System and method for situational behavior of an autonomous vehicle

Abstract

Systems and methods for situational behavior of an autonomous vehicle are disclosed. In one aspect, an autonomous vehicle includes at least one perception sensor configured to generate perception data indicative of at least one other vehicle on a roadway, a non-transitory computer readable medium, and a processor. The processor is configured to determine that the other vehicle is violating one or more rules of the roadway based on the perception data, tag the other vehicle as a non-compliant driver, and modify control of the autonomous vehicle in response to tagging the other vehicle as a non-compliant driver.

What is claimed is: 
     
         1 . An autonomous vehicle comprising:
 at least one perception sensor configured to generate perception data indicative of conditions of the autonomous vehicle on a roadway;   a processor; and   a non-transitory computer readable medium having stored thereon instructions that, when executed by the processor, cause the processor to:
 determine an accident in which the autonomous vehicle has been involved based on the perception data, 
 determine a severity of the accident, 
 determine a course of action to reduce further damage to the autonomous vehicle and any other entities on or near the roadway, and 
 cause the autonomous vehicle to navigate based on the determined course of action. 
   
     
     
         2 . The autonomous vehicle of  claim 1 , wherein the processor is further configured to:
 determine a deceleration of the autonomous vehicle;   determine that the deceleration of the autonomous vehicle is greater than a threshold deceleration; and   determine that a severity of the accident is severe in response to determining that the deceleration of the autonomous vehicle is greater than the threshold deceleration.   
     
     
         3 . The autonomous vehicle of  claim 1 , wherein the processor is further configured to:
 determine that the autonomous vehicle has collided with an object;   determine that the object is: a pedestrian, cyclist, motorcycle, or other vulnerable road user (VRU); and   determine that a severity of the accident is severe in response to determining that the object is: a pedestrian, cyclist, motorcycle, or other vulnerable road user (VRU).   
     
     
         4 . The autonomous vehicle of  claim 3 , wherein the course of action comprises controlling the autonomous vehicle to remain stationary in response to determining that the severity of the accident is severe. 
     
     
         5 . The autonomous vehicle of  claim 1 , wherein the processor is further configured to:
 determine that the autonomous vehicle was moving at a time of the accident,   wherein the course of action comprises controlling the autonomous vehicle to make a complete stop in response determining that the autonomous vehicle was moving at the time of the accident.   
     
     
         6 . The autonomous vehicle of  claim 1 , further comprising:
 a network communications subsystem,   wherein the processor is further configured to:
 perform a diagnostic procedure to identify whether vehicle critical systems are still functioning in response to determining that the accident has occurred, and 
 provide results of the diagnostic procedure to an oversight system via the network communications subsystem. 
   
     
     
         7 . The autonomous vehicle of  claim 6 , wherein the vehicle critical systems comprise systems of the autonomous vehicle involved in performing a minimal risk condition (MRC) maneuver. 
     
     
         8 . The autonomous vehicle of  claim 1 , wherein the processor is further configured to:
 determine that a severity of the accident is light in response to determining that one or more of the following conditions is satisfied: there is no body damage to the autonomous vehicle, the engine is still running, the diagnostic results do not show any malfunction of the autonomous vehicle, and/or there are no debris and/or obstacles which will restrict movement of the autonomous vehicle,   wherein the course of action comprises controlling the autonomous vehicle to execute a minimal risk condition (MRC) maneuver in response to determining that the severity of the accident is light.   
     
     
         9 . The autonomous vehicle of  claim 1 , wherein the at least one perception sensor comprises at least one of: an inertial sensor, a camera, and/or a lidar. 
     
     
         10 . A non-transitory computer-readable medium having stored thereon instructions which, when executed by a processor, cause the processor to:
 determine whether an autonomous vehicle has been involved in an accident based on perception data received from at least one perception sensor configured to generate the perception data indicative of conditions of the autonomous vehicle on a roadway;   in response to determining that the autonomous vehicle has been involved in an accident, determine a severity of the accident;   determine a course of action to reduce further damage to the autonomous vehicle and any other entities on or near the roadway; and   cause the autonomous vehicle to navigate based on the determined course of action.   
     
     
         11 . The non-transitory computer-readable medium of  claim 10 , wherein the instructions further cause the processor to:
 cause the autonomous vehicle to perform an evasive maneuver before determining that the accident has occurred.   
     
     
         12 . The non-transitory computer-readable medium of  claim 11 , wherein the evasive maneuver comprises swerving, braking, or a combination thereof. 
     
     
         13 . The non-transitory computer-readable medium of  claim 10 , wherein the instructions further cause the processor to:
 determine that the autonomous vehicle is in an emergency scenario in which the accident will occur within a threshold time period; and   cause the autonomous vehicle to perform an evasive maneuver in response to determining that the accident will occur within the threshold time period.   
     
     
         14 . The non-transitory computer-readable medium of  claim 13 , wherein the evasive maneuver comprises a steering input to the autonomous vehicle to change a heading of the autonomous vehicle without causing the autonomous vehicle to skid or a trailer of the autonomous vehicle to tip. 
     
     
         15 . The non-transitory computer-readable medium of  claim 13 , wherein the evasive maneuver comprises a braking input to the autonomous vehicle to reduce a speed of the autonomous vehicle up to a maximum deceleration limit of the autonomous vehicle. 
     
     
         16 . The non-transitory computer-readable medium of  claim 15 , wherein the instructions further cause the processor to:
 determine the braking input is sufficient to prevent collision,   wherein the evasive maneuver comprises causing the autonomous vehicle to stay within a current lane in response to determining that the braking input is sufficient to prevent collision.   
     
     
         17 . The non-transitory computer-readable medium of  claim 15 , wherein the instructions further cause the processor to:
 determine that the braking is not sufficient to prevent collision,   wherein the evasive maneuver comprises causing the autonomous vehicle to leave a current lane in response to determining that the braking input is not sufficient to prevent collision.   
     
     
         18 . A method comprising:
 determining an accident in which an autonomous vehicle has been involved based on perception data received from at least one perception sensor configured to generate the perception data indicative of conditions of the autonomous vehicle on a roadway;   determining a severity of the accident;   determining a course of action to reduce further damage to the autonomous vehicle and any other entities on or near the roadway; and   causing the autonomous vehicle to navigate based on the determined course of action.   
     
     
         19 . The method of  claim 18 , further comprising:
 detecting a fast reveal scenario in which an occluded or obstructed entity in a current lane of the autonomous vehicle is revealed or otherwise becomes detectable by the autonomous vehicle due to a source of occlusion being removed based on the perception data, and   cause the autonomous vehicle to perform an evasive maneuver in response to detecting the fast reveal scenario.   
     
     
         20 . The method of  claim 18 , further comprising:
 selecting and monitoring a first predicted path for each of a first set of entities within a predetermined distance of a path of travel of the autonomous vehicle and a second predicted path for each of a second set of entities with a predicted path that crosses the path of travel of the autonomous vehicle; and   determine whether an escape space is available for the autonomous vehicle based on the first and second predicted paths.