This document discloses system, method, and computer program product embodiments for operating a vehicle, comprising: using kinematic models to generate forecasted trajectories of an actor (the kinematic models being respectively associated with different actor types that are assigned to an actor detected in an environment of the vehicle); selecting a first kinematic model based on the forecasted trajectories and a kinematic state of the actor; using the first kinematic model to predict a first path for the actor; selecting a second kinematic model responsive to movement of the actor no longer being consistent with typical movement of an object of one of the different actor types that is associated with the first kinematic model; using the second kinematic model to predict a second path for the actor; and controlling operations of the vehicle based on the first and second paths.

The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a motion planning system that solves gridlock as part of determining a motion plan for an autonomous vehicle (AV). In particular, a scenario generator within a motion planning system can determine one or more keep clear areas associated with the lane sequence, each keep clear area indicative of a region along the nominal path in which gridlock prevention is desired. A gridlock constraint can be generated for each of the one or more keep clear areas, each constraint being defined as a constraint area in a multi-dimensional space. A low-cost trajectory path can be determined through a portion of the multi-dimensional space that minimizes exposure to the constraint areas and that is consistent with all constraints generated for the one or more objects of interest and the one or more keep clear areas.

Embodiments of the present disclosure disclose a method for controlling an autonomous vehicle to pass through a curve, a device and a medium, and relate to the field of autonomous driving technologies. At least one implementation of the method for controlling an autonomous vehicle to pass through a curve includes: determining a curve boundary within a sensing area in a current driving direction of the autonomous vehicle based on a current position of the autonomous vehicle on the curve; determining a current safe stopping distance of the autonomous vehicle on the curve based on current driving parameters of the autonomous vehicle and the curve boundary; determining a speed threshold of the autonomous vehicle based on the current safe stopping distance, braking parameters of the autonomous vehicle and a curve curvature corresponding to the current position; and controlling a speed of the autonomous vehicle not to exceed the speed threshold.

A vehicle exit assist apparatus includes a target information acquisition device configured to detect a target present around a vehicle and acquire information regarding the detected target as target information; and a control unit configured to determine whether or not an obstruction target having a possibility of obstructing a safe vehicle exit of an occupant of the vehicle while the vehicle is stopped is present based on the target information, and to execute vehicle exit assist control that assists in the safe vehicle exit of the occupant when determination is made that the obstruction target is present. The control unit is configured to determine whether or not the obstruction target is a human being, and not to execute the vehicle exit assist control when determination is made that the obstruction target is a human being.

A travel controller includes: an information acquisition part configured to acquire braking state information of a braking device brake state, travel road information, and an ACC-ECU configured to perform travel, based on a set vehicle speed, and follow-up travel control under which the subject vehicle follows another vehicle traveling ahead thereof. After canceling activation of the travel control during the activation of the travel control, when the information acquisition part acquires travel road information showing that a travel road on which the subject vehicle is traveling is not a downhill road any longer, even if a braking performance index based on the braking state information acquired by the information acquisition part is not increased with respect to a second reference threshold, then the ACC-ECU allows the travel control activation to be resumed.

A drive assist apparatus according to the present disclosure includes: a dynamic information acquisition unit acquiring, as dynamic information, at least one of subject vehicle dynamic information, the other vehicle dynamic information, and obstacle dynamic information from each of a plurality of vehicles; a map data acquisition unit acquiring map data including a shape of a traffic lane; a dynamic information management unit associating the dynamic information and the map data with each other and managing them; an interference prediction unit predicting whether or not the subject vehicle interferes with the other vehicle traveling in front of the subject vehicle along a traffic lane adjacent to a traffic lane along which the subject vehicle travels when the other vehicle avoids the obstacle based on the dynamic information and the map data; and a drive assist information generation unit generating drive assist information based on the predicted result.

In described examples, an apparatus includes an object detection (OD) network that is configured to generate OD polygons in response to a received at least one camera image and a semantic segmentation (SS) network that is configured to generate SS data in response to the received at least one camera image. A processor is configured to generate an updated occupancy grid in response to the OD polygons and the SS data. A vehicle is optionally configured to respond to a driving action generated in response to the updated occupancy grid.

A method for platooning vehicles to pass by an intersection, includes obtaining, by a first vehicle controlling driving of a forward platoon, signal information of the intersection; determining, by the first vehicle, vehicle ranks of the forward platoon to pass by the intersection together based on the signal information; and determining, by the first vehicle, a second vehicle to control another driving of a following platoon to be separated from the forward platoon, in response to determining that the vehicle ranks do not pass by the intersection together.

In various examples, systems are described herein that may evaluate one or more radar detections against a set of filter criteria, the one or more radar detections generated using at least one sensor of a vehicle. The system may then accumulate, based at least on the evaluating, the one or more radar detections to one or energy levels that correspond to one or more locations of the one or more radar detections in a zone positioned relative to the vehicle. The system may then determine one or more safety statuses associated with the zone based at least on one or more magnitudes of the one or more energy levels. The system may transmit data, or take some other action, that causes control of the vehicle based at least on the one or more safety statuses.

A system for detecting a road surface includes a computer programmed to determine a virtual boundary for a vehicle body based on a shape of the vehicle body, upon identifying an object, to identify a plurality of points on the object based on received sensor data, to determine a barrier function based on each of the identified plurality of points, wherein the barrier function includes a barrier distance from a reference point of the virtual boundary of the vehicle to a respective one of the points on the object, based on (i) the determined barrier functions, (ii) the determined virtual boundary of the vehicle, and (iii) an input to at least one of propulsion, steering, or braking, to determine at least one of a braking override or a steering override, and based on the determination, to adjust at least one of a vehicle steering or a vehicle speed.