning, and head-out right turning;

changing a moving distance in the reference parking path to find a parking path in which an average obstacle distance, which is an average distance between at least one near-to-path obstacle and the unmanned driving vehicle, is longest among a plurality of candidate parking paths;

setting the parking path having the longest average obstacle distance, as the optimum parking path in response to the longest average obstacle distance being longer than a predetermined limited distance; and

controlling the unmanned driving vehicle to perform a parking operation based on the optimum parking path,

wherein the changing the moving distance comprises;

calculating a reference average obstacle distance, which is an average distance between the at least one near-to-path obstacle and the unmanned driving vehicle in the reference parking path;

changing respective moving distances in the reference parking path;

calculating a first average obstacle distance which is the first average distance between the at least one near-to-path obstacle and the unmanned driving vehicle such that a first parking path is found in which the first average obstacle distance is longer than the reference average obstacle distance; and

setting the first parking path as the parking path having the longest average obstacle distance in response to a difference between the reference average obstacle distance and the first average obstacle distance being less than a set convergence distance.

4. The method of claim 3, wherein the changing the moving distance comprises:

setting the first parking path as a new reference parking path in response to a difference between the reference average obstacle distance and the first average obstacle distance being not less than the set convergence distance; and

performing the calculating the reference average obstacle distance, the changing respective moving distances in the reference parking path, the setting the first parking path as the parking path having the longest average obstacle distance, and the setting the first parking path as the new reference parking path using the new reference parking path as the reference parking path.

5. The method of claim 4, wherein additional conditions for finding the first parking path in the changing respective moving distances in the reference parking path are used such that:

a deviation between a X-axis coordinate of the unmanned driving vehicle at a virtual arrival location and a X-axis coordinate of the unmanned driving vehicle at a target arrival location is less than a X set limit value;

a deviation between a Y-axis coordinate of the unmanned driving vehicle at the virtual arrival location and a Y-axis coordinate of the unmanned driving vehicle at the target arrival location is less than a Y set limit value and;

a deviation between a directed angle of orientation of the unmanned driving vehicle at the virtual arrival location and a directed angle of orientation of the unmanned driving vehicle at the target arrival location is less than a directed angle set limit value.

6. The method of claim 4, wherein the changing respective moving distances in the reference parking path comprises:

calculating a reduced average obstacle distance in a reduced path among the plurality of candidate parking paths, which is a reduced average distance between the at least one near-to-path obstacle and the unmanned driving vehicle in the reduced path, wherein the reduced path is obtained as a result of reducing respective moving distances in the reference parking path by a reference set distance;

calculating an extended average obstacle distance in an extended path among the plurality of candidate parking paths, which is an extended average distance between the at least one near-to-path obstacle and the unmanned driving vehicle in the extended path, wherein the extended path is obtained as a result of extending respective moving distances in the reference parking path by the reference set distance;

changing the respective moving distances based on a result of comparing the reduced average obstacle distance in the reduced path to the extended average obstacle distance in the extended path; and

calculating the first average obstacle distance, which is the first average distance between the at least one near-to-path obstacle and the unmanned driving vehicle such that the first parking path is found in which the first average obstacle distance is longer than the reference average obstacle distance.

7. The method of claim 6, wherein in the changing respective moving distances, the respective moving distances in the reduced path is reduced in response to the reduced average obstacle distance in the reduced path being longer than the extended average obstacle distance in the extended path, and

wherein the first average obstacle distance, which is the first average distance between the at least one near-to-path obstacle and the unmanned driving vehicle, is calculated such that the first parking path is found in which the first average obstacle distance is longer than the reference average obstacle distance in response to the respective moving distances in the reduced path being reduced.

8. The method of claim 7, wherein in the changing respective moving distances, a rate of reducing the moving distance is proportional to a difference between the reduced average obstacle distance in the reduced path and the extended average obstacle distance in the extended path in response to respective moving distances being reduced in the reduced path.

9. The method of claim 6, wherein in the changing respective moving distances, in response to the extended average obstacle distance in the extended path being longer than the reduced average obstacle distance in the reduced path, the respective moving distances in the extended path are extended, and

wherein the first average obstacle distance, which is the first average distance between the at least one near-to-path obstacle and the unmanned driving vehicle, is calculated such that the first parking path is found, in which the first average obstacle distance is longer than the reference average obstacle distance.

10. The method of claim 9, wherein in the changing respective moving distances, a rate of extending the moving distance is proportional to a difference between the reduced average obstacle distance in the reduced path and the extended average obstacle distance in the extended path in response to respective moving distances being extended in the extended path.

11. An unmanned driving vehicle comprising:

a controller which is configured to execute;

generating a reference parking path by selectively combining a plurality of operations which comprise head-in straight driving, head-out straight driving, head-in left turning, head-out left turning, head-in right turning, and head-out right turning;

changing a moving distance in the reference parking path to find a parking path in which an average obstacle distance, which is an average distance between at least one near-to-path obstacle and the unmanned driving vehicle, is longest among a plurality of candidate parking paths;

setting the parking path having the longest average obstacle distance, as an optimum parking path, in response to the longest average obstacle distance being longer than a predetermined limited distance; and

performing a parking operation based on the optimum parking path,

wherein, in order to obtain the average distance between the at least one near-to-path obstacle and the unmanned driving vehicle in the parking path, the controller is configured to calculate a shortest distance between the at least one near-to-path obstacle and the unmanned driving vehicle in respective locations when assuming that positions of the unmanned driving vehicle are disposed to overlap with each other along the parking path , and total results of the calculated shortest distance, and set a value that is obtained by the totaling of the results as the average distance.