Abstract: A sensor fusion and object tracking system and a method thereof are provided. The sensor fusion and object tracking system includes a first fusion module and a second fusion module in signal communication therewith. The first fusion module performs a first fusion process on a 2D driving image and 3D point cloud information to obtain first fusion information having a plurality of recognized objects. The second fusion module performs a second fusion process on the first fusion information and radar information to obtain second fusion information containing the plurality of recognized objects. The second fusion information is used to generate a region of interest (ROI), and the recognized objects within the ROI serve as target objects in subsequent tracking.

Abstract: A visual vehicle-positioning fusion system and a method thereof is provided. In the method, an image point cloud map stored in a storage device is converted into a longitude and latitude database corresponding to the image point cloud map. Longitude and latitude measurement coordinates received by a positioning device are used as first location information. The longitude and latitude database is compared with the longitude and latitude measurement coordinates to generate the initial location of a vehicle. Feature matching is performed on the initial location and the image point cloud map to generate second location information of the vehicle on the image point cloud map. The first location information or the second location information is selected as a final positioning output information and outputted based on a positioning fusion rule.

Abstract: A magnet-guiding switching system includes a lane magnetic field device, a switching controlling module and a route controlling center. As the switching controlling unit informs the magnetic field switching unit to turn on the first switching electromagnets and to turn off the second switching electromagnets according to the driving signal, the vehicle is guided by magnetic fields of the first switching electromagnets to drive from the first section of the first route to the second section along the guiding section; as the switching controlling unit informs the magnetic field switching unit to turn on the second switching electromagnets and to turn off the first switching electromagnets according to the driving signal, the vehicle is guided by magnetic fields of the second switching electromagnets to drive from the first section of the first route to the continuous section of the second route along the switching section.

Abstract: A method with a SOTIF scene collection and a self-update mechanism, which is applied to a vehicle, includes a situation judging step, a scene collecting step, a modifying step, a verifying step, and an updating step. As the situation judging step judges that the sensing control dataset belongs to the accident scene dataset, the sensing control dataset collected by the scene collecting step belongs to a SOTIF scene.

Abstract: A method includes: selecting, from among a series of images, a candidate image that was captured at an image-capturing time instant corresponding to a point-cloud-generating time instant at which a point cloud was generated; generating a two-dimensional data set from the point cloud; superimposing the two-dimensional data set on the candidate image to result in a superimposed image; obtaining a derived distance inconsistency between the candidate image and the two-dimensional data set in the superimposed image; feeding the derived distance inconsistency into a conversion model to obtain a derived time difference; calculating a target time instant based on the derived time difference and the image-capturing time instant of the candidate image; and selecting, from among the series of images that have been received from the image capturing device, a target image that was captured at a time instant the closest to the target time instant.

Abstract: A cabin monitoring and situation understanding perceiving method is proposed. A cabin interior image capturing step is performed to capture a cabin interior image. A generative adversarial network model creating step is performed to create a generative adversarial network model according to the cabin interior image. An image adjusting step is performed to adjust the cabin interior image to generate an approximate image. A cabin interior monitoring step is performed to process the approximate image to generate a facial recognizing result and a human pose estimating result. A cabin exterior image and voice capturing step is performed to capture a cabin exterior image and a voice information. A situation understanding perceiving step is performed to process at least one of the approximate image, the cabin exterior image and the voice information according to a situation understanding model to perceive a situation understanding result.

Abstract: A virtual track detection system and method is disclosed, wherein a track pattern is drawn on a track and positioning elements is disposed along a curved section of the track. The method includes steps: capturing front road images; recognizing the track pattern for determining whether a driving path of the vehicle is straight or curved. If the driving path is straight, calculating a linear equation of the driving path and outputting to a dynamic control end of a vehicle system. If the driving path is curved, detecting the positioning elements and calculating a curvature of the curved section, a turning speed and a modification angle according to the positions of the positioning elements to enable the dynamic control end to modify the driving speed and the heading angle. The present invention integrates image detection and magnetic track detection, exempted from environment influence and reducing operation cost.

Abstract: A self-driving vehicle route planning system detects and transforms environment information of a host vehicle into an aerial view including the coordinate information of coordinate points to recognize and mark traffic lane boundaries, traffic lanes, and other vehicles therein, calculates central points of the traffic lanes, and then, calculates a speed of a front vehicle according to its positions and works out a predicted route thereof. If the predicted route is the same as a driving route of the host vehicle, the front vehicle is used as a route reference point to calculate a final route of the host vehicle; if not, the traffic lane boundary is used as a route reference line to calculate the final route. The invention can plan the route merely using a point cloud data, greatly reducing the cost HD map information and storage space.

Abstract: A method includes: selecting, from among a series of images, a candidate image that was captured at an image-capturing time instant corresponding to a point-cloud-generating time instant at which a point cloud was generated; generating a two-dimensional data set from the point cloud; superimposing the two-dimensional data set on the candidate image to result in a superimposed image; obtaining a derived distance inconsistency between the candidate image and the two-dimensional data set in the superimposed image; feeding the derived distance inconsistency into a conversion model to obtain a derived time difference; calculating a target time instant based on the derived time difference and the image-capturing time instant of the candidate image; and selecting, from among the series of images that have been received from the image capturing device, a target image that was captured at a time instant the closest to the target time instant.

