Managing automated driving complexity of the forward path using perception system measures

• US 10,745,006 B2
• Filed: 02/01/2018
• Issued: 08/18/2020
• Est. Priority Date: 02/01/2018
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Grimm, Donald K., Tong, Wei, Zeng, Shuqing, Mudalige, Upali P.
• Primary Examiner(s): Antonucci, Anne Marie
• Assistant Examiner(s): Motazedi, Sahar
• Application Number:
  US15/886,492
• Publication Number:
  US 20190232955A1
• Time in Patent Office: 929 Days
• CPC Class Codes: B60W 2050/0075 Automatic parameter input, automatic initialising or calibrating means
• CPC Class Codes: B60W 2050/065 by reducing the computational load on the digital processor of the control computer
• CPC Class Codes: B60W 2050/143 Alarm means
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: B60W 50/06 Improving the dynamic response of the control system, e.g. improving the speed of regulation or avoiding hunting or overshoot
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention
• CPC Class Codes: B60W 60/0015 specially adapted for safety
• CPC Class Codes: B60W 60/0018 by employing degraded modes, e.g. reducing speed, in response to suboptimal conditions
• CPC Class Codes: B60W 60/0053 from vehicle to occupant
• CPC Class Codes: B60W 60/0059 Estimation of the risk associated with autonomous or manual driving, e.g. situation too complex, sensor failure or driver incapacity
• CPC Class Codes: G05D 1/0221 involving a learning process
• CPC Class Codes: G06F 18/251 of input or preprocessed data
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/803 of input or preprocessed data
• CPC Class Codes: G06V 10/82 : using neural networks
• CPC Class Codes: G06V 20/56 : exterior to a vehicle by using sensors mounted on the vehicle

Abstract

Technical solutions are described for controlling an automated driving system of a vehicle. An example method includes computing a complexity metric of an upcoming region along a route that the vehicle is traveling along. The method further includes, in response to the complexity metric being below a predetermined low-complexity threshold, determining a trajectory for the vehicle to travel in the upcoming region using a computing system of the vehicle. Further, the method includes in response to the complexity metric being above a predetermined high-complexity threshold, instructing an external computing system to determine the trajectory for the vehicle to travel in the upcoming region. If the trajectory cannot be determined by the external computing system a minimal risk condition maneuver of the vehicle is performed.

Claims

1. A method for controlling an automated driving system of a vehicle, the method comprising:

computing a complexity metric, in real time, of an upcoming region along a route that the vehicle is traveling along;

adjusting the complexity metric, in real time, of the upcoming region along the route that the vehicle is traveling along based on parameters received from crowd-sourcing aggregation from other vehicles that are have passed through the upcoming region within a predetermined interval;

in response to the complexity metric being below a predetermined low-complexity threshold, determining a trajectory for the vehicle to travel in the upcoming region using a computing system of the vehicle; and

in response to the complexity metric being above a predetermined high -complexity threshold;

instructing an external computing system to determine the trajectory for the vehicle to travel in the upcoming region; and

performing a minimal risk condition maneuver of the vehicle when the trajectory cannot be determined by the external computing system.

2. The method of claim 1, further comprising:

in response to the complexity metric being between the low-complexity threshold and the high-complexity threshold;

adjusting the computing system of the vehicle by reallocating computational resources of the computing system of the vehicle;

instructing the adjusted computing system of the vehicle to determine the trajectory for the vehicle to travel in the upcoming region; and

performing the minimal risk condition maneuver of the vehicle when the trajectory cannot be determined by the adjusted computing system.

3. The method of claim 1, wherein computing the complexity metric comprises computing an individual sensor'"'"'s complexity metric based on sensor data captured by one or more sensors of the vehicle.

4. The method of claim 1, wherein computing the complexity metric comprises computing a sensor fusion complexity metric based on sensor fusion data that is determined based on sensor data captured by one or more sensors of the vehicle.

5. The method of claim 1, wherein the complexity metric is computed using machine learning based on a time series analysis of sensor data captured by one or more sensors of the vehicle.

6. The method of claim 1, wherein the complexity metric is computed as r=Σ

_i=1^mw_ip_i, where p_i is an i^th parameter comprising an environmental factor or a complexity-value computed using sensor data from one or more sensors of the vehicle, w_i is a weight associated with the i^th parameter, and m is a total number of parameters.

7. The method of claim 1, further comprising generating an alert for a driver of the vehicle to take control of the vehicle at least a predetermined time interval prior to reaching the upcoming region.

