Active vehicle safety system for cyclists and pedestrians
Disclosed herein is an active cyclist and/or pedestrian safety system for identifying, warning, and reacting to dangerous situations that may be experienced by cyclists and/or pedestrians. The safety system may receive first information indicative of a head position of a cyclist and determine, based on the first information, a field of view of the cyclist. The safety system may receive second information indicative of an environment of the cyclist and determine, based on the field of view and the environment, an expected trajectory of the cyclist in a next road segment. The safety system may also determine, based on the field of view and the environment, a risk probability for the expected trajectory of the cyclist in the next road segment. The safety system may also generate an instruction to transmit a warning to the cyclist if the risk probability exceeds a threshold value.
1. An apparatus comprising:
a processor; and
a communication system comprising a receiver that is communicatively coupled to the processer, wherein the processor is configured to:
receive, via the receiver of the communication system, a first information indicative of a head position of a cyclist;
determine, based on the first information, a field of view of the cyclist;
receive, via the receiver of the communication system, a second information indicative of an environment of the cyclist, wherein the receiver is configured to wirelessly receive the first information and the second information according to at least one of a vehicle to everything (V2X) protocol, a WiFi protocol, or a Bluetooth protocol;
determine, based on the field of view and the environment, an expected trajectory of the cyclist in a next road segment;
determine, based on the field of view and the environment, a risk probability for the expected trajectory of the cyclist in the next road segment; and
generate an instruction to transmit a warning to the cyclist if the risk probability exceeds a threshold value.
2. The apparatus of claim 1 , wherein the processor is further configured to determine the expected trajectory of the cyclist based on a duration of time the field of view is along a possible trajectory of the cyclist.
3. The apparatus of claim 1 , wherein the processor is further configured to determine the expected trajectory of the cyclist based on a posture of the cyclist indicating a possible trajectory of the cyclist.
4. The apparatus of claim 3 , wherein the posture comprises a head rotation and/or an arm signal of the cyclist toward a possible trajectory of the cyclist.
5. The apparatus of claim 4 , wherein the processor is further configured to correlate received map information associated with a geographic location of the cyclist and/or a possible trajectory of the cyclist with the first information to estimate a focus probability that the cyclist is focused on the expected trajectory.
6. The apparatus of claim 1 , wherein the processor is further configured to determine a plurality of possible trajectories for the cyclist and, for each possible trajectory of the plurality of possible trajectories, determine a path score associated with the possible trajectory, and determine the next road segment and the expected trajectory based on the path scores and/or probabilities.
7. The apparatus of claim 6 , wherein the processor is further configured to determine, for each possible trajectory of the plurality of possible trajectories, a risk score associated with the possible trajectory, wherein the risk score is based on the field of view of the cyclist.
8. The apparatus of claim 7 , wherein the risk score is based on at least one of a number of objects in the environment, a distance of the cyclist from the objects, a speed of the objects, a trajectory of the objects, an acceleration of the objects, the expected trajectory of the cyclist, a speed of the cyclist, an acceleration of the cyclist, and/or a road geometry of the next road segment.
9. The apparatus of claim 1 , wherein the risk probability is further based on a learning model associated with the cyclist, wherein the learning model is based on comparisons of the expected trajectory to an actual movement of the cyclist over a plurality of road segments.
10. The apparatus of claim 1 , wherein the first information comprises a camera image associated with a head position of the cyclist, wherein the processor is configured to receive the camera image from a forward-facing camera aligned with the head position of the cyclist.
11. The apparatus of claim 1 , wherein the warning comprises at least one of a visual indication, an audible indication, and/or a haptic feedback configured to alert the cyclist of the risk probability.
12. The apparatus of claim 1 , wherein the warning comprises a movement instruction configured to disable a motive force associated with the cyclist.
13. The apparatus of claim 1 , wherein the warning comprises a movement instruction configured to apply a brake associated with the cyclist.
14. The apparatus of claim 13 , wherein the movement instruction depends on the risk probability and a control loss factor associated with the environment.
15. The apparatus of claim 14 , wherein the control loss factor depends on a road condition of the next road segment, wherein the road condition comprises at least one of a road damage to the next road segment, a wetness level of the next road segment, and/or a geometry of the next road segment.
16. A non-transitory computer readable medium, comprising instructions which, if executed, cause one or more processors to:
receive, via a receiver of a communication system coupled to the one or more processors, first information indicative of a head position of a pedestrian;
receive, via the receiver of the communication system, a second information indicative of an environment of the pedestrian, wherein the receiver is configured to receive the first information and the second information according to at least one of a vehicle to everything (V2X) protocol, a WiFi protocol, or a Bluetooth protocol;
determine, based on the first information, a field of view of the pedestrian;
determine, based on the field of view and the environment, an expected trajectory of the pedestrian in a next road segment;
determine, based on the field of view and the environment, a risk probability for the expected trajectory of the pedestrian in the next road segment; and
generate an instruction to transmit a warning to the pedestrian if the risk probability exceeds a threshold value.
17. The non-transitory computer readable medium of claim 16 , wherein the instructions further cause the one or more processors to determine an awareness score of the pedestrian based on a focus point of the pedestrian, wherein the focus point is based on at least one of the field of view of the pedestrian, a head position of the pedestrian, and/or an eye position of the pedestrian.
18. The non-transitory computer readable medium of claim 17 , wherein the awareness score comprises an expected response time of the pedestrian, wherein the expected response time is based on a correlation of the focus point with the expected trajectory.
19. The non-transitory computer readable medium of claim 16 , wherein the second information comprises sensor information received from a sensor of the pedestrian, wherein the sensor comprises at least one of a back-facing sensor configured to sense an area behind the pedestrian, a front-facing sensor configured to sense an area in front of the pedestrian, a body sensor configured to sense a pose of the pedestrian, and/or a side-facing sensor configured to sense an area beside the pedestrian.