Abstract: Embodiments of real vehicle in-the-loop test systems and methods are disclosed. The system can include a sensor configured to acquire state information and location information of a real vehicle and environment information of an emulation test environment where the vehicle is located; an interaction module configured to acquire a test task in response to the instruction entered by a user, an emulation test environment of the test task comprises a test situation, a map, and an intelligent agent; a vehicle sensing module configured to acquire the state information, the location information, and the environment information from the sensor; and a test task control module configured to receive the test task from the interaction module, the state information and the location information from the vehicle sensing module and load them to the emulation test environment, control the real vehicle to execute the test task, and generate and send the test result.

Abstract: The present invention discloses a method and apparatus for building an agent for test of an unmanned vehicle. The method comprises: obtaining feature information of an agent to be built; generating an agent according to the obtained feature information and verify whether a behavior of the agent is reasonable; considering the agent as a built agent if the behavior of the agent is determined reasonable. The solution of the present invention can be applied to quickly build an agent that meets needs of test of the unmanned vehicle.

Abstract: The present disclosure discloses embodiments of methods and apparatuses for indicating a vehicle moving state. In some embodiments, a method includes receiving a vehicle driving instruction; detecting a driving environment outside the vehicle; determining a driving strategy for executing the vehicle driving instruction in the driving environment; determining a driving track instructed by the driving strategy; and projecting the driving track on a road when the driving environment satisfies a preset condition. This implementation can clearly indicate the position that a vehicle is about to occupy, thereby improving the effect of interaction between the vehicle and other vehicles or pedestrians.

Abstract: The present disclosure discloses methods and systems for testing the vehicle. In some embodiments, a method includes receiving, by an emulation server, a test task and a test scenario set required for executing the test task sent from a client; distributing, by the emulation server, each of the test scenarios to first emulation executors respectively, and sending the test task to each of the first emulation executors; acquiring, by the emulation server, a test result of the test task from each of the first emulation executors; and comparing, by the emulation server, the acquired test result with a preset test standard to generate feedback information of the test task, and sending the feedback information to the client.

Abstract: Disclosed are embodiments of environmental sensing devices and information acquiring methods applied to environmental sensing devices. In some embodiments, an environmental sensing device includes a camera sensor, a laser radar sensor that are integrated, and a control unit. The control unit is connected simultaneously to the camera sensor and the laser radar sensor. The control unit is used for simultaneously entering a trigger signal to the camera sensor and the laser radar sensor. The design of integrating the camera sensor and the laser radar sensor avoids the problems such as poor contact and noise generation that easily occur in a high-vibration and high-interference vehicle environment, and can precisely trigger the camera sensor and the laser radar sensor simultaneously, so as to obtain high-quality fused data, thereby improving the accuracy of environmental sensing. As a result, the camera sensor and the laser radar sensor have a consistent overlapping field of view.

Abstract: The present invention discloses a method and apparatus of obtaining feature information of a simulated agent. The method further comprises: for each agent class, respectively obtaining feature information of real agents belonging to the class and freely participating in traffic activities, the number of real agents belonging to each class being greater than one; for each agent class, extracting representative feature information from feature information of each real agent belonging to the class, and taking the extracted feature information as feature information of simulated agents belonging to this class. The solution of the present invention may be applied to improve correctness of testing results of unmanned vehicles.

Abstract: The present invention discloses a method and an apparatus of constructing a test scenario of an unmanned vehicle. The method comprises: obtaining a scenario attribute set by the user; respectively determining a map and an agent matching with the scenario attribute; generating a test scenario according to the determined map and agent. The solution of the present invention can be used to improve the efficiency of constructing the test scenario.

Abstract: The present invention provides a local trajectory planning method and apparatus for a smart vehicle, pre-acquiring path planning information from a starting location to a destination; the method comprising: determining a target lane; sampling alternative curves from a current location of the smart vehicle to a target lane according to the path planning information; performing speed planning for the sampled alternative curves according to a current travel environment; selecting one of the alternative curves after the speed planning is performed as a target trajectory. Local trajectory planning of the smart vehicle is achieved through the present invention.

Abstract: The present invention provides a method of building a smart vehicle control model, and a method and apparatus for controlling a smart vehicle, wherein the method of building a smart vehicle control model comprises: acquiring sample data which comprise corresponding steering wheel turning angles under driving environments; extracting vehicle state features and road condition features from the sample data; using the extracted features to train a neural network model to obtain the smart vehicle control model. The method of controlling smart vehicle comprises: extracting vehicle state features and road condition features of a vehicle to be controlled; inputting the extracted features into the smart vehicle control model to obtain a steering wheel turning angle; controlling the vehicle to be controlled using the steering wheel turning angle.

