US7460951B2
Expired / Lapsed
US
⏱️ 0.0 years remaining
System and method of target tracking using sensor fusion
Assignee: GM Global Technology Operations LLC
•
Filing: 2005-09-26
•
Granted: 2008-12-02
•
Expires: 2025-09-26
Abstract
Abstract A target tracking and sensory fusion system is adapted for use with a vehicle, and configured to observe a condition of at least one object during a cycle. The system includes a plurality of sensors, and a novel controller communicatively coupled to the sensors and configured to more accurately estimate the condition based on sensory fusion. In a preferred embodiment, Kalman filtering is utilized to produce a fused estimate of the object location. The preferred controller is further configured to match each new sensory observation with a track in a track list, and remove the track from the track list, when a matching observation is not determined, during a subsequent cycle.
Inventors
- 👤 Osman D. Altan
- 👤 Shuqing Zeng
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 13:33
CPC Classifications
G; G01; G01S; G01S13/00; G01S13/88; G01S13/93; G01S13/931; G01S13/66; G01S13/72; G01S13/723; G01S13/726; G01S13/86; G01S13/862; G01S13/865; G01S13/867; G06; G06F; G06F18/00; G06F18/20; G06F18/25; G06F18/253; G06V; G06V10/00; G06V10/70; G06V10/77; G06V10/80; G06V10/806; G06V20/00; G06V20/50; G06V20/56; G01S2013/93185; G01S2013/9321; G01S2013/9322; G01S2013/9327; G01S2013/93271
Claims Analysis
Total Claims: 18
Claim 1
Independent Claim
238 words
A computer program for execution by at least one electronic device associated with a plurality of sensors, wherein each of said sensors are configured to estimate at least one condition of at least one object, said program is configured to receive initial estimate data of said at least one condition from the sensors and apply a sensory fusion algorithm to the initial estimate data, so as to determine a state estimate for said at least one condition, said state estimate presents a higher probability and smaller standard of deviation than the initial estimate data, initial and state estimates are determined for a plurality of conditions, said state estimates are stored in a track (y k (t)), the plurality of conditions include at least one rate condition, each of said tracks is dynamically modeled at a time increment (t+1) by applying to y k (t) a vector multiplier (F) that assumes a constant rate condition, and adding a white Guassian noise vector (v k ), initial and state estimates are determined for a plurality of conditions including object range (r), range rate ({dot over (r)}), azimuth angle (θ) and azimuth angle rate ({dot over (θ)}), and the modeled track (y k (t+1)) is determined according to the formula: y k ( t+ 1)= Fy k ( t )+ v k , where F = [ 1 Δ t 1 1 Δ t 1 ] .
Claim 2
Dependent Claim
238 words
A computer program for execution by at least one electronic device associated with a plurality of sensors, wherein each of said sensors are configured to estimate at least one condition of at least one object, said program is configured to receive initial estimate data of said at least one condition from the sensors and apply a sensory fusion algorithm to the initial estimate data, so as to determine a state estimate for said at least one condition, said state estimate presents a higher probability and smaller standard of deviation than the initial estimate data, initial and state estimates are determined for a plurality of conditions, said state estimates are stored in a track (y k (t)), the plurality of conditions include at least one rate condition, each of said tracks is dynamically modeled at a time increment (t+1) by applying to y k (t) a vector multiplier (F) that assumes a constant rate condition, and adding a white Guassian noise vector (v k ), initial and state estimates are determined for a plurality of conditions including object range (r), range rate ({dot over (r)}), azimuth angle (θ) and azimuth angle rate ({dot over (θ)}), and the modeled track (y k (t+1)) is determined according to the formula: y k ( t+ 1)= Fy k ( t )+ v k , where F = [ 1 Δ t 1 1 Δ t 1 ] .
Claim 3
Dependent Claim
211 words
A computer program for execution by at least one electronic device associated with a plurality of sensors, wherein each of said sensors are configured to estimate at least one condition of at least one object, said program is configured to receive initial estimate data of said at least one condition from the sensors and apply a sensory fusion algorithm to the initial estimate data, so as to determine a state estimate for said at least one condition, said state estimate presents a higher probability and smaller standard of deviation than the initial estimate data, initial and state estimates are determined for a plurality of conditions, said state estimates are stored in a track (y k (t)), state estimates are determined for at least one new object, and compared to y k (t) to determine a difference parameter for each of said conditions, each of said difference parameters being passed through a function based on the characteristics of the sensor, further multiplied by a constant coefficient based on the robustness of individual sensor measurements, and then combined to determine a merit value (L k,i ), and said state estimates of said at least one new object is assigned to y k (t) where L k,i is not less than a pre-determined threshold.
