Apparatus and method for estimating position of vehicle
A vehicle position estimating apparatus may include a position estimation device that maps objects recognized by a sensor of the vehicle and located around of the vehicle to a parking lot map and estimates a position of the vehicle based on movement information related to the vehicle, a weight setting device that predicts a mapping accuracy of the objects using a detected result of a landmark mapped to the parking lot map by the sensor and gives a weight to each particle corresponding to an interest point of each object based on the predicted mapping accuracy of the objects, and a position correction device that corrects the estimated position of the vehicle using the each weighted particle.
1. A vehicle position estimating apparatus comprising:
a memory configured to store program instructions; and
a processor configured to execute the program instructions, the program instructions, when executed, configured for:
a position estimation device configured to map objects, which are recognized by a sensor of a vehicle and located around the vehicle, to a parking lot map and estimate a position of the vehicle based on movement information related to the vehicle, wherein the objects include a pillar and a parking slot which are located in a parking lot;
a weight setting device configured to predict a mapping accuracy of the objects using a detected result of a landmark mapped to the parking lot map by the sensor and give a weight to each particle corresponding to an interest point of each object based on the predicted mapping accuracy of the objects; and
a position correction device configured to correct the estimated position of the vehicle using the each weighted particle,
wherein the weight given to particles corresponding to an interest point of the pillar is higher than the weight given to particles of the parking slot.
2. The vehicle position estimating apparatus of claim 1 , wherein the program instructions when executed are further configured to estimate a probability value of the each particle corresponding to a characteristic of the object using a particle filter and to estimate the position of the vehicle based on the estimated probability value of the each particle.
3. The vehicle position estimating apparatus of claim 1 , to wherein the program instructions when executed are further configured to determine a covariance of particles corresponding to the interest point of the object and to give the weight to the each particle based on the determined covariance.
4. The vehicle position estimating apparatus of claim 3 , wherein the program instructions when executed are further configured to give a relatively high weight to particles corresponding to the interest point of the object in which the covariance is relatively small, and the covariance becomes smaller as the mapping accuracy of the object becomes higher.
5. The vehicle position estimating apparatus of claim 1 , wherein the program instructions when executed are further configured to compare a distance between the position of the vehicle and the landmark with a value obtained by inverse determination of a distance between a position of the landmark mapped to the parking lot map and the each particle and to give a relatively high weight to a particle in which a position error is relatively small.
6. The vehicle position estimating apparatus of claim 1 , wherein the program instructions when executed are further configured to re-sample the each weighted particle and to remove a particle weighted smaller than a reference value.
7. The vehicle position estimating apparatus of claim 6 , wherein the program instructions when executed are further configured to correct the estimated position of the vehicle based on the weight given to the re-sampled particle.
8. The vehicle position estimating apparatus of claim 6 , wherein the program instructions when executed are further configured to re-estimate the position of the vehicle using the re-sampled particle.
9. The vehicle position estimating apparatus of claim 8 , wherein the program instructions when executed are further configured to estimate a probability value of the re-sampled particle using a particle filter and to re-estimate the position of the vehicle by reflecting the weight given to the each particle to the probability value.
10. A vehicle position estimating method comprising:
mapping, by a processor objects recognized by a sensor of a vehicle and located around of the vehicle to a parking lot map to estimate a position of the vehicle based on movement information related to the vehicle, wherein the objects include a pillar and a parking slot which are located in a parking lot;
predicting, by the processor, a mapping accuracy of the objects using a detected result of a landmark mapped to the parking lot map by the sensor;
giving, by the processor, a weight to each particle corresponding to an interest point of each object based on the predicted mapping accuracy of the objects; and
correcting, by the processor, the estimated position of the vehicle using the each weighted particle,
wherein the giving the weight to the each particle includes:
giving, by the processor, higher weight to the particles corresponding to the interest point of the pillar than the weight given to particles of the parking slot.
11. The method of claim 10 , wherein the estimating the position of the vehicle includes:
estimating, by the processor, a probability value of the each particle corresponding to the interest point of the object using a particle filter; and
estimating, by the processor, the position of the vehicle based on the estimated probability value of the each particle.
12. The method of claim 10 , wherein the giving the weight to the each particle includes:
determining, by the processor, a covariance of particles corresponding to the interest point of the object; and
giving, by the processor, the weight to the each particle based on the determined covariance.
13. The method of claim 12 , wherein the giving the weight to the each particle includes:
giving, by the processor, a relatively high weight to particles corresponding to the interest point of the object in which the covariance is relatively small.
14. The method of claim 10 , wherein the giving the weight to the each particle includes:
comparing, by the processor, a distance between the position of the vehicle and the landmark with a value obtained by inverse determination of a distance between a position of the landmark mapped to the parking lot map and the each particle; and
giving, by the processor, a relatively high weight to a particle in which a position error is relatively small.
15. The method of claim 10 , wherein the correcting the estimated position of the vehicle includes:
re-sampling, by the processor, the each weighted particle to remove a particle weighted smaller than a reference value.
16. The method of claim 15 , wherein the correcting the estimated position of the vehicle includes:
correcting, by the processor, the estimated position of the vehicle based on the weight given to the re-sampled particle.
17. The method of claim 15 , further including:
re-estimating, by the processor, the position of the vehicle using the re-sampled particle.
18. The method of claim 17 , wherein the re-estimating the position of the vehicle includes:
estimating, by the processor, a probability value of the re-sampled particle using a particle filter; and
re-estimating, by the processor, the position of the vehicle by reflecting the weight given to the each particle to the probability value.