Patent · US2020385018A1 · A1 · US
Path generation device and vehicle control system
- (11) Publication number
- US2020385018A1
- (21) Application number
- 16/967,282
- (22) Filing date
- 2018-03-23
- (30) Priority date
- 2018-03-23
- (43) Publication date
- 2020-12-10
- (52) CPC
- B60W Conjoint control of vehicle sub-units of different type or different function; control systems specially adapted for hybrid vehicles; road vehicle drive control systems for purposes not related to the control of a particular sub-unit: 60/0011, 2050/0025, 2552/30, 2710/207, 30/045, 40/072
- G01C Measuring distances, levels or bearings; surveying; navigation; gyroscopic instruments; photogrammetry or videogrammetry: 21/3407
- G08G Traffic control systems: 1/167
- (73) Assignee
- MITSUBISHI ELECTRIC CORP
- (54) Title
- Path generation device and vehicle control system
- (57) Abstract
A path generation device and a vehicle control system capable of inhibiting generation of paths that make a vehicle unstable are provided. The path generation device includes a path generator that generates a plurality of paths along which a vehicle is to travel, in association with each piece of environment measurement data about a travel environment of the vehicle detected by a plurality of detectors; a reliability setting part that sets, for each of the generated paths, the reliability of the path in itself, the reliability corresponding to the degree to which a variation in the path falls within a predetermined range, and a path-weight setting part that sets the weight of each path on the basis of the reliability of the path.
- Full text
- View on Google Patents
Claims (1)
- A path generation device comprising: one or more first processors configured to execute a first program; and one or more first memories configured to store the first program which, when the first program is executed by the one or more first processors, causes the one or more first processors to perform first processes comprising: generating a plurality of paths along which a vehicle should travel, in accordance with each piece of environment measurement data about a travel environment of the vehicle detected by a plurality of detectors; setting, for each of the plurality of paths generated, reliability of the path in itself, the reliability corresponding to a degree to which a variation in the path falls within a predetermined range; and setting a weight for each of the plurality of paths on the basis of the reliability of the path in itself. 2. The path generation device according to claim 1, wherein the process of generating the path is the process of generating a plurality of paths sequentially over time, and the process of setting the reliability is the process of setting the reliability of each path in itself to be lower in a case where a variation in the path from a corresponding path generated before the path is greater than a first threshold value than in a case where the variation is smaller than the first threshold value. 3. The path generation device according to claim 1, wherein the set weight is smaller in a case where the reliability of the path in itself is lower than a second threshold value than in a case where the reliability of the path in itself is higher than the second threshold value. 4. The path generation device according to claim 1, wherein a lane for the path is estimated based on the environment measurement data, and the set weight is smaller in a case where the path deviates from the lane than in a case where the path does not deviate from the lane. 5. The path generation device according to claim 1, wherein the first process further comprises: generating a single target path, using the plurality of paths whose weights have been set. 6. The path generation device according to claim 5, wherein the process of generating the target path is the process of generating the single target path by weighted averaging using the plurality of paths whose weights have been set. 7. The path generation device according to claim 1, wherein the first process further comprises: setting an evaluation function, using the plurality of paths whose weights have been set; setting predicted upper and lower limit values of a vehicle state quantity of the vehicle as constraints; setting the vehicle state quantity at a present moment as an initial value for optimization; and optimizing the evaluation function, using the constraints and the initial value as conditions for optimization. 8. A vehicle control system comprising: the path generation device according to claim 5; and a vehicle control device, the vehicle control device including: one or more second processors configured to execute a second program; and one or more second memories configured to store the second program which, when the second program is executed by the one or more second processors, causes the one or more second processors to perform second processes including: calculating a target steering amount by which the vehicle is to travel along the target path, using the single target path generated by the path generation device and travel state data about a travel state of the vehicle. 9. The vehicle control system according to claim 8, wherein the process of calculating the target steering amount is the process of calculating the target steering amount, using a vehicle state quantity of the vehicle in the single target path, the vehicle state quantity being estimated based on a curvature of the target path, an amount of lateral deviation, an amount of angular deviation, and the travel state data at a forward look ahead point that is set forward of the vehicle. 