Abstract: A collision detection method and device, as well as an electronic device and a storage medium are provided. The collision detection method includes: acquiring a plurality of video frames containing an obstacle target within a preset time period; analyzing the plurality of video frames to acquire a historical moving track of the obstacle target within the preset time period; inputting the historical moving track into a pre-trained track prediction model, to acquire at least one predicted moving track of the obstacle target; and performing a collision detection with a planned track of an autonomous vehicle and the at least one predicted moving track. The accuracy of collision detection can be improved.

Abstract: According to various embodiment, described herein are methods and systems for reliably detecting malfunctions in a variety of software or hardware components in an autonomous driving vehicle (ADV). In one embodiment, a redundant system can be provided on an independent computing device in an ADV to check for malfunctions in a number of software or hardware components. When no malfunction occurs in the ADV, an autonomous driving system (ADS) in the ADV operates to drive the ADV, while the redundant system can monitor the ADS in a standby mode. In the event of a malfunction, the redundant system can take over the control of the ADV, and take appropriate actions based on a severity level of the malfunction.

Abstract: A method and apparatus for determining a turn-round path of a vehicle, a device and a storage medium are provided. An embodiment of the method includes: determining a starting position and a target position for the vehicle to turn round on a road; determining, based at least partially on road information associated with the road and vehicle information associated with the vehicle, a candidate turn-round path between the starting position and the target position; evaluating the feasibility of the candidate turn-round path; and determining, based on the evaluation on the feasibility, a turn-round path by which the vehicle is to turn round on the road.

Abstract: Embodiments of the present disclosure provide a method and an apparatus for controlling a vehicle, a device and a storage medium. The method includes: in response to determining that a target vehicle is located in a historical takeover area, obtaining historical control information associated with passing through a historical path in the historical takeover area, the historical takeover area indicating an area through which a vehicle in a manual control state passed in a previous period; determining a planned path for the target vehicle to pass through the historical takeover area based on the historical control information; and controlling the target vehicle to pass through the historical takeover area in an automatic control state based on the planned path.

Abstract: A time-segmented signal timing method is related to the field of intelligent transportation. The specific implementation is: obtaining traffic volume data of a target intersection in each period of time of N consecutive days, N being an integer greater than 1; performing curve fitting on the traffic volume data to determine a traffic volume curve corresponding to the target intersection of each day; determining calculating respective target points in the traffic volume curve with second derivatives satisfying a preset condition; and performing time-segmented signal timing on a traffic light at the target intersection based on time points corresponding to the respective target points.

Abstract: A method and an electronic device for detecting a vehicle queue length are disclosed. The method includes: when determining that a traffic light turns green, obtaining vehicle information of each vehicle on a lane section to be detected in a first preset time period before a time point when the traffic light turns green; determining at least one vehicle that has a static position and a static time point on the lane section to be detected; determining a first queuing vehicle and a last queuing vehicle on the lane section to be detected based on the at least one vehicle that has the static position and the static time point on the lane section to be detected; and determining a vehicle queue length on the lane section to be detected based on a position of the first queuing vehicle and a position of the last queuing vehicle.

Abstract: A method and apparatus for adjusting channelization of a traffic intersection are proposed. The specific implementation of the method is: obtaining a first traffic characteristic of vehicles at each of a plurality of target positions in a process of vehicles in a target traveling direction traveling through the traffic intersection from upstream to downstream in a preset first time period; generating first traffic change information of the traffic intersection based on the first traffic characteristic at each of the plurality of target positions; and in response to that the first traffic change information satisfies a preset first change distribution, generating channelization adjustment information for non-motorized vehicle lanes of the traffic intersection.

Abstract: A method, an apparatus, an electronic device, and a storage medium for monitoring an image acquisition device are provided, which are related to a field of computer vision technology. The method for monitoring the image acquisition device includes: determining a stop position of each target vehicle from a first video image acquired by the image acquisition device; determining a marking line in the first video image according to the stop positions of their respective target vehicles, and determining a deviation amount of the marking line in the first video image from a reference making line, and determining that the image acquisition device has deviated in a case that the deviation amount reaches a predetermined condition. The workload of manual detection is reduced, and the accuracy of deviation amount monitoring is increased by comparing the marking line with the reference marking line.

Abstract: The present disclosure discloses a method, an apparatus, an electronic device and a medium for acquiring map data, and relates to the field of intelligent transportation. A specific implementation solution is: determining a target areas of interest in a map, wherein the map is divided into at least two areas of interest; sending a data acquisition instruction to data acquisition terminals to acquire the map data in the target areas of interest; and receiving the map data fed back from the data acquisition terminal and updating the target areas of interest in the map according to the map data.

Abstract: The present disclosure provides a method and an apparatus for processing a vehicle collision, a vehicle, a device and a storage medium. The method includes: obtaining vehicle state information of a target vehicle; the vehicle state information includes: acceleration information of the target vehicle and/or pressure information of a peripheral part in the target vehicle; determining whether a collision occurs to the target vehicle; sending, when it is determined that the collision occurs to the target vehicle, an ejection instruction is sent to an ejection execution mechanism in the target vehicle, the ejection instruction is used to instruct to eject a baffle located at a target position to contact the ground. The baffle is ejected immediately when the present disclosure detects that a collision occurs to the vehicle, which can avoid a secondary collision of the vehicle, thereby improving the safety performance of the vehicle.

