Patent US6718259B1 successfully refreshed from Google Patents.
US6718259B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Adaptive Kalman filter method for accurate estimation of forward path geometry of an automobile
Assignee: HRL Laboratories LLC
•
Filing: 2002-10-02
•
Granted: 2004-04-06
•
Expires: 2022-10-02
Abstract
Abstract The present invention provides a method and apparatus for estimation of vehicle forward path geometry utilizing an adaptive Kalman filter bank and a two-clothoid road model. The invention provides that each of a plurality of Kalman filters, utilizing the latest available measurement vector Yk at time k, estimates the state vector Xk and error covariance matrix Pk. The outputs of filter 504a, 504b, and 504c denoted as as Xk<j >and Pk<j>, are provided to a plurality of weighting elements, which calculate weight factors, Wk<j >506a, 506b, and 506c for each filter. The weight factor of each filter is the probability that the upcoming road geometry matches the road model hypothesized in the filter. After being assigned a weighted value, the weighted value road models are fused in a fusion element 508, and a weighted output road geometry model is provided.
Inventors
- 👤 Deepak Khosla
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-31 02:45
CPC Classifications
G; G01; G01C; G01C21/00; G01C21/26; G05; G05D; G05D1/00; G05D1/02; G05D1/021; G05D1/0212; G06; G06V; G06V20/00; G06V20/50; G06V20/56; G06V20/588; G08; G08G; G08G1/00; G08G1/16; G08G1/166; G08G1/167; B; B60; B60W; B60W50/00; B60W2050/0001; B60W2050/0043; B60W2050/0052; B60W2552/00; B60W2552/30; B60W2552/53
Claims Analysis
Total Claims: 60
Claim 1
Independent Claim
102 words
An apparatus for dynamically predicting road geometry comprising: i. a bank of filters configured to receive current environmental data from at least one sensor and to perform an estimation using the current environmental data, and to provide a filter output from each filter; ii. a weighting element configured to receive the filter output from the bank of filters and to ascribe a weighted value to each filter output based on a relevance of the filter, thereby providing weighted outputs; iii. a fusing element configured to fuse the weighted outputs into a single output; whereby the output describes a vehicle forward path estimate.
Claim 2
Independent Claim
102 words
An apparatus for dynamically predicting road geometry comprising: i. a bank of filters configured to receive current environmental data from at least one sensor and to perform an estimation using the current environmental data, and to provide a filter output from each filter; ii. a weighting element configured to receive the filter output from the bank of filters and to ascribe a weighted value to each filter output based on a relevance of the filter, thereby providing weighted outputs; iii. a fusing element configured to fuse the weighted outputs into a single output; whereby the output describes a vehicle forward path estimate.
Claim 3
Dependent Claim
47 words
An apparatus for dynamically predicting road geometry as set forth in claim 1 , wherein the bank of filters is further configured to receive a previous vehicle path estimate and to recursively perform the estimation based on the current environmental data and the previous vehicle path estimate.
Claim 4
Dependent Claim
26 words
An apparatus for dynamically predicting road geometry as set forth in claim 2 , wherein each filter in the bank of filters is a Kalman filter.
Claim 5
Dependent Claim
23 words
An apparatus for dynamically predicting road geometry as set forth in claim 3 , wherein the bank of filters includes three Kalman filters.
Claim 6
Dependent Claim
29 words
An apparatus for dynamically predicting road geometry as set forth in claim 4 , wherein the configuration of the bank of filters is based on a polynomial road model.
Claim 7
Dependent Claim
24 words
An apparatus for dynamically predicting road geometry as set forth in claim 5 , wherein the polynomial road model is a two-clothoid road model.
Claim 8
Dependent Claim
30 words
An apparatus for dynamically predicting road geometry as set forth in claim 6 , wherein each filter is tuned to a different class of geometry within the two-clothoid road model.
Claim 9
Dependent Claim
41 words
An apparatus for dynamically predicting road geometry as set forth in claim 7 , wherein the different classes of geometry include a constant geometry road section, an upcoming transition in the far range, and an upcoming transition in the near range.