10. A vehicle control system comprising: the path generation device according to claim 1; and a vehicle control device, the vehicle control device including: one or more second processors configured to execute a second program; and one or more second memories configured to store the second program which, when the second program is executed by the one or more second processors, causes the one or more second processors to perform second processes including: generating a single target path, using the plurality of paths whose weights have been set; and calculating, using the single target path and travel state data about a travel state of the vehicle, a target steering amount by which the vehicle is to travel along the target path. 11. A vehicle control system comprising: the path generation device according to claim 1; and a vehicle control device, the vehicle control device including: one or more second processors configured to execute a second program; and one or more second memories configured to store the second program which, when the second program is executed by the one or more second processors, causes the one or more second processors to perform second processes including: setting an evaluation function, using the plurality of paths whose weights have been set by the path generation device; setting predicted upper and lower limit values of a vehicle state quantity of the vehicle as constraints; setting the vehicle state quantity at a present moment as an initial value for optimization; and optimizing the evaluation function, using the constraints and the initial value as conditions for optimization, and calculating a target steering amount by which the vehicle is to travel along a target path indicated by the optimized evaluation function. 12. A vehicle control system comprising: the path generation device according to claim 7; and a vehicle control device, the vehicle control device including: one or more second processors configured to execute a second program; and one or more second memories configured to store the second program which, when the second program is executed by the one or more second processors, causes the one or more second processors to perform second processes including: calculating a target steering amount by which the vehicle is to travel along a target path indicated by the optimized evaluation function, using the optimized evaluation function and travel state data about a travel state of the vehicle. 13. The vehicle control system according to claim 12, wherein the process of calculating the target steering amount is the process of calculating the target steering amount, using the optimized evaluation function and a vehicle state quantity of the vehicle, the vehicle state quantity being estimated based on the travel state data.
Citations (11)
- US10843711B2
- US10877482B2
- US2008270018A1
- US2009093924A1
- US2012323473A1
- US2017123434A1
- US2017261984A1
- US2018022382A1
- US2018136662A1
- US2018292834A1
- US2020223449A1
Record as JSON
{
"publication_number": "US2020385018A1",
"country": "US",
"kind": "A1",
"title": "Path generation device and vehicle control system",
"abstract": "A path generation device and a vehicle control system capable of inhibiting generation of paths that make a vehicle unstable are provided. The path generation device includes a path generator that generates a plurality of paths along which a vehicle is to travel, in association with each piece of environment measurement data about a travel environment of the vehicle detected by a plurality of detectors; a reliability setting part that sets, for each of the generated paths, the reliability of the path in itself, the reliability corresponding to the degree to which a variation in the path falls within a predetermined range, and a path-weight setting part that sets the weight of each path on the basis of the reliability of the path.",
"claims": [
"1. A path generation device comprising: one or more first processors configured to execute a first program; and one or more first memories configured to store the first program which, when the first program is executed by the one or more first processors, causes the one or more first processors to perform first processes comprising: generating a plurality of paths along which a vehicle should travel, in accordance with each piece of environment measurement data about a travel environment of the vehicle detected by a plurality of detectors; setting, for each of the plurality of paths generated, reliability of the path in itself, the reliability corresponding to a degree to which a variation in the path falls within a predetermined range; and setting a weight for each of the plurality of paths on the basis of the reliability of the path in itself. 2. The path generation device according to claim 1, wherein the process of generating the path is the process of generating a plurality of paths sequentially over time, and the process of setting the reliability is the process of setting the reliability of each path in itself to be lower in a case where a variation in the path from a corresponding path generated before the path is greater than a first threshold value than in a case where the variation is smaller than the first threshold value. 3. The path generation device according to claim 1, wherein the set weight is smaller in a case where the reliability of the path in itself is lower than a second threshold value than in a case where the reliability of the path in itself is higher than the second threshold value. 