An agent device includes: a plurality of agent function units, each of the plurality of agent function units being configured to provide services including outputting a response to an output unit in response to an utterance of an occupant of a vehicle; a recognizer configured to recognize a request included in the occupant's utterance; and an agent selector configured to output a request recognized by the recognizer to the plurality of agent function units and select an agent function unit which outputs a response to the occupant's utterance to the output unit among the plurality of agent function units on the basis of the result of a response of each of the plurality of agent function units.

A driving support method for a vehicle includes: acquiring a sound of a sound source placed outside the vehicle; and displaying, on a display portion, driving support information corresponding to an utterance content of the sound, the utterance content of the sound being recognized by a sound recognition process, in a display mode suggesting a relative position of the sound source from the vehicle, the relative position being specified based on the sound.

A method, a device, a storage medium and a vehicle for vehicle rollover prevention warning, wherein the method for vehicle rollover prevention warning includes: collecting vehicle body rollover state parameters; calculating a lateral-load transfer rate of the vehicle according to the collected vehicle body rollover state parameters and a preset load transfer rate threshold model comprising the centrifugal force rollover moment of the sprung mass; and determining whether the vehicle has the risk of rollover or not according to the calculated lateral-load transfer rate and the preset rollover threshold. According to the technical solution provided by the invention, the load transfer rate threshold model based on the centrifugal force rollover moment of the sprung mass can simulate the actual rollover state of a vehicle more truly, with a more accurate state indication effect and a high warning accuracy.

An autonomous vehicle including a sensor system that outputs a sensor signal indicative of a condition of the autonomous vehicle. The vehicle also includes a communication system including a speaker. Based upon a profile of the passenger, the autonomous vehicle can determine that support is to be provided audibly to the passenger when the support is provided to the passenger. Moreover, the autonomous vehicle can detect occurrence of an event that has been identified as potentially causing discomfort to the passenger based upon the sensor signal output by the sensor system. Responsive to detecting the occurrence of the event, and in accordance with the profile of the passenger, the autonomous vehicle can cause the speaker to output an audible support message. Content of the audible support message is based on the detected event, and the audible support message solicits feedback from the passenger of the autonomous vehicle.

Methods and systems for communicating with a vehicle companion are disclosed. The vehicle companion can include receiving state information about an operator and environmental information about a vehicular environment. A cognitive load and a cognitive requirement can be determined using the state information and the environmental information, respectively. The cognitive load and the cognitive requirement are then compared to determine if an intervention indicator exists. The vehicle companion can then enter into conversation with the operator in response to the intervention indicator, including topics selected based on the operator's personality.

A smart driving management system and a method are disclosed. The management system includes a central control unit, a detection module, a voice reminding module, and a reply receiving module. The management method includes: A. providing a management system communicating with an automotive electronic diagnosis unit of a vehicle to receive driving information of the vehicle detected by the automotive electronic diagnosis unit; B. the management system setting a standard value for the driving information and sending out a voice message when detecting that data of the driving information does not meet the standard value; C. the management system receiving a voice reply content and detecting whether data of new driving information meets the standard value according to the voice reply content; D. the management system generating a detection result based on the new driving information and determining that the detection result is normal driving or dangerous driving.

A conversation guidance method of a speech recognition system may include managing a user domain based on speech recognition function information and situation information corrected from a system mounted on a vehicle, generating a conversation used for speech recognition based on the user domain, and guiding a user with the generated conversation.

A guide voice output control system includes a voice output control unit having a function of outputting a guide voice in response to a trigger and a function of executing interaction related processing having a reception stage for receiving voice, a recognition stage for recognizing voice, and an output stage for outputting voice based on a recognition result, in which the voice output control unit controls the output of the guide voice according to the processing stage of the interaction related processing when the trigger is generated during the execution of the processing, and dynamically controls the output of the guide voice according to whether or not the processing stage is a stage that does not affect the accuracy of voice recognition or listening difficulty of a user even if the guide voice is output.

A control device as a driving support device includes a processor configured such that the processor receives respective voice output instructions from an automatic driving device and a car navigation device provided in a vehicle, and when respective timings to output voice from the automatic driving device and from the car navigation device overlap with each other, the processor performs a control to display a content corresponding to a content of the voice output from the automatic driving device for a longer time than a time to display the content of the voice in a case where the timings do not overlap with each other.

An autonomous vehicle including a sensor system that outputs a sensor signal indicative of a condition of the autonomous vehicle. The vehicle also includes a communication system including a speaker. Based upon a profile of the passenger, the autonomous vehicle can determine that support is to be provided audibly to the passenger when the support is provided to the passenger. Moreover, the autonomous vehicle can detect occurrence of an event that has been identified as potentially causing discomfort to the passenger based upon the sensor signal output by the sensor system. Responsive to detecting the occurrence of the event, and in accordance with the profile of the passenger, the autonomous vehicle can cause the speaker to output an audible support message. Content of the audible support message is based on the detected event, and the audible support message solicits feedback from the passenger of the autonomous vehicle.