Navigation in vehicle crossing scenarios
Systems and methods are disclosed for navigating a host vehicle. In one implementation, at least one processor may be programmed to receive an image captured by a camera; identify an oncoming target vehicle; determine that a planned trajectory for the host vehicle includes a turn that crosses a projected trajectory of the oncoming target vehicle in a potential turn-across-path event; determine a driving jurisdiction associated with the road; determine, based on the driving jurisdiction, whether the target vehicle is approaching a road feature that negates the potential turn-across-path event; and either implement or forego implementing a remedial action based on whether the target vehicle is approaching a road feature that negates the potential turn-across-path event.
1 . A navigation system for a host vehicle, the navigation system comprising:
at least one processor comprising circuitry and a memory, wherein the memory includes instructions that when executed by the circuitry cause the at least one processing device to:
receive one or more images captured by a camera, the one or more images being representative of an environment of the host vehicle;
identify, based on analysis of the one or more images, an oncoming target vehicle in the environment of the host vehicle, wherein the oncoming target vehicle is associated with a projected trajectory of the oncoming target vehicle extending ahead of a current location of the oncoming target vehicle, the projected trajectory being indicated by at least one aspect of a representation of the oncoming target vehicle in the one or more images;
determine that a planned trajectory for the host vehicle includes a turn that crosses the projected trajectory of the oncoming target vehicle at a turn-across-path location and is indicative of a potential turn-across-path event;
determine, based on a location of the host vehicle, a driving jurisdiction associated with the road, the driving jurisdiction being either a right-hand driving jurisdiction or a left-hand driving jurisdiction;
identify, based on analysis of the one or more images, a road feature being approached by the oncoming target vehicle;
determine whether the road feature negates the potential turn-across-path event, the determination whether the road feature negates the potential turn-across-path event being dependent on whether the driving jurisdiction is a right-hand driving jurisdiction or a left-hand driving jurisdiction;
based on a determination that the road feature does not negate the potential turn-across-path event, implement a remedial action in the host vehicle; and
based on a determination that the road feature negates the potential turn-across-path event, forego implementing a remedial action associated with the potential turn-across-path event in determining a navigational action for the host vehicle.
2 . The navigation system of claim 1 , wherein the driving jurisdiction is further determined based on a stored value.
3 . The navigation system of claim 2 , wherein the stored value includes at least one of a setting or a previously determined driving jurisdiction.
4 . The navigation system of claim 1 , wherein the driving jurisdiction is a right-hand driving jurisdiction, the turn-across-path event is associated with a right turn of the host vehicle across the projected trajectory of the oncoming target vehicle, and the road feature is a right-hand curve in the road.
5 . The navigation system of claim 1 , the driving jurisdiction is a left-hand driving jurisdiction, the turn-across-path event is associated with a left turn of the host vehicle across the projected trajectory of the oncoming target vehicle, and the road feature is a left-hand curve in the road.
6 . The navigation system of claim 1 , wherein the road feature being approached by the oncoming target vehicle is a road feature that will cause a path of the oncoming target vehicle to not overlap with a planned trajectory of the host vehicle.
7 . The navigation system of claim 6 , wherein the road feature includes a road edge.
8 . The navigation system of claim 6 , wherein the road feature includes a lane marking.
9 . The navigation system of claim 6 , wherein the road feature includes a structure of a road detected in the one or images.
10 . The navigation system of claim 6 , wherein the road feature includes a sign depicting a road curve.
11 . The navigation system of claim 1 , wherein the one or more images comprises a plurality of images, and wherein the at least one processor is further configured to:
determine, based on analysis of at least two of the plurality of images, a lane of travel of the oncoming target vehicle based on a motion of the oncoming target vehicle; and
determine, based on the motion, a target trajectory associated with the lane of travel of the oncoming target vehicle, wherein the target trajectory includes a bend associated with a road such that the target trajectory of the oncoming target vehicle's lane of travel does not overlap with the planned trajectory of the host vehicle.
12 . The navigation system of claim 1 , wherein the at least one processor is further configured to determine the planned trajectory of the host vehicle based on analysis of the one or more images to determine free space associated with a road.
13 . The navigation system of claim 1 , wherein the at least one processor is further configured to determine the planned trajectory of the host vehicle based on a heading direction of the host vehicle for a predetermined distance ahead of the host vehicle.
14 . The navigation system of claim 1 , wherein the at least one processor is further configured to determine the planned trajectory of the host vehicle based on a stored spline associated with a map.
15 . The navigation system of claim 1 , wherein the at least one processor is further configured to determine a heading direction of the oncoming target vehicle based on analysis of the one or more images.
16 . The navigation system of claim 1 , wherein foregoing the remedial action for the host vehicle includes forgoing application of brakes of the host vehicle.
17 . The navigation system of claim 1 , wherein the remedial action includes at least one of braking of the host vehicle or changing a heading direction of the host vehicle.
18 . The navigation system of claim 1 , wherein the at least one processor is further configured to:
determine, from a stored map, a lane of travel of the oncoming target vehicle; and
determine, from the stored map, a target trajectory associated with the lane of travel of the oncoming target vehicle, wherein the target trajectory includes a bend associated with a road such that the target trajectory of the oncoming target vehicle's lane of travel does not overlap with the planned trajectory of the host vehicle.
