US 12,296,872 B2
Method and apparatus for determining a position of a vehicle
Andrew Batchelor, Reading (GB); and Douglas Watson, Reading (GB)
Appl. No. 17/297,006
Filed by HITACHI RAIL GTS UK LIMITED, London (GB)
PCT Filed Nov. 28, 2019, PCT No. PCT/EP2019/082929
§ 371(c)(1), (2) Date May 26, 2021,
PCT Pub. No. WO2020/109476, PCT Pub. Date Jun. 4, 2020.
Claims priority of application No. 1819619.6 (GB), filed on Nov. 30, 2018.
Prior Publication US 2022/0024505 A1, Jan. 27, 2022
Int. Cl. B61L 25/02 (2006.01); G01C 21/16 (2006.01); G01C 21/20 (2006.01)
CPC B61L 25/025 (2013.01) [B61L 25/023 (2013.01); G01C 21/1652 (2020.08); G01C 21/1656 (2020.08); G01C 21/20 (2013.01); B61L 25/021 (2013.01); B61L 25/026 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method of determining a position of a vehicle within a transport network and determining a route option taken by the vehicle, comprising:
obtaining track geometry data indicating track geometry of at least a part of the transport network;
determining, based upon the track geometry data and sensor data from at least one sensor arranged to output a signal indicative of a motion of the vehicle, that the vehicle is approaching a junction, wherein the at least one sensor comprises an inertial measurement unit, IMU, and a sensor other than an IMU;
determining, based upon the track geometry data, a plurality of route options from the junction;
generating a plurality of Bayesian estimation filter algorithms each associated with a respective one of the plurality of route options and configured to estimate a position of the vehicle based upon the track geometry data indicative of the associated route option, the plurality of Bayesian estimation filter algorithms being configured to estimate a position of the vehicle based upon the output signal of the at least one sensor, wherein the plurality of Bayesian estimation filter algorithms are configured to output data indicative of probabilities of the vehicle taking the associated route options, the output data comprising innovation values calculated by the plurality of Bayesian estimation filter algorithms based upon pseudo-measurements of the associated route options, the pseudo-measurements of the associated route options being determined based upon the track geometry data indicative of the associated route options;
monitoring the output of the plurality of Bayesian estimation filter algorithms as the vehicle passes through the junction; and
determining the route option taken by the vehicle by selecting one of the plurality of route options which presents the highest probability based upon the output of the plurality of Bayesian estimation filter algorithms;
wherein a first one of the Bayesian estimation filter algorithms is executed to:
predict a position of the vehicle in a prediction step based at least upon a first sensor data output by the IMU and the track geometry data such that the predicted position of the vehicle lies on a track defined by the track geometry data; and
update the predicted position of the vehicle in an update step based at least upon a second sensor data output by the sensor other than an IMU, and
wherein the estimated position of the vehicle is based upon at least one of the predicted position and the updated predicted position of the vehicle.