Abstract: A method of adaptive trajectory generation for a vehicle is provided. A computer device of the vehicle may update a current trajectory for the vehicle when some predetermined conditions that are related to an obstacle positioned within a predetermined distance of the vehicle are satisfied.

Abstract: A trajectory planning method for lane changing of a vehicle includes steps of: calculating a current position of a reference point of the vehicle on a preliminary lane change trajectory that is received from an LCA system of the vehicle at a current time point; based on kinematics data received from an IMU of the vehicle, calculating longitudinal and lateral displacements of the reference point moving during a unit of time from the current time point to a next time point, and a yaw angle of the vehicle at the next time point; and obtaining a calibrated lane change trajectory based on the preliminary lane change trajectory, the current position, the longitudinal and lateral displacements, and the yaw angle.

Abstract: An intersection speed deciding method includes a dataset obtaining and calculating step and a speed adjusting step. At least one of the vehicles expected to pass through one of the points is defined as the approaching vehicle, and a first arrival time of the approaching vehicle is obtained. Whether a preceding vehicle is on the host route is judged. If yes, a second arrival time of the preceding vehicle is obtained. Whether the host vehicle is expected to wait for a red light is judged. If yes, a red light duration is obtained. A time difference exists between a best arrival time and a corresponding expected arrival time, and each time difference is minimized based on the first arrival time, the second arrival time and the red time duration. A speed of the host vehicle is adjusted or remained based on the expected arrival times.

Abstract: A system for remotely monitoring an autonomous vehicle and a method using the same is disclosed. The system includes a filtering unit, a message converting unit, and an abnormality analyzing module. The filtering unit retrieves the raw vehicle-body data of the on-board system information and filters out the raw vehicle-body data unsatisfying with a threshold value to generate vehicle-parameter information. The message converting unit receives the vehicle-parameter information and estimates vehicle-body environment information based on the vehicle-parameter information. The abnormality analyzing module receives the vehicle-parameter information and the vehicle-body environment information, incorporates the vehicle-parameter information and the vehicle-body environment information into a comparison condition to generate a comparison result, generates an abnormality warning signal corresponding to the comparison result, and transmits the abnormality warning signal to a far-end server to display it.

Abstract: A method for planning a trajectory for a self-driving vehicle on a road includes: generating multiple target planned trajectory sets based on information concerning the self-driving vehicle; calculating multiple projected moving ranges and multiple projected moving speeds of an obstacle based on information concerning the obstacle, the projected moving ranges corresponding respectively with multiple time points in a driving time period, the projected moving speeds corresponding respectively with the time points; and selecting one of the target planned trajectory sets as an optimal planned trajectory set based on the target planned trajectory sets, the projected moving ranges and the projected moving speeds for the obstacle.

Abstract: A braking control method according to friction of road surface includes computing a real-time wheel speed according to a signal received from a wheel speed sensor; storing the real-time wheel speed as a wheel initial velocity when a braking event occurs; determining a relative-peak value according to the real-time wheel speed; estimating a vehicle deceleration according to the relative-peak value and the wheel initial velocity; computing an adjustment parameter according to the vehicle deceleration and a tire slip threshold, wherein the adjustment parameter reflects friction coefficient of road surface; and adjusting time length of an enhancement stage in an enhance-pressure control period of a stepped pressure-increasing phase according to the adjustment parameter; or adjusting time length of a reduction stage in a reduce-pressure control period of a stepped pressure-decreasing phase according to the adjustment parameter.

Abstract: A trajectory planning method for lane changing of a vehicle includes steps of: calculating a current position of a reference point of the vehicle on a preliminary lane change trajectory that is received from an LCA system of the vehicle at a current time point; based on kinematics data received from an IMU of the vehicle, calculating longitudinal and lateral displacements of the reference point moving during a unit of time from the current time point to a next time point, and a yaw angle of the vehicle at the next time point; and obtaining a calibrated lane change trajectory based on the preliminary lane change trajectory, the current position, the longitudinal and lateral displacements, and the yaw angle.

Abstract: A method of simultaneous localization and mapping (SLAM) is provided to position a target object. Each of detected tracked objects in a surrounding environment of the target object is classified into a moving object or a static object based on data detected at different time points. The target object is then positioned without considering any of the tracked objects that are classified into a moving object.

Abstract: A self-driving coordination system and the control method thereof are disclosed. The system and the control method are applied to an all-self-driving vehicle fleet. The self-driving coordination system comprises a leader control device, a follower control device, and a server. The leader control device is mounted in a leader. The follower control device is mounted in a follower. The leader control device and the follower control device communicate with each other for bidirectional data transmission. The server communicates with the leader control device and the follower control device for respective bidirectional data transmission.

Abstract: A method for analyzing a number of people includes an image shooting step and a front-end analyzing step. In the image shooting step, a first image and a second image are obtained. In the front-end analyzing step, a foreground object analysis is operated, and a plurality of foreground objects located at a region of interest in the first image are obtained. A human body detection is operated, and at least one human body and a location thereof of the second image are obtained. An intersection analysis is operated, and the location of the human body is matched to the first image. A number of people estimation is operated to estimate the number of the people according to the first covering ratio, a number of the human body, and a second covering ratio of all the foreground objects to the region of interest.

Abstract: A headlight optical system and a lamp using the same are provided. The headlight optical system is implemented with the refractive optical system of a single lens. The headlight optical system includes a first incident surface, a second incident surface, and an exit surface. The first incident surface is a horizontal plane. The second incident surface surrounds the first incident surface. The inner edge of the second incident surface is connected with the outer edge of the first incident surface. The second incident surface has an inclined angle with respect to the first incident surface. After the light emitted from the polycrystalline light source is incident on the first incident surface or the second incident surface, the refractive optical system refracts and emits the light from the exit surface.