19 . A method for navigating a host vehicle, the method comprising:
receiving one or more images captured by a camera, the one or more images being representative of an environment of the host vehicle;
identifying, based on analysis of the one or more images, an oncoming target vehicle in the environment of the host vehicle, wherein the oncoming target vehicle is associated with a projected trajectory of the oncoming target vehicle extending ahead of a current location of the oncoming target vehicle, the projected trajectory being indicated by at least one aspect of a representation of the oncoming target vehicle in the one or more images;
determining that a planned trajectory for the host vehicle includes a turn that crosses the projected trajectory of the oncoming target vehicle at a turn-across-path location and is indicative of a potential turn-across-path event;
determining, based on a location of the host vehicle, a driving jurisdiction associated with the road, the driving jurisdiction being either a right-hand driving jurisdiction or a left-hand driving jurisdiction;
identifying, based on analysis of the one or more images, a road feature being approached by the oncoming target vehicle;
determining whether the road feature negates the potential turn-across-path event, the determination whether the road feature negates the potential turn-across-path event being dependent on whether the driving jurisdiction is a right-hand driving jurisdiction or a left-hand driving jurisdiction;
based on a determination that the road feature does not negate the potential turn-across-path event, implementing a remedial action in the host vehicle; and
based on a determination that the road feature negates the potential turn-across-path event, foregoing implementing a remedial action associated with the potential turn-across-path event in determining a navigational action for the host vehicle.
20 . The method of claim 19 , wherein the driving jurisdiction is further determined based on a stored value.
21 . The method of claim 20 , wherein the stored value includes at least one of a setting or a previously determined driving jurisdiction.
22 . The method of claim 19 , wherein the driving jurisdiction is a right-hand driving jurisdiction, the turn-across-path event is associated with a right turn of the host vehicle across the projected trajectory of the oncoming target vehicle, and the road feature is a right-hand curve in the road.
23 . The method of claim 19 , the driving jurisdiction is a left-hand driving jurisdiction, the turn-across-path event is associated with a left turn of the host vehicle across the projected trajectory of the oncoming target vehicle, and the road feature is a left-hand curve in the road.
24 . The method of claim 19 , wherein the one or more images includes a plurality of images, and wherein the at least one processor is further configured to:
determine, based on analysis of at least two of the plurality of images, a lane of travel of the oncoming target vehicle based on a motion of the oncoming target vehicle; and
determine, based on the motion, a target trajectory associated with the lane of travel of the oncoming target vehicle, wherein the target trajectory includes a bend associated with a road such that the target trajectory of the oncoming target vehicle's lane of travel does not overlap with the planned trajectory of the host vehicle.
25 . A non-transitory computer-readable medium storing instructions for performing a method for navigating a host vehicle, the method comprising:
receiving one or more images captured by a camera, the one or more images being representative of an environment of the host vehicle;
identifying, based on analysis of the one or more images, an oncoming target vehicle in the environment of the host vehicle, wherein the oncoming target vehicle is associated with a projected trajectory of the oncoming target vehicle extending ahead of a current location of the oncoming target vehicle, the projected trajectory being indicated by at least one aspect of a representation of the oncoming target vehicle in the one or more images;
determining that a planned trajectory for the host vehicle includes a turn that crosses the projected trajectory of the oncoming target vehicle at a turn-across-path location and is indicative of a potential turn-across-path event;
determining, based on a location of the host vehicle, a driving jurisdiction associated with the road, the driving jurisdiction being either a right-hand driving jurisdiction or a left-hand driving jurisdiction;
identifying, based on analysis of the one or more images, a road feature being approached by the oncoming target vehicle;
determining whether the road feature negates the potential turn-across-path event, the determination whether the road feature negates the potential turn-across-path event being dependent on whether the driving jurisdiction is a right-hand driving jurisdiction or a left-hand driving jurisdiction;
based on a determination that the road feature does not negate the potential turn-across-path event, implementing a remedial action in the host vehicle; and
based on a determination that the road feature negates the potential turn-across-path event, foregoing implementing a remedial action associated with the potential turn-across-path event in determining a navigational action for the host vehicle.
26 . The non-transitory computer-readable medium of claim 25 , wherein the driving jurisdiction is further determined based on a stored value.
27 . The non-transitory computer-readable medium of claim 26 , wherein the stored value includes at least one of a setting or a previously determined driving jurisdiction.
28 . The non-transitory computer-readable medium of claim 25 , wherein the driving jurisdiction is a right-hand driving jurisdiction, the turn-across-path event is associated with a right turn of the host vehicle across the projected trajectory of the oncoming target vehicle, and the road feature is a right-hand curve in the road.
29 . The non-transitory computer-readable medium of claim 25 , the driving jurisdiction is a left-hand driving jurisdiction, the turn-across-path event is associated with a left turn of the host vehicle across the projected trajectory of the oncoming target vehicle, and the road feature is a left-hand curve in the road.
30 . The non-transitory computer-readable medium of claim 25 , wherein the one or more images includes a plurality of images, and wherein the at least one processor is further configured to:
determine, based on analysis of at least two of the plurality of images, a lane of travel of the oncoming target vehicle based on a motion of the oncoming target vehicle; and
determine, based on the motion, a target trajectory associated with the lane of travel of the oncoming target vehicle, wherein the target trajectory includes a bend associated with a road such that the target trajectory of the oncoming target vehicle's lane of travel does not overlap with the planned trajectory of the host vehicle.