Vehicle position estimation system, device, method, and camera device
US-2016305794-A1 · Oct 20, 2016 · US
US2018059680A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2018059680-A1 |
| Application number | US-201715688633-A |
| Country | US |
| Kind code | A1 |
| Filing date | Aug 28, 2017 |
| Priority date | Aug 29, 2016 |
| Publication date | Mar 1, 2018 |
| Grant date | — |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A vehicle location recognition device has a correction unit for correcting a position of an own vehicle detected by a vehicle position estimation unit. The correction unit corrects the position of the own vehicle so as to reduce a difference in position between a position of a road object detected by a sensor and a position of a map road object contained in map road object information stored in a memory unit. When there are plural combinations of road objects detected by the sensor and map road objects acquired from the map road object information, the correction unit uses a weight value to adjust a likelihood of each of the combinations, and corrects the position of the own vehicle based on the weighted likelihood. The weight value is increased according to increasing of a magnitude of the likelihood.
Opening claim text (preview).
What is claimed is: 1 . A vehicle location recognition device 1 for detecting and recognizing a current position of an own vehicle, using a computer system including a central processing unit, the computer system being configured to provide: a vehicle position estimation unit which estimates a position of the own vehicle; a road object detection unit which detects a detection point of a road object in acquired image data acquired by and transmitted from a sensor mounted on the own vehicle; a road object estimation unit which estimates a position of the road object detected by the road object detection unit on the basis of the detection point of the road object and the position of the own vehicle; a map road object information acquiring unit which acquires map road object information from a memory unit, the memory unit storing the map road object information, the map road information containing at least position and features of each of map road objects, the map road object information representing each of the map road objects which being present within a detection range of the road object detection unit; a correction unit which corrects the position of the own vehicle estimated by the road object estimation unit so as to reduce a difference between the position of the road object estimated by the road object estimation unit and the position of the map road object contained in the acquired map road object information; and a first likelihood calculation unit which calculates a likelihood X of similarity between the road object and the map road object in each of combinations on the basis of the position and features of the map road object, each of the combinations being composed of the road object detected by the road object detection unit and the map road object in the map road information acquired by the map road object information acquiring unit, and the likelihood X representing a degree in similarity between the road object and the map road object in each of the combinations, wherein the correction unit weights a correction value of each of the combinations so that the correction value increases according to increasing of the likelihood X of the combination, and corrects the position of the own vehicle by using the correction value of each of the combinations. 2 . The vehicle location recognition device according to claim 1 , wherein the map road object information acquiring unit acquires map road object information from the memory unit, the map road information containing, as the features of the map road object, at least one feature selected from a position, a color, and a pattern of the map road object. 3 . The vehicle location recognition device according to claim 1 , wherein the first likelihood calculation unit calculates a likelihood of each of the features of the map road object, and integrates the calculated likelihoods of the features of the map road object, and calculates the likelihood X of the combination on the basis of the integrated value of the calculated likelihoods. 4 . The vehicle location recognition device according to claim 2 , wherein the first likelihood calculation unit calculates a likelihood of each of the features of the map road object, and integrates the calculated likelihoods of the features of the map road object, and calculates the likelihood X of the combination on the basis of the integrated value of the calculated likelihoods. 5 . The vehicle location recognition device according to claim 3 , further comprising a state amount acquiring unit which acquires a state amount, the state amount represents one of a magnitude of a slope of the road on which the own vehicle drives, a magnitude of a curvature of the road, and an estimation error of the position of the own vehicle detected by the vehicle position estimation unit, wherein when the state amount acquired by the state amount acquiring unit is not less than a threshold value, the first likelihood calculation unit avoids using the feature, which corresponds to the state amount of not less than the threshold value, in the calculation of the likelihood X of the combinations. 6 . The vehicle location recognition device according to claim 4 , further comprising a state amount acquiring unit which acquires a state amount, the state amount represents one of a magnitude of a slope of the road on which the own vehicle drives, a magnitude of a curvature of the road, and an estimation error of the position of the own vehicle detected by the vehicle position estimation unit, wherein when the state amount acquired by the state amount acquiring unit is not less than a threshold value, the first likelihood calculation unit avoids using the feature, which corresponds to the state amount of not less than the threshold value, in the calculation of the likelihood X of the combinations. 7 . The vehicle location recognition device according to claim 1 , further comprising: a speed calculation unit which calculates a speed in a fixed coordinate system of the road object detected by the road object detection unit; and a second likelihood calculation unit which calculates a likelihood Y which represents a degree of moving of the road object detected by the road object detection unit so that the likelihood Y increases according to reducing the speed of the road object calculated by the speed calculation unit, wherein the first likelihood calculation unit calculates the likelihood X of the combination so that the likelihood X increases according to increasing of the likelihood Y. 8 . The vehicle location recognition device according to claim 2 , further comprising: a speed calculation unit which calculates a speed in a fixed coordinate system of the road object detected by the road object detection unit; and a second likelihood calculation unit which calculates a likelihood Y which represents a degree of moving of the road object detected by the road object detection unit so that the likelihood Y increases according to reducing the speed of the road object calculated by the speed calculation unit, wherein the first likelihood calculation unit calculates the likelihood X of the combination so that the likelihood X increases according to increasing of the likelihood Y. 9 . The vehicle location recognition device according to claim 3 , further comprising: a speed calculation unit which calculates a speed in a fixed coordinate system of the road object detected by the road object detection unit; and a second likelihood calculation unit which calculates a likelihood Y which represents a degree of moving of the road object detected by the road object detection unit so that the likelihood Y increases according to reducing the speed of the road object calculated by the speed calculation unit, wherein the first likelihood calculation unit calculates the likelihood X of the combination so that the likelihood X increases according to increasing of the likelihood Y. 10 . The vehicle location recognition device according to claim 4 , further comprising: a speed calculation unit which calculates a speed in a fixed coordinate system of the road object detected by the road object detection unit; and a second likelihood calculation unit which calculates a likelihood Y which represents a degree of moving of the road object detected by the road object detection unit so that the likelihood Y increases according to reducing the speed of the road object calculated by the speed calculation unit, wherein the first likelihood calculation unit calculates the likelihood X of the combination so that the likelihood X increases according to increasing of the likelihood Y. 11 . The vehicle location recognition device according
of land vehicles · CPC title
whereby the position solution is constrained to lie upon a particular curve or surface, e.g. for locomotives on railway tracks · CPC title
Combination of radar systems with cameras · CPC title
Map- or contour-matching · CPC title
of land vehicles · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.