In-vehicle artificial intelligence assistant for agent misbehavior accident prevention and related method
Described are systems and methods for minimizing the effects of agent misbehaviors using an in-vehicle artificial intelligence system. In one example, the system includes a processor and a memory in communication with the processor. The memory includes instructions that cause the processor to receive an utterance input from an occupant of a vehicle describing a misbehavior by an agent that may be undetected by the active safety system of the vehicle. The instructions also cause the processor to determine one or more behavioral measurements of the occupant when the occupant was describing the misbehavior by the agent. In response to the utterance input, the behavioral measurement, and the likelihood that the misbehavior by the agent can occur at the location of the vehicle, the instructions can cause the vehicle to perform an emergency maneuver to minimize effects of the misbehavior by the agent on the vehicle.
1 . A system comprising:
a processor; and
a memory in communication with the processor, the memory having instructions that, when executed by the processor, cause the processor to:
receive an utterance input from an occupant of a vehicle describing a misbehavior of an agent external to the vehicle;
determine a behavioral measurement of the occupant when the occupant was describing the misbehavior of the agent; and
in response to the utterance input, the behavioral measurement and a likelihood that the misbehavior of the agent occurring at a location of the vehicle, wherein the likelihood is based at least in part on historical information, cause the vehicle to perform an emergency maneuver based on the misbehavior of the agent.
2 . The system of claim 1 , wherein the memory further includes instructions that, when executed by the processor, cause the processor to:
in response to a determination that the likelihood that the misbehavior of the agent occurring at the location of the vehicle falls below a threshold, request additional information from the occupant.
3 . The system of claim 2 , wherein the additional information includes at least one of confirmation that the misbehavior of the agent is occurring and a location of the misbehavior of the agent.
4 . The system of claim 1 , wherein the behavioral measurement includes one or more of: a gaze of the occupant, hand gestures of the occupant, and facial expressions of the occupant.
5 . The system of claim 1 , wherein the memory further includes instructions that, when executed by the processor, cause the processor to determine the emergency maneuver using a maneuver input from the occupant.
6 . The system of claim 1 , wherein the memory further includes instructions that, when executed by the processor, cause the processor to activate vehicle sensors to detect the misbehavior of the agent in response to the utterance input.
7 . The system of claim 1 , wherein the emergency maneuver is determined based on the behavioral measurement.
8 . The system of claim 1 , wherein the memory further includes instructions that, when executed by the processor, cause the processor to leverage external data from external devices and save information that can be referenced later in scenarios where a data streaming ability is limited due to network limitations, the information comprises locations related to elements in the scenarios along with map information.
9 . A method comprising steps of:
receiving an utterance input from an occupant of a vehicle describing a misbehavior of an agent external to the vehicle;
determining a behavioral measurement of the occupant when the occupant was describing the misbehavior of the agent; and
in response to the utterance input, the behavioral measurement, and a likelihood that the misbehavior of the agent occurring at a location of the vehicle, wherein the likelihood is based at least in part on historical information, causing the vehicle to perform an emergency maneuver based on the misbehavior of the agent.
10 . The method of claim 9 , further comprising the step of:
in response to a determination that the likelihood that the misbehavior of the agent occurring at the location of the vehicle falls below a threshold, requesting additional information from the occupant.
11 . The method of claim 10 , wherein the additional information includes at least one of confirmation that the misbehavior of the agent is occurring and a location of the misbehavior of the agent.
12 . The method of claim 9 , wherein the behavioral measurement includes one or more of: a gaze of the occupant, hand gestures of the occupant, and facial expressions of the occupant.
13 . The method of claim 9 , further comprising the step of determining the emergency maneuver using a maneuver input from the occupant.
14 . The method of claim 9 , further comprising the step of activating vehicle sensors to detect the misbehavior of the agent in response to the utterance input.
15 . The method of claim 9 , wherein the emergency maneuver is determined based on the behavioral measurement.
16 . The method of claim 9 , further comprising the step of leveraging external data from external devices and saving information that can be referenced later in scenarios where a data streaming ability is limited due to network limitations, the information comprises locations related to elements in the scenarios along with map information.
17 . A non-transitory computer-readable medium having instructions that, when executed by a processor, cause the processor to:
receive an utterance input from an occupant of a vehicle describing a misbehavior of an agent external to the vehicle;
determine a behavioral measurement of the occupant when the occupant was describing the misbehavior of the agent; and
in response to the utterance input, the behavioral measurement and a likelihood that the misbehavior of the agent occurring at a location of the vehicle, wherein the likelihood is based at least in part on historical information, cause the vehicle to perform an emergency maneuver based on the misbehavior of the agent.
18 . The non-transitory computer-readable medium of claim 17 , further including instructions that, when executed by the processor, cause the processor to:
in response to a determination that the likelihood that the misbehavior of the agent occurring at the location of the vehicle falls below a threshold, request additional information from the occupant.
19 . The non-transitory computer-readable medium of claim 18 , wherein the additional information includes at least one of confirmation that the misbehavior of the agent is occurring and a location of the misbehavior of the agent.
20 . The non-transitory computer-readable medium of claim 17 , wherein the behavioral measurement includes one or more of: a gaze of the occupant, hand gestures of the occupant, and facial expressions of the occupant.