The invention is notably directed to a method of steering an automated vehicle (2) in a designated area, thanks to a set (10) of offboard perception sensors (110-140). The method comprises repeatedly executing algorithmic iterations, where each iteration comprises the following steps. First, sensor data are dispatched to K processing systems (11, 12), whereby each processing system k of the K processing systems receives N.sub.k datasets of the sensor data as obtained from N.sub.k respective sensors of the set (10) of offboard perception sensors (110-140), where k=1 to K, K2, and N.sub.k2. The N.sub.k datasets are subsequently processed at each processing system k to obtain M.sub.k occupancy grids corresponding to perceptions from M.sub.k respective sensors of the offboard perception sensors, respectively, where N.sub.kM.sub.k1. The M.sub.k occupancy grids overlap at least partly. Data from the M.sub.k occupancy grids obtained are then fused, at each processing system k, to form a fused occupancy grid, whereby K fused occupancy grids are formed by the K processing systems (11, 12), respectively. The K fused occupancy grids are then forwarded to a further processing system (14), which merges the K fused occupancy grids to obtain a global occupancy grid for the designated area. Eventually, a trajectory is determined for the automated vehicle (2), based on the global occupancy grid. This trajectory is then forwarded to a drive-by-wire system (20) of the automated vehicle (2), to accordingly steer the latter. The invention is further directed to related systems and computer program products.

The technology provides a sign detection and classification methodology. A unified pipeline approach incorporates generic sign detection with a robust parallel classification strategy. Sensor information such as camera imagery and lidar depth, intensity and height (elevation) information are applied to a sign detector module. This enables the system to detect the presence of a sign in a vehicle's externa environment. A modular classification approach is applied to the detected sign. This includes selective application of one or more trained machine learning classifiers, as well as a text and symbol detector. Annotations help to tie the classification information together and to address any conflicts with different the outputs from different classifiers. Identification of where the sign is in the vehicle's surrounding environment can provide contextual details. Identified signage can be associated with other objects in the vehicle's driving environment, which can be used to aid the vehicle in autonomous driving.

Method and device for processing LIDAR sensor data are disclosed. The method includes: receiving a first dataset and a second dataset having pluralities of data points; matching at least some of the plurality of first points with at least some of the plurality of second points, thereby determining a plurality of pairs; for the given one of the plurality of pairs, determining a pair-specific filtering parameter by calculating neighbour beam distances between the given first data point and respective ones the set of neighboring points, a given neighbour beam distance being representative of a linear distance between the given first data point and a respective one of the set of neighbouring points; in response to the pair-specific parameter being positive, excluding the given one of the plurality of pairs from further processing; and processing the reduced plurality of pairs for merging the first dataset and the second dataset.

A profiler arranged to be used on a host vehicle. The profiler is capable of (a) receiving data collected by the profiler while traveling over a surface and (b) generating a surface profile using the data collected with no minimum speed requirement. Since there is no minimum speed requirement, the profiler is capable of generating valid, repeatable and reliable road surface profiles in situations not previously possible, such as during a stop, during acceleration of the host vehicle, during deceleration of the host vehicle, or while the host vehicle is traveling at very low speeds below thresholds typically required for prior profilers.

A pick-up and drop-off area, which is a predetermined area in which an automated driving vehicle stops to pick up or drop off a user, includes a downstream area existing downstream of a standard stop space and an upstream area existing upstream of the standard stop space. An automated driving system controls the automated driving vehicle so as to stop in a target stop space in the pick-up and drop-off area. When the standard stop space is available, the standard stop space is set as the target stop space. When the standard stop space is not available for the automated driving vehicle to stop to drop off the user, the automated driving system searches for an upstream available space in the upstream area and preferentially sets the upstream available space as the target stop space.

Method and device for processing LIDAR sensor data are disclosed. The method includes (i) receiving from the LIDAR sensor a first dataset having a plurality of first data points representative of respective coordinates and associated with respective normal vectors, (ii) determining an uncertainty parameter for a given first data point based on a normal covariance of the normal vector of the given first data point where the normal covariance takes into account a measurement error of the LIDAR sensor when determining the respective coordinates of the given first data point, (iii) in response to the uncertainty parameter being above a pre-determined threshold, excluding the given first data point from the plurality of first data points, (iv) using the filtered plurality of first data points, instead of the plurality of first data points, for merging the first dataset of the LIDAR sensor with a second dataset of the LIDAR sensor.

Systems, methods, and non-transitory computer-readable media can determine a road segment. A set of features associated with the road segment can be determined based at least in part on data captured by one or more sensors of a vehicle. A level of similarity between the road segment and each of a set of road segment types can be determined by comparing the set of features to features associated with each of the set of road segment types. The road segment can be classified as a road segment type based on the level of similarity. Scenario information associated with the road segment can be determined based on the classified road segment type.

A vehicle travel control device includes computation circuitry, and a device controller that controls actuation of a traveling device mounted on a vehicle, based on a result from the computation circuitry. The computation circuitry identifies a vehicle outdoor environment based on an output from image circuitry that acquires image information of vehicle outdoor environment, sets a route on which the vehicle is to travel, in accordance with the vehicle outdoor environment previously identified, determines a target motion of the vehicle to follow the route previously set, calculates a target physical quantity to be executed by the traveling device to achieve the target motion previously determined, and calculates a controlled variable of the traveling device such that the target physical quantity calculated is achieved, and the device controller outputs a control signal to the traveling device so as to control the traveling device to control a motion of the vehicle.

A radar device for a vehicle includes: a radar sensor disposed on either one or both of a front surface of a vehicle and a rear surface of the vehicle, and configured to emit an electromagnetic wave signal toward a road having a lane at least partially containing an electromagnetic wave absorbing paint; and a radar control unit configured to determine whether a target is an object, the road, or the lane, based on an intensity of an electromagnetic wave reflected by the object, the road, or the lane, by using a radar signal received from the radar sensor.

An automatic driving vehicle that is automatically movable, the automatic driving vehicle includes a LIDAR configured to acquire external world information on an automatic movement, and a bracket holding the LIDAR and fixed to the automatic driving vehicle. The bracket is fixed to a rearview mirror which is as another device different from the LIDAR.