Autonomous driving merge management system

• US 8,788,134 B1
• Filed: 01/04/2013
• Issued: 07/22/2014
• Est. Priority Date: 01/04/2013
• Status: Active Grant

• Current Assignee: Carnegie Mellon University, GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Litkouhi, Bakhtiar Brian, Wei, Junqing, Dolan, John M.
• Primary Examiner(s): Beaulieu, Yonel
• Application Number:
  US13/733,919
• Publication Number:
  US 20140195093A1
• Time in Patent Office: 564 Days
• Field of Search: 701/23, 701/26, 701/36, 701301-302, 340901-905, 340435-436, 342/70, 342/455
• US Class Current: 701/23
• CPC Class Codes: B60W 30/16 Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
• CPC Class Codes: B60W 30/18163 Lane change; Overtaking manoeuvres
• CPC Class Codes: B62D 15/0255 Automatic changing of lane, e.g. for passing another vehicle
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

An autonomous driving merge management system includes an autonomous driving control device and an intention decision management system. The management system includes a candidate strategy subsystem generating a plurality of candidate driving strategies, a merging vehicle behavior recognition subsystem predicting a merging intention of a merging vehicle; an intention-based interactive prediction subsystem predicting future merging scenarios between the host vehicle and merging vehicle as a function of inputs by the merging vehicle behavior recognition subsystem and inputs by the candidate strategy subsystem, and a cost function-based evaluation subsystem determining a cost for each future merging scenario generated by the intention-based interactive prediction subsystem. A processor selects a merge strategy of the host vehicle based on intention-based prediction results and cost function-based evaluation results. The autonomous driving control device applies the merge strategy to the host vehicle for allowing the merging vehicle to cooperatively merge with the host vehicle.

Claims

1. An autonomous driving merge management system comprising:

an autonomous driving control device for autonomously controlling accelerations of a host vehicle;

an intention decision management system comprising;

a candidate strategy subsystem generating a plurality of candidate driving strategies, each candidate driving strategy being a potential driving strategy executable by the host vehicle;

a merging vehicle behavior recognition subsystem predicting a merging intention of a merging vehicle;

the merging intention relating to a positive acceleration or a negative acceleration of the merging vehicle;

an intention-based interactive prediction subsystem predicting future merging scenarios between the host vehicle and merging vehicle as a function of inputs by the merging vehicle behavior recognition subsystem and inputs by the candidate strategy subsystem;

a cost function-based evaluation subsystem determining a cost for each future merging scenario generated by the intention-based interactive prediction subsystem; and

a processor for selecting a merge strategy of the host vehicle based on intention-based prediction results and cost function-based evaluation results;

wherein the autonomous driving control device applies the merge strategy to the host vehicle for allowing the merging vehicle to cooperatively merge with the host vehicle.

2. The autonomous driving merge management system of claim 1 wherein the cost function-based evaluation subsystem determines the cost for each scenario based on a progress cost, a comfort cost, a safety cost, and fuel consumption cost associated with a respective scenario.

3. The autonomous driving merge management system of claim 2 wherein the progress cost includes an efficiency of completing a task during a merging maneuver.

4. The autonomous driving merge management system of claim 2 wherein the comfort cost includes avoiding excessive accelerations of the vehicle to complete the merging maneuver.

5. The autonomous driving merge management system of claim 2 wherein the safety cost includes maintaining a respective distance to the merging vehicle and maintaining a braking distance based on the velocity of the host vehicle and merging vehicle.

6. The autonomous driving merge management system of claim 2 wherein the fuel consumption cost includes an amount of fuel expended to complete a merging maneuver.

7. The autonomous driving merge management system of claim 2 wherein the cost function-based evaluation subsystem determines the cost for a respective scenario based on the following formula:

C_sce=μ

₁C_progress+μ

₂C_comfortμ

₃C_safety+μ

₄C_fuel 

 

(8)

where C_progress is the progress cost, C_comfort is the comfort cost, C_safety is the safety cost, C_fuel consumption cost, and μ

₁,μ

₂,μ

₃, and μ

₄ represent weight factors.

8. The autonomous driving merge management system of claim 7 wherein a cost for a respective strategy for a respective intention is represented by the following formula:

9. The autonomous driving merge management system of claim 8 wherein a cost for a respective strategy given a respective probability of an intention is represented by the following formula:

C_str(i)P(I=Y)C_str(i)|Y+p(I=N)C_str(i)|N

where p(I=Y) is a probability of the remote vehicle yielding during the merging maneuver, p(I=Y)C_str(i)|Y is the cost associated to the host vehicle given the probability as a result of the merging vehicle yielding to the host vehicle, p(I=N) is a probability of the merging vehicle not yielding during the merging maneuver, and p(I=N)C_str(i)|N is the cost associated to the host vehicle given the probability as a result of the merging vehicle not yielding to the host vehicle.

