The disclosed technology provides solutions for generating simulated scenes to facilitate autonomous vehicle (AV) testing. In some implementations, the disclosed technology encompasses methods for generating simulated scenes that can includes steps for receiving road data, wherein the road data comprises sensor data collected for a recorded scene measured using one or more vehicle-mounted sensors, processing the road data to generate semantic scene data, and generating a simulated scene based on the semantic scene data. Systems and machine-readable media are also provided.

According to one embodiment, a three-dimensional map estimation apparatus includes a processor that selects an imaging apparatus from a plurality of imaging apparatuses and then estimates a position and orientation for a moving object on which the selected imaging apparatus is mounted based on images captured by the selected imaging apparatus. The processor outputs a first position and orientation estimation result for the moving object based on images from selected imaging apparatuses. The processor calculates a second position and orientation estimation result indicating an estimated position and orientation for the moving object using the first position and orientation estimation result. The processor estimates a three-dimensional map for the surroundings of the moving object based on the second position and orientation estimation result.

A computer-implemented method of estimating a 6D pose and shape of one or more objects from a 2D image, comprises the steps of: detecting, within the 2D image, one or more 2D regions of interest, each 2D region of interest containing a corresponding object among the one of more objects; cropping out a corresponding pixel value array, coordinate tensor , and feature map for each 2D region of interest; concatenating the corresponding pixel value array, coordinate tensor, and feature map for each 2D region of interest; and inferring, for each 2D region of interest, a 4D quaternion describing a rotation of the corresponding object in the 3D rotation group, a 2D centroid, which is a projection of a 3D translation of the corresponding object onto a plane of the 2D image given a camera matrix associated to the 2D, image, a distance from a viewpoint of the 2D image to the corresponding object a size and a class-specific latent shape vector of the corresponding object.

A system and method for future forecasting using action priors that include receiving image data associated with a surrounding environment of an ego vehicle and dynamic data associated with dynamic operation of the ego vehicle. The system and method also include analyzing the image data to classify dynamic objects as agents and to detect and annotate actions that are completed by the agents that are located within the surrounding environment of the ego vehicle and analyzing the dynamic data to process an ego motion history that is associated with the ego vehicle that includes vehicle dynamic parameters during a predetermined period of time. The system and method further include predicting future trajectories of the agents located within the surrounding environment of the ego vehicle and a future ego motion of the ego vehicle within the surrounding environment of the ego vehicle based on the annotated actions.

Embodiments for operational envelope detection (OED) with situational assessment are disclosed. Embodiments herein relate to an operational envelope detector that is configured to receive, as inputs, information related to sensors of the system and information related to operational design domain (ODD) requirements. The OED then compares the information related to sensors of the system to the information related to the ODD requirements, and identifies whether the system is operating within its ODD or whether a remedial action is appropriate to adjust the ODD requirements based on the current sensor information. Other embodiments are described and/or claimed.

An apparatus for assisting driving of a vehicle includes a camera mounted to the vehicle for viewing an area in front of the vehicle, a radar sensor mounted to the vehicle to sense around the vehicle, and a controller connected to the camera and/or the radar sensor to detect obstacles and perform collision avoidance control. The controller is further configured to recognize a first obstacle approaching in a lateral direction from an outside of a driving lane of the vehicle, generate and store a collision avoidance path for avoiding collision with the first obstacle, recognize a third obstacle passing behind a second obstacle in the lateral direction after the recognition of the first obstacle is interrupted by the second obstacle, and perform collision avoidance control of the vehicle based on a similarity between the first obstacle and the third obstacle and based on the stored collision avoidance path.

The present invention relates to a method for avoiding collisions of a moving vehicle with other road users in the surroundings of the vehicle, comprising at least the method steps of: a) detecting, by means of one or more sensors, the vehicle surroundings and the other road users located therein; b) dividing the vehicle surroundings into a plurality of occupied areas; c) classifying the other road users detected in method step a), wherein, by means of the classification, at least one road user group is assigned to each of the other road users; d) prioritising the road user classified in method step c), taking into account both the classification carried out in method step c) and the occupied area defined in method step b), wherein road users from one or more predetermined road user groups in the particular occupied area are given a high priority and road users from other, non-predetermined road user groups in the particular occupied area are given a lower priority; and e) determining the probability of collision of the other road users with the vehicle, wherein the collision probability is determined in accordance with the prioritisation carried out in method step d) and the collision probability of the other road users having a high priority is determined first; f) changing or maintaining the current driving behaviour of the vehicle on the basis of the collision probabilities determined in method step e).

A vehicle detection unit detects a plurality of vehicles traveling in an adjacent lane adjacent to a lane where the one vehicle is traveling, based on a sensor mounted on the vehicle. A speed information acquisition unit acquires speed information of a preceding vehicle traveling ahead of a target vehicle traveling right ahead of the one vehicle in the adjacent lane among the plurality of vehicles. A deceleration factor determination unit determines whether there is a deceleration factor in front of the preceding vehicle. A traveling state determination unit determines whether the target vehicle travels with the flow of traffic based on the speed information of the preceding vehicle and whether there is the deceleration factor.

Provided are autonomous vehicles (AV), computer program products, and methods for maneuvering an AV in a roadway, including receiving forecast information associated with predicted trajectories of one or more actors in a roadway, determining a relevant trajectory of an actor based on correlating a forecast for predicted trajectories of the actor with the trajectory of the AV, regenerate a distance table for the relevant trajectory previously generated for processing constraints, generate a plurality of margins for the AV to evaluate, the margins based on a plurality of margin types for providing information about risks and effects on passenger comfort associated with a future proximity of the AV to the actor, classifying an interaction between the AV and the actor based on a plurality of margins, and generating continuous scores for each candidate trajectory that is also within the margin of the actor generated for the relevant trajectory.

A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to receive geoindexed detected vehicle event data from at least one vehicle occurring within a predefined time period, normalize the geoindexed detected vehicle event data according to Global Position System (GPS) data corresponding to a geoindex map, and generate an infrastructure recommendation based on the normalized and aggregated geoindexed detected vehicle event data.