Operating an autonomous vehicle according to road user reaction modeling with occlusions

A system comprising:

• a detection system configured to detect objects in an environment of an autonomous vehicle, the detected objects including a first object and a second object;
• and
• one or more computing devices in communication with the detection system, the one or more computing devices being configured to:
• determine one or more lane segments to be occluded by the first object from a perspective of the autonomous vehicle during a set time interval according to a positional relationship between the first object and the one or more lane segments;
• determine a reaction time for the second object according to the occluded one or more lane segments;
• and
• operate the autonomous vehicle based on the reaction time.

A non-transitory, tangible computer-readable storage medium on which computer readable instructions of a program are stored, the instructions, when executed by one or more processors, cause the one or more processors to perform a method, the method comprising:

• detecting, using a detection system of an autonomous vehicle, a first object and a second object in the autonomous vehicle's environment;
• determining one or more lane segments to be occluded by the first object from a perspective of the autonomous vehicle during a set time interval according to a positional relationship between the first object and the one or more lane segments;
• determining a reaction time for the second object according to the occluded one or more lane segments;
• and
• operating the autonomous vehicle based on the determined reaction time.