8. An automated driving system of a vehicle comprising:

one or more sensors;

a computing system; and

a controller coupled with the one or more sensors and the computing system, the controller configured to determine an operational mode of the automated driving system, the determining the operational mode of the automated driving system comprising;

computing a complexity metric, in real time, of an upcoming region along a route that the vehicle is traveling along;

adjusting the complexity metric, in real time, of the upcoming region along the route that the vehicle is traveling along based on parameters received from crowd -sourcing aggregation from other vehicles that have passed through the upcoming region within a predetermined interval;

in response to the complexity metric being below a predetermined low -complexity threshold, determining a trajectory for the vehicle to travel in the upcoming region along the route that the vehicle is traveling along, the trajectory to be determined using an internal computing system of the vehicle; and

in response to the complexity metric being above a predetermined high -complexity threshold;

instructing an external computing system to determine the trajectory for the vehicle to travel in the upcoming region, performing a minimal risk condition maneuver of the vehicle if the trajectory cannot be determined by the external computing system, and

adjusting the computing system of the vehicle by reallocating computational resources of the computing system of the vehicle, wherein the reallocating the computational resources comprises reducing a loop time for analyzing sensor data from the one or more sensors.

9. The automated driving system of claim 8, wherein the determining the operational mode of the automated driving system further comprises:

instructing the adjusted computing system of the vehicle to determine the trajectory for the vehicle to travel in the upcoming region; and

performing the minimal risk condition maneuver of the vehicle if the trajectory cannot be determined by the adjusted computing system.

10. The automated driving system of claim 8, wherein computing the complexity metric comprises computing a sensor fusion complexity metric based on sensor fusion data that is determined based on the sensor data captured by the one or more sensors.

11. The automated driving system of claim 8, wherein the complexity metric is computed as r=Σ

_i=1^mw_ip_i, where p_i is an i^th parameter comprising an environmental factor or a complexity-value computed using the sensor data from the one or more sensors of the vehicle, w_i is a weight associated with the i^th parameter, and m is a total number of parameters.

12. The automated driving system of claim 8, wherein the controller determines the trajectory of the upcoming region using the internal computing system or the external computing system based on a machine learning algorithm that computes the complexity metric of the upcoming region using a time series analysis of the sensor data captured by the one or more sensors of the vehicle.

13. The automated driving system of claim 8, wherein the controller is further configured to generate an alert for a driver of the vehicle to take control of the vehicle at least a predetermined time interval prior to reaching the upcoming region.

14. An automated vehicle comprising:

a communication system; and

a controller coupled with the communication system, the controller configured to determine an operational mode of an automated driving system, the determining the operational mode of the automated driving system comprising;

computing a complexity metric, in real time, of an upcoming region along a route that the vehicle is traveling along;

adjusting the complexity metric, in real time, of the upcoming region along the route that the vehicle is traveling along based on parameters received from crowd -sourcing aggregation from other vehicles that have passed through the upcoming region within a predetermined interval;

in response to the complexity metric being below a predetermined low -complexity threshold, determining a trajectory for the vehicle to travel in the upcoming region using a computing system of the vehicle; and

in response to the complexity metric being above a predetermined high -complexity threshold;

instructing an external computing system to determine the trajectory for the vehicle to travel in the upcoming region;

performing a minimal risk condition maneuver of the vehicle if the trajectory cannot be determined by the external computing system; and

adjusting the computing system of the vehicle by reallocating computational resources of the computing system of the vehicle, wherein the reallocating the computational resources comprises reducing a loop time for analyzing sensor data from one or more sensors, wherein reducing the loop time further comprises reducing the loop time from sensors facing a particular side of the vehicle.

15. The vehicle of claim 14, wherein computing the complexity metric comprises:

computing an individual sensor'"'"'s complexity metric based on the sensor data captured by the one or more sensors of the vehicle;

computing a sensor fusion complexity metric based on sensor fusion data that is determined based on the sensor data captured by the one or more sensors of the vehicle; and

computing an object tracking complexity metric based on a number of stably tracked objects from the sensor data and a total number of objects tracked by the one or more sensors of the vehicle.

16. The vehicle of claim 14, wherein the complexity metric is computed as r=Σ

_i=1^mw_ip_i, where p_i is an i^th parameter comprising an environmental factor or a complexity-value computed using the sensor data from the one or more sensors of the vehicle, w_i is a weight associated with the i^th parameter, and m is a total number of parameters.

17. The vehicle of claim 14, wherein the controller is further configured to generate an alert for a driver of the vehicle to take over control of the vehicle at least a predetermined time interval prior to reaching the upcoming region.

18. The vehicle of claim 14, wherein the complexity metric is computed using machine learning based on a time series analysis of the sensor data captured by the one or more sensors of the vehicle.