Claim 10
Dependent Claim
38 words
An apparatus for dynamically predicting road geometry as set forth in claim 8 , wherein the weighting element ascribes weighted values based on the posterior probabilities of a fit between the filter and the forward vehicle path estimate.
Claim 11
Dependent Claim
37 words
An apparatus for dynamically predicting road geometry as set forth in claim 9 , wherein the at least one sensor is a device selected from a group consisting of imaging devices, GPS/map systems, laser sensors, and radars.
Claim 12
Dependent Claim
41 words
An apparatus for dynamically predicting road geometry as set forth in claim 10 , wherein the output of the apparatus is configured for use by other automotive systems selected from a group consisting of driver assistance systems and vehicle safety systems.
Claim 13
Dependent Claim
25 words
An apparatus for dynamically predicting road geometry as set forth in claim 1 wherein each filter in the bank of filters is a Kalman filter.
Claim 14
Dependent Claim
29 words
An apparatus for dynamically predicting road geometry as set forth in claim 1 , wherein the configuration of the bank of filters is based on a polynomial road model.
Claim 15
Dependent Claim
24 words
An apparatus for dynamically predicting road geometry as set forth in claim 13 , wherein the polynomial road model is a two-clothoid road model.
Claim 16
Dependent Claim
30 words
An apparatus for dynamically predicting road geometry as set forth in claim 1 , wherein each filter is tuned to a different class of geometry within the two-clothoid road model.
Claim 17
Dependent Claim
41 words
An apparatus for dynamically predicting road geometry as set forth in claim 15 , wherein the different classes of geometry include a constant geometry road section, an upcoming transition in the far range, and an upcoming transition in the near range.
Claim 18
Dependent Claim
38 words
An apparatus for dynamically predicting road geometry as set forth in claim 1 , wherein the weighting element ascribes weighted values based on the posterior probabilities of a fit between the filter and the forward vehicle path estimate.
Claim 19
Dependent Claim
37 words
An apparatus for dynamically predicting road geometry as set forth in claim 1 , wherein the at least one sensor is a device selected from a group consisting of imaging devices, GPS/map systems, laser sensors, and radars.
Claim 20
Dependent Claim
41 words
An apparatus for dynamically predicting road geometry as set forth in claim 1 , wherein the output of the apparatus is configured for use by other automotive systems selected from a group consisting of driver assistance systems and vehicle safety systems.
Claim 21
Dependent Claim
96 words
A computer program product for dynamically predicting road geometry, the computer program product comprising means, stored on computer readable medium, for: i. filtering current environmental data from at least one sensor and performing an estimation using the current environmental data, and outputting a filter output from each filter; ii. weighing the filter output from the bank of filters and ascribing a weighted value to each filter output based on a relevance of the filter, thereby providing weighted outputs; iii. fusing the weighted outputs into a single output; whereby the output describes a vehicle forward path estimate.
Claim 22
Dependent Claim
96 words
A computer program product for dynamically predicting road geometry, the computer program product comprising means, stored on computer readable medium, for: i. filtering current environmental data from at least one sensor and performing an estimation using the current environmental data, and outputting a filter output from each filter; ii. weighing the filter output from the bank of filters and ascribing a weighted value to each filter output based on a relevance of the filter, thereby providing weighted outputs; iii. fusing the weighted outputs into a single output; whereby the output describes a vehicle forward path estimate.
Claim 23
Dependent Claim
48 words
A computer program product for dynamically predicting road geometry as set forth in claim 20 , wherein means for filtering is further configured to receive a previous vehicle path estimate and to recursively perform the estimation based on the current environmental data and the previous vehicle path estimate.
Claim 24
Dependent Claim
29 words
A computer program product for dynamically predicting road geometry as set forth in claim 21 , wherein filters used in the filtering step include a bank of Kalman filters.
Claim 25
Dependent Claim
25 words
A computer program product for dynamically predicting road geometry as set forth in claim 22 , wherein the bank of filters includes three Kalman filters.
