METHOD AND SYSTEM FOR PRIORITIZING SENSORS FOR A PERCEPTION SYSTEM

1 . A method of prioritizing sensors for a perception system, comprising the steps of:

collecting sensor information, by a plurality of sensors, about a surrounding area of a motor vehicle;

generating a perception scene graph (PSG), by a perception controller, comprising a virtual map of the surrounding area based on the collected sensor information;

defining a primary focus region and a secondary focus region in the virtual map of the surrounding area; and

assigning a high-level priority to the sensors collecting information contributing to the primary focus region, and assigning a low-level priority to the sensors collecting information contributing to the secondary focus region.

2 . The method of claim 1 , further including the step of allocating a greater processing power to process the information collected by the high-level priority sensors than to process the information collected by low-level priority sensors.

3 . The method of claim 2 , further comprising the steps of:

identifying an overlapping region between the primary focus region and a secondary focus region;

assigning a mid-level priority to the sensors collecting information contributing to any overlapping focus region; and

allocating a processing power to process the information collected by the mid-level priority sensors, wherein the processing power is less than the processing power allocated for the high-level sensors but greater than the processing power allocated for the low-level sensors.

4 . The method of claim 3 , further comprising the step of extracting information from the PSG, by a state decision logic controller, for executing a vehicle software application;

wherein the secondary focus region is determined by the vehicle software application, and

wherein the primary focus region is determined by a perception controller based on predetermined criteria required for the safe operation of the vehicle.

5 . The method of claim 4 , further comprising the steps of:

identifying a first group of sensors, wherein each sensor includes an effective coverage area that covers at least a portion of the primary focus region;

fusing the collected sensor information from the first group of sensors to obtain the overall coverage area of the first group of sensors;

comparing the overall area of coverage of the first group of sensors with the primary focus region; and

if the overall area of coverage of the first group of sensors is less than then primary focus region, then the perception controller generates a warning signal.

6 . The method of claim 5 , further comprising the steps of:

identifying a second group of sensors, wherein each sensor includes an effective coverage area that covers at least a portion of the second focus region;

fusing the collected sensor information from the second group of sensors to obtain the overall coverage area of the second group of sensors;

comparing the overall area of coverage of the secondary group of sensors with the secondary focus region; and

if the overall area of coverage by the second group of sensors is less than secondary focus region, then the perception controller generates a warning signal.

7 . The method of claim 6 , further comprising the step of allocating greater processing power to the first group of sensors than the second group of sensors.

8 . The method of claim 7 , further comprising the steps of:

identifying a subset of sensors from the first group of sensors and second group of sensors, wherein the subset of sensors has an overall coverage area that includes the overlapping region; and

allocating greater processing power to the subset of sensors than the second group of sensors, but less than the first group of sensors.

9 . A method of prioritizing sensors for a perception system, comprising the steps of:

determining a primary focus region in a surrounding area of a vehicle;

determining a secondary focus region in the surrounding area of the vehicle;

identifying an overlapping region between the primary focus region and a secondary focus region;

assigning a high-level priority to the primary focus region, a mid-level priority to the over lapping region, and a low-level priority to the second focus region;

collecting information, by a plurality of sensors, on the primary, secondary, and overlapping focus regions; and

allocating processing power to process collected information, wherein information collected from a high-level priority region will be allocated greater processing power than the information collected from the mid-level or low-level priority regions.

10 . The method of claim 9 , wherein the information collected from a mid-level priority region is allocated lesser processing power than the information collected from high-level priority region, but higher processing power than the information collected from low-level priority region.

11 . The method of claim 10 , further comprising the steps of:

identifying sensors, where each sensor includes an effective coverage area that covers at least a portion of the primary focus region;

fusing the collected sensor information from the plurality of sensors to obtain the overall coverage area;

comparing the overall coverage area with the primary focus region; and

if the primary focus area is greater than the overall coverage area, then generate an alarm signal.

12 . The method of claim 10 , further comprising the steps of:

identifying sensors, where each sensor includes an effective coverage area that covers at least a portion of the secondary focus region;

fusing the collected sensor information from the plurality of sensors to obtain the overall coverage area;

comparing the overall coverage area with the secondary focus region; and

if the secondary focus area is greater than the overall coverage area, then generate an alarm signal.

13 . The method of claim 12 , wherein the primary focus region is determined by a perception controller based on the predetermined operating parameters of the vehicle.

14 . The method of claim 12 , wherein the secondary focus region is determined by a perception controller based on the input required by vehicle software applications.

15 . A perception system for a motor vehicle, comprising a:

a plurality of sensors configured to gather information on a surrounding area of the motor vehicle;

a pre-processor in communication with the plurality of sensors, wherein the pre-processor is configured to isolate and detect objects in the surrounding of the motor vehicle;

at least one perception controller in communication with the pre-processor to receive the processed sensor information to generate a perception scene graph (PSG) containing a virtual map of the surroundings area based on the gathered information; and

a plurality of state sensors configured to determine the state of the vehicle including at least one of a vehicle state comprising heading, velocity, and acceleration;

wherein the perception controller is further configured to identify a primary focus region in the PSG based on the predetermined state of the vehicle for the safe operation of the vehicle.

16 . The perception system of claim 15 , further comprising a state decision logic controller configured to extract information from the PSG to execute a vehicle application routine; wherein the vehicle application routine includes instructions to identify a secondary focus region.

17 . The system of claim 16 , wherein the perception controller is further configured to identify an overlapping focus region by determining the overlapping regions of the primary focus region and the secondary order focus region.

18 . The system of claim 17 , wherein the perception controller is configured to assign a high-level priority to the primary focus region, a mid-level priority to the overlapping focus region, and a low-level priority to the secondary focus region.

19 . The system of claim 18 , wherein the perception controller is further configured to identifying at least one first sensor that has a sensor region that overlaps the primary focus region, at least one second sensor that has a sensor region that overlaps the secondary focus region, and at least one third sensor that has a sensor region that overlaps the overlapping focus region; wherein a sensor region is the area of detection of a sensor.

20 . The method of claim 19 , wherein the perception controller is further configured to determine if one or more of the focus regions is not completely overlapped by one or more sensor regions, and activate a warning system if one or more of the focus regions is not completely overlapped by one or more sensor regions.