Abstract: An intersection warning system based on information fusion and a method thereof, the system includes an intersection sensing device, an intersection computing device, a user device and a cloud server. The cloud server receives and stores on-site sensing information output from the intersection computing device and determines whether user positioning coordinates are received from the user device, if so, the cloud server reads the on-site sensing information and at least one background information, and calculates a fusion risk assessment value based on the on-site sensing information, the at least one background information, and multiple weightings; when the cloud server determines the fusion risk assessment value is greater than a threshold value, a warning command is output to the user device which sends out warning messages according to the warning command.

Abstract: A system and a method for updating and sharing crossroad dynamic map data are disclosed.

Abstract: An intersection warning system based on information fusion and a method thereof, the system includes an intersection sensing device, an intersection computing device, a user device and a cloud server. The cloud server receives and stores on-site sensing information output from the intersection computing device and determines whether user positioning coordinates are received from the user device, if so, the cloud server reads the on-site sensing information and at least one background information, and calculates a fusion risk assessment value based on the on-site sensing information, the at least one background information, and multiple weightings; when the cloud server determines the fusion risk assessment value is greater than a threshold value, a warning command is output to the user device which sends out warning messages according to the warning command.

Abstract: A voice recognition device includes at least one position retrieving device, a directional voice receiving device, a noise suppressor, and a voice recognition processor. The position retrieving device is sequentially coupled to the directional voice receiving device, the noise suppressor, and the voice recognition processor. The position retrieving device retrieves the physical voice position of a voice source and outputs the voice position to the directional voice receiving device. The directional voice receiving device receives a voice signal generated by the voice source according to the voice position. The noise suppressor eliminates the noise of the voice signal to generate a voice recognition signal based on noise model corresponding to the voice position. The voice recognition processor receives the voice recognition signal and generates an operating signal based on the voice recognition signal.

Abstract: A voice recognition device includes at least one position retrieving device, a directional voice receiving device, a noise suppressor, and a voice recognition processor. The position retrieving device is sequentially coupled to the directional voice receiving device, the noise suppressor, and the voice recognition processor. The position retrieving device retrieves the physical voice position of a voice source and outputs the voice position to the directional voice receiving device. The directional voice receiving device receives a voice signal generated by the voice source according to the voice position. The noise suppressor eliminates the noise of the voice signal to generate a voice recognition signal based on noise model corresponding to the voice position. The voice recognition processor receives the voice recognition signal and generates an operating signal based on the voice recognition signal.

Abstract: A system and a method for updating and sharing crossroad dynamic map data are disclosed.

Abstract: A safe warning system for automatic driving takeover includes a sensing unit, a wireless communicating unit, a driver detecting unit, a system self-testing unit, a human-machine interaction computing unit and an interface warning unit. The sensing unit senses an environmental condition to generate an environmental condition datum. The wireless communicating unit receives a cloud datum to generate a field status datum. The driver detecting unit detects the driver to generate a driver controlling datum. The system self-testing unit detects the sensing unit, the wireless communicating unit and the driver detecting unit to generate a system testing datum. The human-machine interaction computing unit receives and computes the environmental condition datum, the field status datum, the driver controlling datum and the system testing datum to generate an interface warning datum. The interface warning unit receives the interface warning datum and shows a warning signal to the driver.

Abstract: A safe warning system for automatic driving takeover includes a sensing unit, a wireless communicating unit, a driver detecting unit, a system self-testing unit, a human-machine interaction computing unit and an interface warning unit. The sensing unit senses an environmental condition to generate an environmental condition datum. The wireless communicating unit receives a cloud datum to generate a field status datum. The driver detecting unit detects the driver to generate a driver controlling datum. The system self-testing unit detects the sensing unit, the wireless communicating unit and the driver detecting unit to generate a system testing datum. The human-machine interaction computing unit receives and computes the environmental condition datum, the field status datum, the driver controlling datum and the system testing datum to generate an interface warning datum. The interface warning unit receives the interface warning datum and shows a warning signal to the driver.

Abstract: The present invention discloses an autonomous driving system able to make driving decisions and a method thereof, which decide a safer vehicle movement, wherein a processor generates a left-turn signal, a forward signal and a right-turn signal, receives and vectorizes a vehicle movement signal and object movement signals to determine whether one object is a dangerous or non-dangerous object, inputs the results into a corresponding equation to generate dangerous and non-dangerous object weights, substitutes the dangerous and non-dangerous object weights into a space weight equation to calculate left-turn, forward and right-turn lane section weights, uses the lane section weights to generate left-turn, forward and right-turn signal weights, generates a movement signal or a braking signal according to whether a highest one of the signal weights is over or below preset weight.

Abstract: The present invention discloses an autonomous driving system able to make driving decisions and a method thereof, which decide a safer vehicle movement, wherein a processor generates a left-turn signal, a forward signal and a right-turn signal, receives and vectorizes a vehicle movement signal and object movement signals to determine whether one object is a dangerous or non-dangerous object, inputs the results into a corresponding equation to generate dangerous and non-dangerous object weights, substitutes the dangerous and non-dangerous object weights into a space weight equation to calculate left-turn, forward and right-turn lane section weights, uses the lane section weights to generate left-turn, forward and right-turn signal weights, generates a movement signal or a braking signal according to whether a highest one of the signal weights is over or below preset weight.

Abstract: A vehicle positioning method and its system are disclosed. The vehicle positioning method has a camera adapted to be mounted in front of a vehicle, multiple visible marks mounted in a photographing-available range of a camera, and a vehicle positioning system. Each visible mark contains a position information related to a location of the visible mark. The vehicle positioning system receives an image of the visible mark captured from the camera and image-processes the image to read the position information of the captured visible mark. The vehicle positioning system further calculates a distance between the captured visible mark and the vehicle and then further corrects the position information of the captured visible mark to have GPS coordinates of the vehicle.

Abstract: A vehicle positioning method and its system are disclosed. The vehicle positioning method has a camera adapted to be mounted in front of a vehicle, multiple visible marks mounted in a photographing-available range of a camera, and a vehicle positioning system. Each visible mark contains a position information related to a location of the visible mark. The vehicle positioning system receives an image of the visible mark captured from the camera and image-processes the image to read the position information of the captured visible mark. The vehicle positioning system further calculates a distance between the captured visible mark and the vehicle and then further corrects the position information of the captured visible mark to have GPS coordinates of the vehicle.

Abstract: A vehicle collision avoidance system is implemented in a host vehicle. A wireless communication module in the host vehicles wirelessly broadcasts vehicle information packages of the host vehicle and receives external vehicle information packages from other neighboring vehicles. Based on the received vehicle information packages, a collision avoidance process is performed. The process has steps of mapping coordinates system, categorizing collision zones, determining whether a possible collision position exists, calculating a collision time and outputting warning messages. The estimations of the possible collision position and the collision time are not affected by the positions of the neighboring vehicles. Therefore, the neighboring vehicles approaching the host vehicle from different direction are effectively monitored.

Abstract: A vehicle collision avoidance system is implemented in a host vehicle. A wireless communication module in the host vehicles wirelessly broadcasts vehicle information packages of the host vehicle and receives external vehicle information packages from other neighboring vehicles. Based on the received vehicle information packages, a collision avoidance process is performed. The process has steps of mapping coordinates system, categorizing collision zones, determining whether a possible collision position exists, calculating a collision time and outputting warning messages. The estimations of the possible collision position and the collision time are not affected by the positions of the neighboring vehicles. Therefore, the neighboring vehicles approaching the host vehicle from different direction are effectively monitored.