Claim 4
Dependent Claim
211 words
A computer program for execution by at least one electronic device associated with a plurality of sensors, wherein each of said sensors are configured to estimate at least one condition of at least one object, said program is configured to receive initial estimate data of said at least one condition from the sensors and apply a sensory fusion algorithm to the initial estimate data, so as to determine a state estimate for said at least one condition, said state estimate presents a higher probability and smaller standard of deviation than the initial estimate data, initial and state estimates are determined for a plurality of conditions, said state estimates are stored in a track (y k (t)), state estimates are determined for at least one new object, and compared to y k (t) to determine a difference parameter for each of said conditions, each of said difference parameters being passed through a function based on the characteristics of the sensor, further multiplied by a constant coefficient based on the robustness of individual sensor measurements, and then combined to determine a merit value (L k,i ), and said state estimates of said at least one new object is assigned to y k (t) where L k,i is not less than a pre-determined threshold.
Claim 5
Dependent Claim
16 words
The program as claimed in claim 2 , said function being a fuzzy logic membership function.
Claim 6
Dependent Claim
15 words
The program as claimed in claim 2 , said function being a symmetric kernel function.
Claim 7
Dependent Claim
46 words
The program as claimed in claim 4 , said function being f R ( Δ R ) = K ( Δ R h R ) , where h R denotes a scaling factor based on the characteristics of the sensor.
Claim 8
Dependent Claim
15 words
The program as claimed in claim 5 , said function being a Gaussian Kernel function.
Claim 9
Dependent Claim
18 words
The program as claimed in claim 6 , said function being: K ( u )=exp(− u 2 ).
Claim 10
Dependent Claim
15 words
The program as claimed in claim 5 , said function being a quadratic Kernel function.
Claim 11
Dependent Claim
36 words
The program as claimed in claim 8 , said function being K ( u ) = { ( 1 - d 2 ) if d < 1 , 0 otherwise .
Claim 12
Dependent Claim
84 words
The program as claimed in claim 2 , wherein a plurality of observations (O i (t)) are assigned to y k (t), and each of said observations are defined by the formula: O i ( t )= Gy ( t )+ w i , where G = [ 1 1 1 0 ] , w i is a 3-by-1 white Gaussian noise vector derived in part from the accuracy of the sensor system, and the observations are combined to determine a true track status.
Claim 13
Dependent Claim
22 words
The program as claimed in claim 10 , wherein the observations are combined using Kalman filtering to determine the true track status.
Claim 14
Dependent Claim
92 words
The program as claimed in claim 11 , wherein the true track status is determined in accordance with the formula(s): y ( t + 1 ) = y ^ ( t + 1 | t ) + ∑ i = 1 s K i ( O i - G y ^ ( t + 1 | t ) ) where y ^ ( t + 1 | t ) = Fy ( t ) .
Claim 15
Dependent Claim
86 words
The program as claimed in claim 12 , wherein the true track status is further determined in accordance with the covariance formula(s): P ( t + 1 ) = ( I - ∑ i = 1 s K i G ) P ^ ( t + 1 | t ) , where P ^ ( t + 1 | t ) = FP ( t ) F T + Q .
Claim 16
Dependent Claim
55 words
The program as claimed in claim 12 , wherein the KF gain for the i-th observer (K i ) is determined in accordance with the following formula: K i ={circumflex over (P)} ( t+ 1 |t ) G T ( R i +G{circumflex over (P)} ( t+ 1 |t ) G T ) −1 .
Claim 17
Dependent Claim
77 words
The program as claimed in claim 2 , each of said tracks y k (t) being assigned a track strength (q k (t)), wherein q k (t)=1 upon the assignment of an observation to the track, and decays at a rate (λ) over a subsequent period, if no observations are assigned to the track over the period, and the track y k (t) is removed from Y(t), if q k (t) falls below a pre-determined minimum threshold.
Claim 18
Dependent Claim
27 words
The program as claimed in claim 15 , wherein a first portion of the tracks decays at a different rate than a second portion of the tracks.
References Cited (Backward Citations)
US5983161A
Cited
US6828903B2
Cited
US6898585B2
Cited
US6856903B2
Cited
US7298868B2
Cited
US6897802B1
Cited
US7272474B1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2011-12-02 | 2012-06-02 | 2012-12-02 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2015-12-02 | 2016-06-02 | 2016-12-02 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2019-12-02 | 2020-06-02 | 2020-12-02 | $7700.00 | Window Closed / Lapsed |