An automatic drive device includes a fusion unit recognizing travel environment of a vehicle based on an output signal of a surrounding monitoring sensor and a control planning unit generating a control plan based on a recognition result of the fusion unit. A diagnostic device includes an abnormality detection unit that detects an abnormality of a field recognition system from the surrounding monitoring sensor to the fusion unit by monitoring the output signal of the surrounding monitoring sensor and the recognition result of the fusion unit over time. The diagnostic device requests the control planning unit to perform MRM based on a detection of the abnormality of the recognition system by the abnormality detection unit.

The invention relates to a method for locating a vehicle (1) in a surrounding area, comprising the following steps: providing a primary sensor system (2, 34, 41, 52); providing a secondary sensor system (4, 35, 44, 56), the secondary system being configured in such a manner as to provide a backup to the primary system, the primary sensor system and the secondary sensor system being configured in such a manner as to completely control the vehicle; detecting environment data by means of the primary sensor system and the secondary sensor system; creating maps of the surroundings from the environment data from the primary sensor system and the secondary sensor system by means of a computer system; transferring the maps of the surroundings created from the primary sensor system and the maps of the surroundings created from the secondary sensor system to the computer system; generating at least one plausibility-checked primary sensor system sub-map and at least one plausibility-checked secondary sensor system sub-map by means of the computer system; transferring the plausibility-checked primary sensor system sub-map to the primary sensor system and transferring the plausibility-checked secondary sensor system sub-map to the secondary sensor system; locating the vehicle in the surrounding area by matching the environment data from the primary sensor system with the plausibility-checked primary sensor system sub-map and by matching the environment data from the secondary sensor system with the plausibility-checked secondary sensor system sub-map; comparing the location of the vehicle determined by the primary sensor system with the location of the vehicle determined by the secondary sensor system.

Disclosed is an electronic device for a vehicle, including a processor receiving first image data from a first camera, receiving second image data from a second camera, receiving first sensing data from a first lidar, generating a depth image based on the first image data and the second image data, and fusing the first sensing data for each of divided regions in the depth image.

Provided is a vehicle control system capable of grouping objects detected by a plurality of sensors with high accuracy in a short time. A vehicle control system 100 includes an information integration device 120 that groups first detection information and second detection information of a first sensor 111 and a second sensor 112 and outputs integrated detection information, and a vehicle control device 130 that controls a vehicle on the basis of the integrated detection information. An arithmetic device 121 of the information integration device 120 stores first time-series information of the first detection information and second time-series information of the second detection information in a storage device 122, calculates a correction parameter of the first detection information by grouping the first time-series information and the second time-series information when the first sensor 111 and the second sensor 112 detect the same object, calculates correction information obtained by correcting the first detection information using the correction parameter, and outputs the integrated detection information by instantaneous value grouping using the correction information and the second detection information.

Embodiments relate to the detection of edge cases through application of a neural network to predict future vehicle environment data and identifying an edge case when the prediction error exceeds a given threshold. This allows edge cases to be identified based on unexpected vehicle environmental conditions or conditions that otherwise cause the neural network to make inaccurate predictions. These edge cases can then be utilised to better train machine learning systems, for instance, to train autonomous vehicle control systems. Alternatively, the identification of an edge case can highlight the need for remedial action, and can therefore trigger an alert to a vehicle control system to take remedial action. Further methods and systems described herein improve environmental sensing by providing a computationally efficient and accurate means for fusing sensor data and using this fused data to control sensors to focus on areas that would most reduce the uncertainty in the sensing system.

In various examples, a multi-sensor fusion machine learning model—such as a deep neural network (DNN)—may be deployed to fuse data from a plurality of individual machine learning models. As such, the multi-sensor fusion network may use outputs from a plurality of machine learning models as input to generate a fused output that represents data from fields of view or sensory fields of each of the sensors supplying the machine learning models, while accounting for learned associations between boundary or overlap regions of the various fields of view of the source sensors. In this way, the fused output may be less likely to include duplicate, inaccurate, or noisy data with respect to objects or features in the environment, as the fusion network may be trained to account for multiple instances of a same object appearing in different input representations.

A vehicle configured to operate in an autonomous mode is provided. The vehicle is configured to obtain an indication of a final destination, and, if the final destination is not on a pre-approved road for travel by the vehicle, the vehicle is configured to determine a route from the vehicle's current location to an intermediary destination. The vehicle is further configured to determine a means for the vehicle user to reach the final destination from the intermediate destination.

Systems and methods for predicting object motion and controlling autonomous vehicles are provided. In one example embodiment, a computer implemented method includes obtaining state data indicative of at least a current or a past state of an object that is within a surrounding environment of an autonomous vehicle. The method includes obtaining data associated with a geographic area in which the object is located. The method includes generating a combined data set associated with the object based at least in part on a fusion of the state data and the data associated with the geographic area in which the object is located. The method includes obtaining data indicative of a machine-learned model. The method includes inputting the combined data set into the machine-learned model. The method includes receiving an output from the machine-learned model. The output can be indicative of a plurality of predicted trajectories of the object.

Provided herein is technology relating to automated driving and particularly, but not exclusively, to systems comprising roadside intelligent units (RIU) and infrastructure of specific intelligence levels and related methods for providing and/or supplementing automated driving capabilities of connected and automated vehicles (CAV).

Embodiments of the present application disclose a positioning method and apparatus, an autonomous driving vehicle, an electronic device and a storage medium, relating to the field of autonomous driving technologies, comprising: collecting first pose information measured by an inertial measurement unit within a preset time period, and collecting second pose information measured by a wheel tachometer within the time period; generating positioning information according to the first pose information, the second pose information and the adjacent frame images; controlling driving of the autonomous driving vehicle according to the positioning information. The positioning information is estimated by combining the first pose information and the second pose information corresponding to the inertial measurement unit and the wheel tachometer respectively. Compared with the camera, the inertial measurement unit and the wheel tachometer are not prone to be interfered by the external environment.