Systems and methods for navigating with sensing uncertainty

A method for navigating a vehicle, the method comprising:

• receiving a first output captured by a first sensor onboard the host vehicle, wherein the first output is associated with a first portion of an environment of the host vehicle;
• receiving a second output captured by a second sensor onboard the host vehicle, wherein the second output is associated with a second portion of the environment of the host vehicle, and wherein the second portion at least partially overlaps with the first portion;
• identifying a representation of a target object in the first output;
• determining, based on the first output, a detected driving condition associated with the target object and whether the detected driving condition triggers at least one navigational constraint, the at least one navigational constraint being configured to limit one or more navigational actions available to the host vehicle;
• based on a determination that the at least one navigational constraint is triggered by the detected driving condition, causing at least a first adjustment to the one or more navigational actuators of the host vehicle in response to the target object;
• and
• based on a determination that the at least one navigational constraint is not triggered by the detected driving condition, determining whether a representation of the target object is included in the second output at a location in the second output corresponding to a location of the target object in the first output, and:
• when the representation of the target object is included in the second output, causing at least a second adjustment to one or more navigational actuators of the host vehicle in response to the target object, the second adjustment being different from the first adjustment;
• or
• when the representation of the target object is not included in the second output, foregoing any adjustments to the one or more navigational actuators of the host vehicle in response to the target object.

A non-transitory computer-readable medium comprising instructions that are executable by at least one processor to cause the at least one processor to perform a method for navigating a vehicle, the method comprising:

• receiving a first output captured by a first sensor onboard the host vehicle, wherein the first output is associated with a first portion of an environment of the host vehicle;
• receiving a second output captured by a second sensor onboard the host vehicle, wherein the second output is associated with a second portion of the environment of the host vehicle, and wherein the second portion at least partially overlaps with the first portion;
• identifying a representation of a target object in the first output;
• determining, based on the first output, a detected driving condition associated with the target object and whether the detected driving condition triggers at least one navigational constraint, the at least one navigational constraint being configured to limit one or more navigational actions available to the host vehicle;
• based on a determination that the at least one navigational constraint is triggered by the detected driving condition, causing at least a first adjustment to the one or more navigational actuators of the host vehicle in response to the target object;
• and
• based on a determination that the at least one navigational constraint is not triggered by the detected driving condition, determining whether a representation of the target object is included in the second output at a location in the second output corresponding to a location of the target object in the first output, and:
• when the representation of the target object is included in the second output, causing at least a second adjustment to one or more navigational actuators of the host vehicle in response to the target object, the second adjustment being different from the first adjustment;
• or
• when the representation of the target object is not included in the second output, foregoing any adjustments to the one or more navigational actuators of the host vehicle in response to the target object.

A host vehicle, the host vehicle comprising:

• a first sensor;
• a second sensor;
• and
• at least one processing device 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 a first output captured by the first sensor, wherein the first output is associated with a first portion of an environment of the host vehicle;
• receive a second output captured by the second sensor, wherein the second output is associated with a second portion of the environment of the host vehicle, and wherein the second portion at least partially overlaps with the first portion;
• identify a representation of a target object in the first output;
• determine, based on the first output, a detected driving condition associated with the target object and whether the detected driving condition triggers at least one navigational constraint, the at least one navigational constraint being configured to limit one or more navigational actions available to the host vehicle;
• based on a determination that the at least one navigational constraint is triggered by the detected driving condition, cause at least a first adjustment to the one or more navigational actuators of the host vehicle in response to the target object;
• and
• based on a determination that the at least one navigational constraint is not triggered by the detected driving condition, determine whether a representation of the target object is included in the second output at a location in the second output corresponding to a location of the target object in the first output, and:
• when the representation of the target object is included in the second output, cause at least a second adjustment to one or more navigational actuators of the host vehicle in response to the target object, the second adjustment being different from the first adjustment;
• or
• when the representation of the target object is not included in the second output, forego any adjustments to the one or more navigational actuators of the host vehicle in response to the target object.