10. The autonomous driving merge management system of claim 1 wherein the merging vehicle behavior recognition subsystem utilizes a statistical merging vehicle model for determining a vehicle behavior of the merging vehicle.

11. The autonomous driving merge management system of claim 1 wherein statistical merging vehicle model is represented by the following formula:

12. The autonomous driving merge management system of claim 10 wherein the statistical merging vehicle model is derived from a deterministic model utilizing a Gaussian distribution.

13. The autonomous driving merge management system of claim 10 wherein the statistical merging vehicle model is represented by the following equations:

d_yield−

d_C−

(d_min+k_vv_host)

d_nyield=d_C+(d_min+k_vv_host)

Δ

t=(dd_yield,nyield−

d_merge)/v_merge−

(d_C−

d_host)/v_host

acc_merge=c_gainΔ

t

where d_yield is the distance from C to D_yield, d_nyield the distance from C to D_nyield d_min is the minimum desired distance to the leading vehicle, k is a gain causing the desired distance to grow with the host vehicle'"'"'s speed, d_merge and d_host are the positions of the merging and host vehicles at any given instance of time, acc_merge is a desired control command for the merging vehicle, Δ

t is a time difference between the host vehicle and merging vehicle arrivals at C, and c_gain is the proportional gain converting the time difference into the acceleration command of the merging vehicle.

14. The autonomous driving merge management system of claim 1 wherein the autonomous driving control device includes a speed controller device.

15. The autonomous driving merge management system of claim 1 wherein the intention decision management system determines an intention of the merging vehicle to merge relative to the host vehicle when transitioning from an entrance ramp to a primary driven road traveled by the host vehicle.

16. The autonomous driving merge management system of claim 1 wherein the intention decision management system determines an intention of the merging vehicle relative to the host vehicle when changing lanes from an adjacent lane to a primary driven lane of the host vehicle.

17. A method for autonomously controlling a vehicle speed during a merging maneuver between a host vehicle and a merging vehicle, the method comprising the steps of:

obtaining speed data and position data of the host vehicle and the remote data;

generating a plurality of candidate driving strategies by a processor, each candidate driving strategy being a potential driving strategy executable by the host vehicle;

predicting an intention of the merging vehicle to merge forward or rearward of the host vehicle by the processor,

generating a plurality of merging scenarios between the host vehicle and merging vehicle by the processor as a function of the predicted merging intention of the merging vehicle and the plurality of candidate driving strategies;

determining a cost for each merging scenario by the processor based on a cost function evaluation analysis technique;

selecting a merge strategy of the host vehicle by the processor based on the cost function evaluation results; and

autonomously controlling accelerations of a host vehicle using an autonomous driving control device, wherein the autonomous driving control device applies the merge strategy to the host vehicle for cooperatively allowing the merging vehicle to cooperatively merge with the host vehicle.

18. The method of claim 17 wherein processor determines the cost for each scenario based on a progress cost, a comfort cost, a safety cost, and fuel consumption cost associated with a respective scenario.

19. The method of claim 18 wherein the processor determines the cost for a respective scenario based on the following formula:

C_sce=μ

₁C_progress+μ

₂C_comfort+μ

₃C_safety+μ

₄C_fuel 

 

(8)

where C_progress is the progress cost, C_comfort is the comfort cost, C_safety is the safety cost, C_fuel fuel consumption cost, and μ

₁,μ

₂,μ

₃, and μ

₄ represent weight factors.

20. The method of claim 19 wherein a cost for a respective strategy for a respective intention is represented by the following formula:

21. The method of claim 20 wherein a cost for a respective strategy given a respective probability of an intention is represented by the following formula:

C_str(i)=p(I=Y)C_str(i)|Y+p(I=N)C_str(i)|N

where p(I=Y) is a probability of the remote vehicle yielding during the merging maneuver, p(I=Y)C_str(i)|Y is the cost associated to the host vehicle given the probability as a result of the merging vehicle yielding to the host vehicle, p(I=N) is a probability of the merging vehicle not yielding during the merging maneuver, and p(I=N)C_str(i)|N is the cost associated to the host vehicle given the probability as a result of the merging vehicle not yielding to the host vehicle.