Vulnerable road user (VRU) collision avoidance system
Techniques are disclosed for reducing false positives for generating warnings to avoid potential collisions between a vehicle and vulnerable road users (VRUs). This is accomplished via an onboard vehicle safety system that uses crowdsourced map data to determine whether a vehicle is capable of performing a maneuver that results in a lateral shift of the vehicle (which may include a lane-shifting or turning maneuver) within a predetermined threshold time period. The ability for the vehicle to make the turning maneuver, among other driving scenarios, may be used to by the safety system to intelligently determine whether a warning or other action is needed to avoid a potential collision with a VRU. In this way, the occurrence and number of false warnings/interventions are minimized or at least reduced, leading to more attentive drivers and thereby improving VRU safety.
1 . A vehicle, comprising:
one or more cameras configured to acquire image data of a vulnerable road user (VRU); and
processing circuitry configured to:
determine a position of the vehicle using map data;
detect a speed and position of the VRU with respect to the vehicle based upon the acquired image data;
generate a warning when (i) a potential collision between the vehicle and the VRU is detected based upon the position of the vehicle, and (ii) the potential collision between the vehicle and the VRU is calculated to occur within a subsequent time period that is less than a threshold time period,
wherein the warning is generated further based upon a driving scenario that is defined by the vehicle being located in a predetermined geographic region; and
adjust the threshold time period based upon a determination of whether the vehicle is capable of executing a turning maneuver from a current lane.
2 . The vehicle as claimed in claim 1 , wherein the processing circuitry is further configured to cause the vehicle to perform a navigational change to prevent a collision between the vehicle and the VRU.
3 . The vehicle as claimed in claim 1 , wherein the processing circuitry is configured to adjust a manner in which the potential collision between the vehicle and the VRU is calculated based upon a driving scenario that is defined by the vehicle being located in the predetermined geographic region.
4 . The vehicle as claimed in claim 3 , wherein the processing circuitry is configured to adjust the manner in which the potential collision between the vehicle and the VRU is calculated by adjusting the threshold time period.
5 . The vehicle as claimed in claim 1 , wherein the processing circuitry is configured to generate the warning further based upon a driving scenario that is defined by a time of day.
6 . The vehicle as claimed in claim 1 , wherein the processing circuitry is configured to detect the speed and position of the VRU with respect to the vehicle by analyzing a region of interest within one or more frames of the acquired image data, and to adjust the region of interest based upon a driving scenario that is defined by the vehicle being located in the predetermined geographic region.
7 . The vehicle as claimed in claim 1 , wherein the predetermined geographic region corresponds to the vehicle being located within a threshold distance of an intersection of two or more roads.
8 . The vehicle as claimed in claim 1 , wherein the processing circuitry is configured to determine whether the vehicle is capable of executing the turning maneuver from the current lane that would result in the potential collision between the vehicle and the VRU based upon a current lane position of the vehicle indicating that a turn in front of the VRU is not possible.
9 . The vehicle as claimed in claim 1 , wherein the map data includes landmarks and corresponding predetermined geographic locations and comprises data provided by a plurality of vehicles that has been aggregated over time.
10 . A non-transitory computer-readable medium having instructions stored thereon that, when executed by processing circuitry of a vehicle, cause the vehicle to:
acquire image data of a vulnerable road user (VRU);
determine a position of the vehicle using map data;
detect a speed and position of the VRU with respect to the vehicle based upon the acquired image data;
generate a warning when (i) a potential collision between the vehicle and the VRU is detected based upon the position of the vehicle, and (ii) the potential collision between the vehicle and the VRU is calculated to occur within a subsequent time period that is less than a threshold time period,
wherein the warning is generated further based upon a driving scenario that is defined by the vehicle being located in a predetermined geographic region; and
adjust the threshold time period based upon a determination of whether the vehicle is capable of executing a turning maneuver from a current lane.
11 . The non-transitory computer-readable medium as claimed in claim 10 , wherein the instructions, when executed by the processing circuitry of the vehicle, cause the vehicle to perform a navigational change to prevent a collision between the vehicle and the VRU.
12 . The non-transitory computer-readable medium as claimed in claim 10 , wherein the instructions, when executed by the processing circuitry of the vehicle, cause the vehicle to adjust a manner in which the potential collision between the vehicle and the VRU is calculated based upon a driving scenario that is defined by the vehicle being located in the predetermined geographic region.
13 . The non-transitory computer-readable medium as claimed in claim 12 , wherein the instructions, when executed by the processing circuitry of the vehicle, cause the vehicle to adjust the manner in which the potential collision between the vehicle and the VRU is calculated by adjusting the threshold time period.
14 . The non-transitory computer-readable medium as claimed in claim 10 , wherein the instructions, when executed by the processing circuitry of the vehicle, cause the vehicle to generate the warning further based upon a driving scenario that is defined by a time of day.
15 . The non-transitory computer-readable medium as claimed in claim 10 , wherein the instructions, when executed by the processing circuitry of the vehicle, cause the vehicle to detect the speed and position of the VRU with respect to the vehicle by analyzing a region of interest within one or more frames of the acquired image data, and to adjust the region of interest based upon a driving scenario that is defined by the vehicle being located in the predetermined geographic region.
16 . The non-transitory computer-readable medium as claimed in claim 10 , wherein the predetermined geographic region corresponds to the vehicle being located within a threshold distance of an intersection of two or more roads.
17 . The non-transitory computer-readable medium as claimed in claim 10 , wherein the instructions, when executed by the processing circuitry of the vehicle, cause the vehicle to determine whether the vehicle is capable of executing the turning maneuver from the current lane that would result in the potential collision between the vehicle and the VRU based upon a current lane position of the vehicle indicating that a turn in front of the VRU is not possible.
18 . The non-transitory computer-readable medium as claimed in claim 10 , wherein the map data includes landmarks and corresponding predetermined geographic locations and comprises data provided by a plurality of vehicles that has been aggregated over time.