Abstract: An air parking brake electric control valve includes an air valve unit and a self-lock unit. The air valve unit includes a main valve body, an auxiliary valve body, a valve core and a first electromagnetic assembly. The valve core is driven by the first electromagnetic assembly to move between a first action position and a second action position. The self-lock unit is disposed on the auxiliary valve body, and includes a second electromagnetic assembly. The second electromagnetic assembly includes a movable column operable to move between a release position and a lock position.

Abstract: A feature point integration positioning system includes a moving object, an image input source, an analyzing module and a positioning module. The image input source is disposed at the moving object to shoot an environment for obtaining a sequential image dataset. The analyzing module includes a machine vision detecting unit configured to generate a plurality of first feature points in each of the images based on each of the images, a deep learning detecting unit configured to generate a plurality of second feature points in each of the images based on each of the images, and an integrating unit configured to integrate the first feature points and the second feature points in each of the images into a plurality of integrated feature points in each of the images. The positioning module confirms a position of the moving object relative to the environment at each of the time points.

Abstract: A method for detecting an interior condition of a vehicle is provided to use a camera device and a radar device to acquire images and point cloud datasets with respect to an interior space of the vehicle. A computing device generates a synthesized image based on the images and the point cloud datasets, obtains a skeleton feature dataset and a facial feature dataset with respect to a living object in the synthesized image, and determines the interior condition of the vehicle based on the skeleton feature dataset and the facial feature dataset.

Abstract: A vehicle platoon following deciding system based on cloud computing is configured to decide a plurality of vehicle platoon accelerations of a leading vehicle and at least one following vehicle. A cloud processing unit receives a leading vehicle parameter group and at least one following vehicle parameter group. The cloud processing unit is configured to implement a cloud deciding step. The cloud deciding step includes judging whether the leading vehicle is manually driven according to the leading vehicle parameter group to generate a driving mode judging result, calculating a driving acceleration range according to a leading vehicle acceleration range and at least one following vehicle acceleration range, estimating a compensated acceleration according to the leading vehicle parameter group, and calculating the vehicle platoon accelerations according to the driving mode judging result and at least one of the driving acceleration range and the compensated acceleration.

Abstract: A stably braking system and a method using the same control wheels on a single axle of a ground vehicle. Firstly, at least one of a wheel deceleration and an actual slip of each of the wheels is calculated. Hydraulic control commands are generated when a braking operation is performed in response to a braking indication signal and it is detected that the wheel deceleration or the actual slip is higher. The hydraulic control commands are configured to control a hydraulic braking system to adjust the wheel speed. When the ground vehicle drives in a straight line or turns with a first pose physical quantity, the hydraulic control command with a low priority is replaced by the hydraulic control command with a high priority and the hydraulic braking system is controlled to adjust the wheel speeds based on the identical hydraulic control commands.

Abstract: A vehicle positioning method via data fusion and a system using the same are disclosed. The method is performed in a processor electrically connected to a self-driving-vehicle controller and multiple electronic systems. The method is to perform a delay correction according to a first real-time coordinate, a second real-time coordinate, real-time lane recognition data, multiple vehicle dynamic parameters, and multiple vehicle information received from the multiple electronic systems with their weigh values, to generate a fusion positioning coordinate, and to determine confidence indexes. Then, the method is to output the first real-time coordinate, the second real-time coordinate, and the real-time lane recognition data that are processed by the delay correction, the fusion positioning coordinate, and the confidence indexes to the self-driving-vehicle controller for a self-driving operation.

Abstract: An air brake electric control valve includes a valve body, a force balance unit including a guide member, and an electromagnetic urge unit including a movable column operable to move between an urging position and a retracted position. When the movable column is at the urging position, the movable column pushes the air guide member such that a through hole of the air guide member is blocked. When the movable column is at the retracted position, a gap is formed between the movable column and the air guide member such that an intermediate section and a second passage of the valve body are in fluid communication via the through hole of the air guide member and the gap.

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

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 active steering control with automatic torque compensation are disclosed with a processor that generates a targeted torque signal after receiving a steering assistance signal generated by an active driver assistance device, overlays the targeted torque signal on a driver's torque signal after receiving the driver's torque signal sensed by a torque sensor to generate a steering torque signal, and performs an assistance logic algorithm according to the steering torque signal. As the assistance logic algorithm is performed based on both the steering assistance signal and the driver's torque signal, the steering assistance effect provided by the system and the method will not resist against the way of driver's steering, allowing the driver to easily and stably control the vehicle.

Abstract: A dynamic velocity planning method for an autonomous vehicle is performed to plan a best velocity curve of the autonomous vehicle. An information storing step is performed to store an obstacle information, a road information and a vehicle information. An acceleration limit calculating step is performed to calculate the vehicle information according to a calculating procedure to generate an acceleration limit value range. An acceleration combination generating step is performed to generate a plurality of acceleration combinations according to the obstacle information, the road information, and the acceleration limit value range. An acceleration filtering step is performed to filter the acceleration combinations according to a jerk threshold and a jerk switching frequency threshold to obtain a selected acceleration combination. An acceleration smoothing step is performed to execute a driving behavior procedure to adjust the selected acceleration combination to generate the best velocity curve.