Abstract: A method, apparatus, device, and medium for verifying vehicle information are provided. A specific implementation scheme is: determining a target coding precision and a target coding mode of a target data packet to be transmitted; coding the target data packet based on the target coding precision and the target coding mode, to determine target verification information of the target data packet; and transmitting the target data packet and the target verification information, to instruct a receiving-end vehicle to verify the target data packet based on the target verification information.

Abstract: A method and apparatus for detecting and tracking a target, an electronic device and a storage medium are provided. The method includes: cameras, detection modules, tracking modules and storage queues are provided in advance; the numbers of cameras, storage queues and tracking modules are equal, and there is a one-to-one correspondence between the cameras and the storage queues and between the cameras and the tracking modules; distributing data streams collected by the cameras to the plurality of detection modules; detecting, by the detection modules, the received data streams, and sending detection results of the data streams collected by the cameras, to the storage queues corresponding to the cameras; and extracting, by the tracking modules corresponding to the cameras, the detection results from the storage queues corresponding to the cameras, and using the detection results for tracking the target.

Abstract: The present disclosure provides a method for measuring a sensing range of a vehicle, a device and a medium, and relates to a technical field of automatic driving. The method includes: determining a target road side unit to be measured according to a road side unit identifier; when it is detected that the vehicle receives a road-side message from the target road side unit, determining vehicle positioning information of the vehicle when the road-side message is received; and determining a sensing range of the vehicle to the target road side unit in a target lane in which the vehicle travels according to the vehicle positioning information.

Abstract: A target tracking method and device, as well as an electronic apparatus and a storage medium are provided. The method includes: acquiring feature information of a detection box in a current video frame and feature information of a detection box in a previous video frame, the feature information comprising position information of the detection box and an appearance feature of an obstacle target within the detection box, wherein the appearance feature comprises a texture feature and a semantics feature; matching the feature information of the detection box in the current video frame with the feature information of the detection box in the previous video frame; and determining a tracking trajectory of the detection box in the current video frame according to a matching result. In the embodiment of the application, an accuracy for tracking an object can be improved.

Abstract: According to various embodiment, described herein are methods and systems for reliably detecting malfunctions in a variety of software or hardware components in an autonomous driving vehicle (ADV). In one embodiment, a redundant system can be provided on an independent computing device in an ADV to check for malfunctions in a number of software or hardware components. When no malfunction occurs in the ADV, an autonomous driving system (ADS) in the ADV operates to drive the ADV, while the redundant system can monitor the ADS in a standby mode. In the event of a malfunction, the redundant system can take over the control of the ADV, and take appropriate actions based on a severity level of the malfunction.

Abstract: A method, an apparatus, an electronic device, and a storage medium for monitoring an image acquisition device are provided, which are related to a field of computer vision technology. The method for monitoring the image acquisition device includes: determining a stop position of each target vehicle from a first video image acquired by the image acquisition device; determining a marking line in the first video image according to the stop positions of their respective target vehicles, and determining a deviation amount of the marking line in the first video image from a reference making line, and determining that the image acquisition device has deviated in a case that the deviation amount reaches a predetermined condition. The workload of manual detection is reduced, and the accuracy of deviation amount monitoring is increased by comparing the marking line with the reference marking line.

Abstract: A method and apparatus for adjusting channelization of a traffic intersection are proposed. The specific implementation of the method is: obtaining a first traffic characteristic of vehicles at each of a plurality of target positions in a process of vehicles in a target traveling direction traveling through the traffic intersection from upstream to downstream in a preset first time period; generating first traffic change information of the traffic intersection based on the first traffic characteristic at each of the plurality of target positions; and in response to that the first traffic change information satisfies a preset first change distribution, generating channelization adjustment information for non-motorized vehicle lanes of the traffic intersection.

Abstract: A timing control method and a timing control apparatus for a signal light, and a storage medium are disclosed. The method includes: determining an optimal passing-through duration of a signal light corresponding to each passing-through direction at a target intersection according to traffic in the passing-through direction; determining a range of values for each variable in a calibration function corresponding to the target intersection according to a constraint to each passing-through direction at the target intersection, wherein the calibration function comprises the optimal passing-through duration corresponding to each passing-through direction and a variable corresponding to a final passing-through duration in each passing-through direction; and calculating the final passing-through duration in each passing-through direction in a case where the calibration function meets a preset condition, according to the range of values for each variable.

Abstract: A target detection method, device, an electronic apparatus, and a storage medium are provided, which are related to a field of computer vision technology. The specific implementation includes: determining at least one first image from multiple images, wherein a candidate target is contained in respective first images; acquiring confidence degrees of the candidate target in the respective first images; calculating an appearance probability of the candidate target according to weights and the confidence degrees of the respective first image; and determining the candidate target as a final target, in a case that the appearance probability meets a first preset condition. A candidate target may be comprehensively determined by using a detection result of multiple images, thereby determining a detected final target, and improving the detection accuracy of the final target.

Abstract: A collision detection method and device, as well as an electronic device and a storage medium are provided. The collision detection method includes: acquiring a plurality of video frames containing an obstacle target within a preset time period; analyzing the plurality of video frames to acquire a historical moving track of the obstacle target within the preset time period; inputting the historical moving track into a pre-trained track prediction model, to acquire at least one predicted moving track of the obstacle target; and performing a collision detection with a planned track of an autonomous vehicle and the at least one predicted moving track. The accuracy of collision detection can be improved.