Claim 26
Dependent Claim
29 words
A computer program product for dynamically predicting road geometry as set forth in claim 23 , wherein the bank of filters is configured based on a polynomial road model.
Claim 27
Dependent Claim
26 words
A computer program product for dynamically predicting road geometry as set forth in claim 24 , wherein the polynomial road model is a two-clothoid road model.
Claim 28
Dependent Claim
37 words
A computer program product for dynamically predicting road geometry as set forth in claim 25 , wherein each filter in the bank of filters is tuned to a different class of geometry within the two-clothoid road model.
Claim 29
Dependent Claim
43 words
A computer program product for dynamically predicting road geometry as set forth in claim 26 , wherein the different classes of geometry include a constant geometry road section, an upcoming transition in the far range, and an upcoming transition in the near range.
Claim 30
Dependent Claim
41 words
A computer program product for dynamically predicting road geometry as set forth in claim 27 , wherein the means for weighing ascribes weighted values based on the posterior probabilities of a fit between the filter and the forward vehicle path estimate.
Claim 31
Dependent Claim
44 words
A computer program product for dynamically predicting road geometry as set forth in claim 28 , wherein the environmental data is received from at least one sensor is a device selected from a group consisting of imaging devices, GPS/map systems, laser sensors, and radars.
Claim 32
Dependent Claim
39 words
A computer program product for dynamically predicting road geometry as set forth in claim 29 , wherein the output is configured for use by automotive systems selected from a group consisting of driver assistance systems and vehicle safety systems.
Claim 33
Dependent Claim
28 words
A computer program product for dynamically predicting road geometry as set forth in claim 20 wherein filters used in the filtering step include a bank of Kalman filters.
Claim 34
Dependent Claim
31 words
A computer program product for dynamically predicting road geometry as set forth in claim 20 , wherein the configuration of the bank of filters is based on a polynomial road model.
Claim 35
Dependent Claim
26 words
A computer program product for dynamically predicting road geometry as set forth in claim 32 , wherein the polynomial road model is a two-clothoid road model.
Claim 36
Dependent Claim
32 words
A computer program product for dynamically predicting road geometry as set forth in claim 20 , wherein each filter is tuned to a different class of geometry within the two-clothoid road model.
Claim 37
Dependent Claim
43 words
A computer program product for dynamically predicting road geometry as set forth in claim 34 , wherein the different classes of geometry include a constant geometry road section, an upcoming transition in the far range, and an upcoming transition in the near range.
Claim 38
Dependent Claim
41 words
A computer program product for dynamically predicting road geometry as set forth in claim 20 , wherein the means for weighing ascribes weighted values based on the posterior probabilities of a fit between the filter and the forward vehicle path estimate.
Claim 39
Dependent Claim
44 words
A computer program product for dynamically predicting road geometry as set forth in claim 20 , wherein the environmental data is received from at least one sensor is a device selected from a group consisting of imaging devices, GPS/map systems, laser sensors, and radars.
Claim 40
Dependent Claim
39 words
A computer program product for dynamically predicting road geometry as set forth in claim 20 , wherein the output is configured for use by automotive systems selected from a group consisting of driver assistance systems and vehicle safety systems.
Claim 41
Independent Claim
87 words
A method for dynamically predicting road geometry, the method comprising steps of: i. filtering current environmental data from at least one sensor and performing an estimation using the current environmental data, and outputting a filter output from each filter; ii. weighing the filter output from the bank of filters and ascribing a weighted value to each filter output based on a relevance of the filter, thereby providing weighted outputs; iii. fusing the weighted outputs into a single output; whereby the output describes a vehicle forward path estimate.
Claim 42
Independent Claim
87 words
A method for dynamically predicting road geometry, the method comprising steps of: i. filtering current environmental data from at least one sensor and performing an estimation using the current environmental data, and outputting a filter output from each filter; ii. weighing the filter output from the bank of filters and ascribing a weighted value to each filter output based on a relevance of the filter, thereby providing weighted outputs; iii. fusing the weighted outputs into a single output; whereby the output describes a vehicle forward path estimate.