Abstract: A braking control method according to friction of road surface includes computing a real-time wheel speed according to a signal received from a wheel speed sensor; storing the real-time wheel speed as a wheel initial velocity when a braking event occurs; determining a relative-peak value according to the real-time wheel speed; estimating a vehicle deceleration according to the relative-peak value and the wheel initial velocity; computing an adjustment parameter according to the vehicle deceleration and a tire slip threshold, wherein the adjustment parameter reflects friction coefficient of road surface; and adjusting time length of an enhancement stage in an enhance-pressure control period of a stepped pressure-increasing phase according to the adjustment parameter; or adjusting time length of a reduction stage in a reduce-pressure control period of a stepped pressure-decreasing phase according to the adjustment parameter.

Abstract: A method and a system for generating dynamic map information with environment information are provided, wherein the system includes a cloud server, multiple relay hosts distributed around the environment and multiple vehicle devices each installed respectively in different vehicles. Each vehicle device includes a LiDAR sensor and a camera for sensing the environment to respectively generate point cloud data and image data. When the point cloud data from different vehicles are transmitted to a neighboring relay host, the relay host performs a multi-vehicle data integration mode to merge the point cloud data and obtain 3D coordinates information of objects in the environment according to the merged data. Based on the 3D coordinates information of objects, the cloud server generates and transmits dynamic map information to the vehicles. By sharing sensing data of different vehicles, the sensing area of each vehicle is expanded to mitigate dark zones or blind zones.

Abstract: A method and a system for generating dynamic map information with environment information are provided, wherein the system includes a cloud server, multiple relay hosts distributed around the environment and multiple vehicle devices each installed respectively in different vehicles. Each vehicle device includes a LiDAR sensor and a camera for sensing the environment to respectively generate point cloud data and image data. When the point cloud data from different vehicles are transmitted to a neighboring relay host, the relay host performs a multi-vehicle data integration mode to merge the point cloud data and obtain 3D coordinates information of objects in the environment according to the merged data. Based on the 3D coordinates information of objects, the cloud server generates and transmits dynamic map information to the vehicles. By sharing sensing data of different vehicles, the sensing area of each vehicle is expanded to mitigate dark zones or blind zones.

Abstract: A multiple-positioning-system switching and fused calibration method and a device thereof are provided. A first sensing device generates first sensing information, and the central processor calculates the first positioning information of a current position according to the first sensing information and a starting position, and downloads map information from the cloud database. A second sensing device detects a feature object, and obtains the distance information of the feature object and the current position, to the central processor. The central processor calculates a current position in the map information, and generates second positioning information, and performs fused calculation on the first positioning information and the second positioning information according to the weight values of a weight distribution table, to generate new first positioning information to replace the first positioning information.

Abstract: A method for sampling and converting vehicular network data is executed by a vehicle host. The vehicle host selects one of multiple data signals from an original signal, and establishes a data table. The vehicle host further determines whether the original signal includes any data signal remaining unselected. When the original signal does not include any data signal remaining unselected, the vehicle host differentially samples data in the data table corresponding to other time sequences by using the data in the data table corresponding to a first time sequence as a reference to generate a differential data table, and compresses the differential data table. The method can reduce the amount of data by performing differential sampling, so that the compression ratio of the data can be effectively improved, and the delay of data transmission can be avoided.

Abstract: A foreign object detection device includes a processor, a detecting circuit assembly connected to the processor, a coil connected to the detecting circuit assembly, a signal generator connected to the processor and the detecting circuit assembly, and a coil configuring circuit connected to the processor and the coil. The processor outputs a control signal to the coil configuring circuit so as to control the coil configuring circuit to generate a switch signal for enabling the coil to switch to one of a closed mode and an open mode, and controls the signal generator to transmit a test signal to the coil via the detecting circuit assembly when the coil is in the open mode.

Abstract: The intelligent driving method applied to a vehicle includes a support vector machine providing step in which the support vector machine is provided. The support vector machine has been trained by a training process. In the training process, a training dataset is provided to the support vector machine. The training dataset is obtained after an original dataset processed by a dimensionality reducing module and a time scaling module. The intelligent driving method includes a dataset processing step in which p features from an environment sensing unit are processed by the dimensionality reducing module and the time scaling module, and the processed dataset will be provided to the support vector machine. The intelligent driving method further includes a deciding step for providing a driving decision for the vehicle according to a classed result of the support vector machine.

Abstract: A nighttime vehicle detecting method is for capturing an image by a camera and driving a computing unit to compute the image and then detect a highlight point of the image. The nighttime vehicle detecting method is for driving the computing unit to perform a communicating region labeling algorithm to label a plurality of highlight pixels connected to each other as a communicating region value, and then performing an area filtering algorithm to analyze an area of the highlight pixels connected to each other and judge whether the highlight pixels connected to each other are a vehicle lamp or not according to a size of the area. The nighttime vehicle detecting method is for driving the computing unit to perform an optical flow algorithm to obtain a speed of the vehicle lamp, and then filtering the vehicle lamp moved at the speed smaller than a predetermined speed.

Abstract: The present disclosure provides a method for analyzing an error and an existence probability of a multi-sensor fusion. The method includes the ab obstacle sensing step, an obstacle predicting step, an error-model providing step, an existence-probability step, a tracking and fusing step and an error accumulating and correcting step. Therefore, by using the method, a plurality of fused obstacle datasets can be obtained, and an accumulation of error variations thereof can be corrected, which can improve the reliability for judging whether the obstacle exist or not.