Abstract: The present invention discloses a vehicle control method and apparatus and a method and apparatus for acquiring a decision-making model. The vehicle control method, comprising: during travel of an unmanned vehicle, acquiring current external environment information and map information in real time; determining vehicle state information corresponding to the external environment information and map information acquired each time according to a decision-making model obtained by pre-training and reflecting correspondence relationship between the external environment information, map information and vehicle state information, and controlling a travel state of the unmanned vehicle according to the determined vehicle state information. Application of the solution of the present invention can improve security and reduce the workload.

Abstract: The present application discloses a method and an apparatus for generating a high precision map. According to an embodiment, the method comprises: acquiring three-dimensional (3D) laser point cloud data and information related to a grid map for generating the high precision map; determining position information of each piece of the 3D laser point data of the 3D laser point cloud data in the grid map; rendering each pixel point in the grid map, by using the reflection value of corresponding 3D laser point data of the 3D laser point cloud data, in order to generate each of grid images in the grid map; identifying, by using a machine learning algorithm, traffic information of each of the grid images in the grid map; clustering the traffic information of each of the grid images in the grid map to obtain the traffic information of the grid map; and loading the traffic information of the grid map into the grid map to generate the high precision map.

Abstract: The present application discloses a vehicle navigation method and apparatus. In some embodiments, the method includes: collecting a road condition image; deciding whether a lane currently traveled by a vehicle is a navigation lane; determining a lane object in the road condition image on which a guiding track object is to be superimposed and displayed, the guiding track object adapted to instruct the vehicle to travel along the lane currently traveled by the vehicle, or to instruct the vehicle to turn to the navigation lane; and superimposing and displaying the guiding track object on the determined lane object. According to the current vehicle position and the navigation route, by superimposing and displaying the guiding track object on the lane traveled by the vehicle, the driver is intuitively guided to drive the vehicle in the lane where the vehicle should be driven, thus navigating the vehicle more accurately.

Abstract: Disclosed embodiments include a driverless vehicle control method, apparatus and system. In some embodiments, method comprises: receiving a vehicle control message of a driverless vehicle, the vehicle control message used to represent vehicle control characteristics of the driverless vehicle; converting the vehicle control message to a vehicle control protocol message, the vehicle control protocol message used to implement a general instruction description for the vehicle control message; generating a vehicle control command based on the vehicle control protocol message; and converting the vehicle control command to a vehicle control instruction corresponding to the vehicle control message, and sending the vehicle control instruction to the driverless vehicle. In this way, the vehicle control message can be described by using a general message instruction, achieving the objective of controlling the driverless vehicle by using a general message instruction.

Abstract: Disclosed embodiments include a driverless vehicle, and a method, an apparatus and a system for positioning a driverless vehicle. In some embodiments, the method includes: acquiring first laser point cloud reflection value data matching a current position of the driverless vehicle; converting the first laser point cloud reflection value data into laser point cloud projection data in a horizontal earth plane; determining a first matching probability of the laser point cloud projection data in a predetermined range of a laser point cloud reflection value map by using a position of a predetermined prior positioning position in the laser point cloud reflection value map as an initial position; and determining a position of the driverless vehicle in the laser point cloud reflection value map based on the first matching probability. The implementation can accurately position the current position of the driverless vehicle.

Abstract: Disclosed embodiments include an unmanned vehicle, a method, apparatus and system for positioning an unmanned vehicle. In some embodiments, the method includes: acquiring first laser point cloud height value data matching a current position of the unmanned vehicle, the first laser point cloud height value data; converting the first laser point cloud height value data into laser point cloud projection data in a horizontal earth plane; determining a first matching probability of the laser point cloud projection data in a predetermined range of a laser point cloud height value map; and determining a position of the unmanned vehicle in the laser point cloud height value map based on the first matching probability. The embodiment implements an accurate positioning on the current position of the unmanned vehicle.

Abstract: The present application discloses a method and apparatus for detecting a vehicle contour based on point cloud data. The method includes: acquiring to-be-trained point cloud data; generating label data corresponding to points in the to-be-trained point cloud data in response to labeling on the points in the to-be-trained point cloud, the labeling used to indicate whether each of the points in the to-be-trained point cloud data is on a vehicle contour; training a fully convolutional neural network model based on the points in the to-be-trained point cloud data and the label data corresponding to the points in the to-be-trained point cloud data, to obtain a vehicle detection model; and acquiring to-be-detected point cloud data, and obtaining a detection result corresponding to each to-be-detected point in the to-be-detected point cloud data based on the vehicle detection model. The implementation may achieve an accurate detection of the vehicle contour.