Disclosed herein are system, method, and computer program product embodiments for automated autonomous vehicle pose validation. An embodiment operates by generating a range image from a point cloud solution comprising a pose estimate for an autonomous vehicle. The embodiment queries the range image for predicted ranges and predicted class labels corresponding to lidar beams projected into the range image. The embodiment generates a vector of features from the range image. The embodiment compares a plurality of values to the vector of features using a binary classifier. The embodiment validates the autonomous vehicle pose based on the comparison of the plurality of values to the vector of features using the binary classifier.

An autonomous vehicle control system includes one or more processors. The one or more processors are configured to cause a transmitter to transmit a transmit signal from a laser source. The one or more processors are configured to cause a receiver to receive a return signal reflected by an object. The one or more processors are configured to cause one or more optics to generate a first polarized signal of the return signal with a first polarization, and generate a second polarized signal of the return signal with a second polarization. The one or more processors are configured to calculate a value of reflectivity based on a signal-to-noise ratio (SNR) value of the first polarized signal and an SNR value of the second polarized signal. The one or more processors are configured to operate a vehicle based on the value of reflectivity.

Techniques for collecting, synchronizing, and displaying various types of data relating to a road segment enable, via one or more local or remote processors, servers, transceivers, and/or sensors, (i) enhanced and contextualized analysis of vehicle events by way of synchronizing different data types, relating to a monitored road segment, collected via various different types of data sources; (ii) enhanced and contextualized analysis of filed insurance claims pertaining to a vehicle incident at a road segment; (iii) advantageous machine learning techniques for predicting a level of risk assumed for a given vehicle event or a given road segment; (iv) techniques for accounting for region-specific driver profiles when controlling autonomous vehicles; and/or (v) improved techniques for providing a GUI to display collected data in a meaningful and contextualized manner.

The disclosed aspects and implementations enable efficient disambiguation of spurious internal reflections in sensing (lidar, radar, or sonar) devices from reflections off closely positioned objects by imparting a longitudinal motion to the sensing devices, or components of such devices. In one implementation, the disclosed techniques involve outputting a transmitted wave and receiving a reflected wave generated by the transmitted wave while imparting, to a transceiver, a velocity along a direction of the transmitted wave. The techniques further involve detecting a difference of a transmitted wave frequency and a reflected wave frequency and determining whether the reflected beam is reflected from a real object located in an outside environment or is caused by an internal reflection within the sensing device.

A vehicular control system includes a sensor disposed at a vehicle and sensing exterior and at least forward of the vehicle. The vehicular control system is operable in a student driver mode. The vehicular control system, responsive to processing the sensor data, determines when the vehicle is undertaking a parking maneuver. The vehicular control system, responsive to determining that the vehicle is undertaking a parking maneuver and when the vehicular control system is operating in the student driver mode, determines when an acceleration of the vehicle is unintentional. The vehicular control system, responsive to determining that the acceleration of the vehicle is unintentional, limits acceleration of the vehicle.

According to an aspect of an embodiment, a method may include obtaining multiple sets of camera images and light detection and ranging (LIDAR) point clouds along a track within a geographic sector of a map. The method may include applying a learning model to the camera images to characterize objects within the camera images within classes of objects to generate segmented images. The method may additionally include mapping the sets of camera images and the LIDAR point clouds to three dimensional points of the geographic sector of the map. The method may also include projecting the three dimensional points onto the segmented images to obtain corresponding classes for the three dimensional points of the geographic sector of the map.

Techniques for analysis of autonomous vehicle operations are described. As an example, a method of autonomous vehicle operation includes storing sensor data from one or more sensors located on the autonomous vehicle into a storage medium, performing, based on at least some of the sensor data, a simulated execution of one or more programs associated with the operations of the autonomous vehicle, generating, based on the simulated execution of the one or more programs and as part of a simulation, one or more control signal values that control a simulated driving behavior of a simulated vehicle, and providing a visual feedback of the simulated driving behavior of the simulated vehicle on a simulated road.

The disclosure relates to a method for operating a lane change assistance system, in which a detection apparatus, which is provided on a front corner of the motor vehicle, monitors an adjacent lane in front and to the side, and in which the detection apparatus detects an object on the adjacent lane and, when the detected object is evaluated by way of an electronic computing apparatus, at least one characterizing parameter of the object is determined, wherein at least one function unit detects an intention of a user of the motor vehicle to change lane and a differential speed between the motor vehicle and the object is determined as a characterizing parameter and the electronic computing apparatus generates at least one control signal for at least one further function unit on the basis of the intention to change lane and the differential speed.

A vehicular multi-sensor system includes a plurality of sensors that include at least a forward-viewing camera and a forward-sensing 3D point-cloud LIDAR sensor. The forward-viewing camera views (i) a traffic lane of a multi-lane road being traveled along by the equipped vehicle and (ii) another traffic lane of the multi-lane road, and the field of sensing of the forward-sensing 3D point-cloud LIDAR sensor at least encompasses the other traffic lane of the multi-lane road. Image data captured by the forward-viewing camera is transferred to and is processed at an electronic control unit (ECU). 3D point-cloud LIDAR data captured by the forward-sensing 3D point-cloud LIDAR sensor is transferred to and processed at the ECU. Responsive at least in part to processing at the ECU of 3D point-cloud LIDAR data captured by the forward-sensing 3D point-cloud LIDAR sensor, a traffic participant present forward of the equipped vehicle is detected.

Provided are methods for managing vehicle resources based on scenarios, which can include obtaining, from the at least one sensor, information representative of the environment of the vehicle; determining, based on the information representative of the environment of the vehicle, a current scenario of the environment of the vehicle; determining, based on the determined current scenario, a level of computational resources appropriate for the determined current scenario; and adjusting at least one parameter associated with the at least one sensor based on the determined level of computational resources. Systems and computer program products are also provided.