Intelligent vehicle navigation systems, methods, and control logic for deriving road segment speed limits

Patent metadata

Field	Value
Publication number	US-10838423-B2
Application number	US-201816142680-A
Country	US
Kind code	B2
Filing date	Sep 26, 2018
Priority date	Aug 7, 2018
Publication date	Nov 17, 2020
Grant date	Nov 17, 2020

Abstract

Presented are systems and methods for deriving speed limits of designated road segments by mining large-scale vehicle data traces. A method for controlling operation of a motor vehicle includes: determining a current location of the vehicle; determining a designated road segment corresponding to the vehicle's location; receiving host speed data indicative of the vehicle's speed while travelling on the road segment for a calibrated timeframe; receiving crowd-sourced speed data indicative of the speeds of participatory vehicles while travelling on the road segment for the calibrated timeframe; accumulating a speed distribution function for the road segment based on the host and crowd-sourced speed data; generating a finite mixture model from the speed distribution function to estimate a speed limit range; selecting a speed limit candidate from the estimated speed limit range; and transmitting command signals to a vehicle subsystem to execute a control operation based on the selected speed limit candidate.

First claim

What is claimed:

1. A method for controlling operation of a motor vehicle, the method comprising:
determining, via a resident vehicle controller of the motor vehicle, a vehicle location of the motor vehicle;
determining, via the resident vehicle controller, a designated road segment corresponding to the vehicle location;
receiving, by the resident vehicle controller from a memory-stored map database, a stored speed limit assigned to the designated road segment;
receiving host vehicle speed data indicative of a vehicle speed of the motor vehicle while travelling on the designated road segment for a calibrated timeframe;
receiving crowd-sourced speed data indicative of vehicle speeds of multiple participatory vehicles while travelling on the designated road segment for the calibrated timeframe;
accumulating a statistical speed distribution function for the designated road segment based on the received host vehicle speed data and the received crowd-sourced speed data;
generating a finite mixture model from the statistical speed distribution function to estimate a speed limit range for the designated road segment;
selecting a speed limit candidate from the estimated speed limit range; and
transmitting, via the resident vehicle controller, a command signal to a resident vehicle subsystem of the motor vehicle to execute a control operation based on the selected speed limit candidate.

2. The method of claim 1 , wherein accumulating the statistical speed distribution function includes accumulating a daily speed distribution function and an hourly speed distribution function for the designated road segment.

3. The method of claim 1 , wherein generating the finite mixture model includes applying an expectation maximization algorithm to determine one or more mixture model parameters corresponding to a class density and a prior probability of the finite mixture model.

4. The method of claim 1 , further comprising determining a K-value indicative of a number of components for the finite mixture model based on the statistical speed distribution function.

5. The method of claim 4 , wherein the K-value is equal to n, and wherein generating the finite mixture model includes generating n finite mixture models for the designated road segment.

6. The method of claim 1 , wherein the statistical speed distribution function is represented as g(x) and is calculated as:

g
⁡

(
x
)

=

∑
m

⁢

w
i

⁢

P
i

⁡

(

x
;

μ
i

,

σ
i

)

where

P
i

⁡

(

x
;

μ
i

,

σ
i

)

=

1

(

2
⁢
π

)

1
/
2

⁢

σ
i

⁢

e

[

-

1
2

⁢

(

x
-

μ
i

)

⁢

σ
i

-
1

⁡

(

x
-

μ
i

)

]

and where w i is a weighted factor given to a particular ith hidden component; P i is an individual component of a probabilistic distribution function for each hidden component; x is an observed vehicle speed; μ i is a mean of an ith hidden distribution function; and σ i is a standard deviation of the ith hidden distribution function.

7. The method of claim 1 , further comprising:
selecting a plurality of hypothesized speed limit candidates from the estimated speed limit range; and
applying a maximal likelihood test to each of the hypothesized speed limit candidates to thereby select the speed limit candidate for the designated road segment.

8. The method of claim 1 , wherein the finite mixture model includes a weighted sum of multiple multi-dimensional Gaussian probability density functions.

9. The method of claim 1 , wherein receiving the host vehicle speed data, receiving the crowd-sourced speed data, accumulating the statistical speed distribution function, generating the finite mixture model, and selecting the speed limit candidate are executed by a remote system server computer off-board from the motor vehicle.

10. The method of claim 1 , further comprising:
calculating, via the resident vehicle controller, a

Assignees

• Gm Global Tech Operations Llc

Inventors

• Bai Fan
• Chen Shu
• Grimm Donald K
• Bojanowski David E
• Yu Bo
• Chen Jinzhu

Classifications

• B60W2556/45

  External transmission of data to or from the vehicle · CPC title

• G01C21/3492

  employing speed data or traffic data, e.g. real-time or historical (traffic control systems for road vehicles involving transmission of navigation instructions to the vehicle G08G1/0968) · CPC title

• B60W2555/60

  Traffic rules, e.g. speed limits or right of way · CPC title

• B60K31/0058

  responsive to externally generated signalling · CPC title

• G01C21/3461

  Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types or segments such as motorways, toll roads or ferries · CPC title