4. The path generation device according to claim 1, wherein a lane for the path is estimated based on the environment measurement data, and the set weight is smaller in a case where the path deviates from the lane than in a case where the path does not deviate from the lane. 5. The path generation device according to claim 1, wherein the first process further comprises: generating a single target path, using the plurality of paths whose weights have been set. 6. The path generation device according to claim 5, wherein the process of generating the target path is the process of generating the single target path by weighted averaging using the plurality of paths whose weights have been set. 7. The path generation device according to claim 1, wherein the first process further comprises: setting an evaluation function, using the plurality of paths whose weights have been set; setting predicted upper and lower limit values of a vehicle state quantity of the vehicle as constraints; setting the vehicle state quantity at a present moment as an initial value for optimization; and optimizing the evaluation function, using the constraints and the initial value as conditions for optimization. 8. A vehicle control system comprising: the path generation device according to claim 5; and a vehicle control device, the vehicle control device including: one or more second processors configured to execute a second program; and one or more second memories configured to store the second program which, when the second program is executed by the one or more second processors, causes the one or more second processors to perform second processes including: calculating a target steering amount by which the vehicle is to travel along the target path, using the single target path generated by the path generation device and travel state data about a travel state of the vehicle. 9. The vehicle control system according to claim 8, wherein the process of calculating the target steering amount is the process of calculating the target steering amount, using a vehicle state quantity of the vehicle in the single target path, the vehicle state quantity being estimated based on a curvature of the target path, an amount of lateral deviation, an amount of angular deviation, and the travel state data at a forward look ahead point that is set forward of the vehicle. 10. A vehicle control system comprising: the path generation device according to claim 1; and a vehicle control device, the vehicle control device including: one or more second processors configured to execute a second program; and one or more second memories configured to store the second program which, when the second program is executed by the one or more second processors, causes the one or more second processors to perform second processes including: generating a single target path, using the plurality of paths whose weights have been set; and calculating, using the single target path and travel state data about a travel state of the vehicle, a target steering amount by which the vehicle is to travel along the target path. 11. A vehicle control system comprising: the path generation device according to claim 1; and a vehicle control device, the vehicle control device including: one or more second processors configured to execute a second program; and one or more second memories configured to store the second program which, when the second program is executed by the one or more second processors, causes the one or more second processors to perform second processes including: setting an evaluation function, using the plurality of paths whose weights have been set by the path generation device; setting predicted upper and lower limit values of a vehicle state quantity of the vehicle as constraints; setting the vehicle state quantity at a present moment as an initial value for optimization; and optimizing the evaluation function, using the constraints and the initial value as conditions for optimization, and calculating a target steering amount by which the vehicle is to travel along a target path indicated by the optimized evaluation function. 12. A vehicle control system comprising: the path generation device according to claim 7; and a vehicle control device, the vehicle control device including: one or more second processors configured to execute a second program; and one or more second memories configured to store the second program which, when the second program is executed by the one or more second processors, causes the one or more second processors to perform second processes including: calculating a target steering amount by which the vehicle is to travel along a target path indicated by the optimized evaluation function, using the optimized evaluation function and travel state data about a travel state of the vehicle. 13. The vehicle control system according to claim 12, wherein the process of calculating the target steering amount is the process of calculating the target steering amount, using the optimized evaluation function and a vehicle state quantity of the vehicle, the vehicle state quantity being estimated based on the travel state data."
],
"cpc": [
"B60W 60/0011",
"B60W 2050/0025",
"B60W 2552/30",
"B60W 2710/207",
"B60W 30/045",
"B60W 40/072",
"G01C 21/3407",
"G08G 1/167"
],
"assignees": [
"MITSUBISHI ELECTRIC CORP"
],
"filing_date": "2018-03-23",
"publication_date": "2020-12-10",
"priority_date": "2018-03-23",
"application_number": "US-201816967282-A",
"family_id": "64480570",
"citations": [
"US10843711B2",
"US10877482B2",
"US2008270018A1",
"US2009093924A1",
"US2012323473A1",
"US2017123434A1",
"US2017261984A1",
"US2018022382A1",
"US2018136662A1",
"US2018292834A1",
"US2020223449A1"
]
}
Record 748 of 5,000 in Patents full text (MLC-0201). Request the full dataset.