Claim 43
Dependent Claim
45 words
A method for dynamically predicting road geometry as set forth in claim 39 , wherein step of filtering is tailored to receive a previous vehicle path estimate and to recursively perform the estimation based on the current environmental data and the previous vehicle path estimate.
Claim 44
Dependent Claim
27 words
A method for dynamically predicting road geometry as set forth in claim 40 , wherein filters used in the filtering step include a bank of Kalman filters.
Claim 45
Dependent Claim
23 words
A method for dynamically predicting road geometry as set forth in claim 41 , wherein the bank of filters includes three Kalman filters.
Claim 46
Dependent Claim
27 words
A method for dynamically predicting road geometry as set forth in claim 42 , wherein the bank of filters is configured based on a polynomial road model.
Claim 47
Dependent Claim
24 words
A method for dynamically predicting road geometry as set forth in claim 43 , wherein the polynomial road model is a two-clothoid road model.
Claim 48
Dependent Claim
35 words
A method for dynamically predicting road geometry as set forth in claim 44 , wherein each filter in the bank of filters is tuned to a different class of geometry within the two-clothoid road model.
Claim 49
Dependent Claim
41 words
A method for dynamically predicting road geometry as set forth in claim 45 , wherein the different classes of geometry include a constant geometry road section, an upcoming transition in the far range, and an upcoming transition in the near range.
Claim 50
Dependent Claim
39 words
A method for dynamically predicting road geometry as set forth in claim 46 , wherein the step of weighing ascribes weighted values based on the posterior probabilities of a fit between the filter and the forward vehicle path estimate.
Claim 51
Dependent Claim
42 words
A method for dynamically predicting road geometry as set forth in claim 47 , wherein the environmental data is received from at least one sensor is a device selected from a group consisting of imaging devices, GPS/map systems, laser sensors, and radars.
Claim 52
Dependent Claim
37 words
A method for dynamically predicting road geometry as set forth in claim 48 , wherein the output is configured for use by automotive systems selected from a group consisting of driver assistance systems and vehicle safety systems.
Claim 53
Dependent Claim
26 words
A method for dynamically predicting road geometry as set forth in claim 39 wherein filters used in the filtering step include a bank of Kalman filters.
Claim 54
Dependent Claim
29 words
A method for dynamically predicting road geometry as set forth in claim 39 , wherein the configuration of the bank of filters is based on a polynomial road model.
Claim 55
Dependent Claim
24 words
A method for dynamically predicting road geometry as set forth in claim 51 , wherein the polynomial road model is a two-clothoid road model.
Claim 56
Dependent Claim
30 words
A method for dynamically predicting road geometry as set forth in claim 39 , wherein each filter is tuned to a different class of geometry within the two-clothoid road model.
Claim 57
Dependent Claim
41 words
A method for dynamically predicting road geometry as set forth in claim 53 , wherein the different classes of geometry include a constant geometry road section, an upcoming transition in the far range, and an upcoming transition in the near range.
Claim 58
Dependent Claim
39 words
A method for dynamically predicting road geometry as set forth in claim 39 , wherein the step of weighing ascribes weighted values based on the posterior probabilities of a fit between the filter and the forward vehicle path estimate.
Claim 59
Dependent Claim
42 words
A method for dynamically predicting road geometry as set forth in claim 39 , wherein the environmental data is received from at least one sensor is a device selected from a group consisting of imaging devices, GPS/map systems, laser sensors, and radars.
Claim 60
Dependent Claim
37 words
A method for dynamically predicting road geometry as set forth in claim 39 , wherein the output is configured for use by automotive systems selected from a group consisting of driver assistance systems and vehicle safety systems.
References Cited (Backward Citations)
US6265991B1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2007-04-06 | 2007-10-06 | 2008-04-06 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2011-04-06 | 2011-10-06 | 2012-04-06 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2015-04-06 | 2015-10-06 | 2016-04-06 | $7700.00 | Window Closed / Lapsed |