Various implementations described herein generate training instances that each include corresponding training instance input that is based on corresponding sensor data of a corresponding autonomous vehicle, and that include corresponding training instance output that is based on corresponding sensor data of a corresponding additional vehicle, where the corresponding additional vehicle is captured at least in part by the corresponding sensor data of the corresponding autonomous vehicle. Various implementations train a machine learning model based on such training instances. Once trained, the machine learning model can enable processing, using the machine learning model, of sensor data from a given autonomous vehicle to predict one or more properties of a given additional vehicle that is captured at least in part by the sensor data.

A method of path planning for a host vehicle includes: receiving host vehicle, environmental and obstacle information; calculating one or more projected host vehicle locations; computing a projected obstacle location for each obstacle; and determining a collision potential between each projected host vehicle location and each projected obstacle location. Until a maximum number of steps is reached, and while at least one projected host vehicle location has an associated collision potential below a collision threshold, the method further includes repeating the calculating, computing and determining steps.

The present invention is a method for determining an optimal speed of a first vehicle preceded by a second vehicle. Position, speed and acceleration of the second vehicle are measured in order to determine a trajectory thereof, and a dynamic model of the first vehicle is constructed. The optimal speed is then determined by minimizing the energy consumption of the vehicle by use of the dynamic model by minimization being constrained by the trajectory of the second vehicle.

Determining an instantaneous vehicle characteristic (e.g., at least one yaw rate) of an additional vehicle that is in addition to a vehicle being autonomously controlled, and adapting autonomous control of the vehicle based on the determined instantaneous vehicle characteristic of the additional vehicle. For example, autonomous steering, acceleration, and/or deceleration of the vehicle can be adapted based on a determined instantaneous vehicle characteristic of the additional vehicle. In many implementations, the instantaneous vehicle characteristics of the additional vehicle are determined based on data from a phase coherent Light Detection and Ranging (LIDAR) component of the vehicle, such as a phase coherent LIDAR monopulse component and/or a frequency-modulated continuous wave (FMCW) LIDAR component.

A collision avoidance method for a vehicle includes monitoring a lateral distance between the vehicle and a target vehicle while the vehicle is travelling within a first lane and the target vehicle is travelling within an adjacent second lane, activating a warning on the vehicle and automatically adjusting operation of the vehicle to increase the distance between the vehicle and the target vehicle when the lateral distance between the vehicle and the target vehicle is less than the threshold distance while the vehicle is travelling within the first lane. Automatically adjusting operation of the vehicle may include one or both of steering the vehicle laterally away from the target vehicle and adjusting a longitudinal velocity of the vehicle. A related collision avoidance system is also provided.

A method secures a host vehicle circulating on a traffic lane of a road infrastructure including at least one lane adjacent to the traffic lane. The securing method includes, for each adjacent lane: detecting a plurality of vehicles present on the adjacent lane, including an estimate of at least one information item relating to each detected vehicle, including the speed; determining, with the detected vehicles forming a flow of vehicles, a value representing the speed of the flow on the adjacent lane, for example, the average speed; comparing the speed of the host vehicle with the value representing the speed of the flow of vehicles on the adjacent lane; and, if the speed of the host vehicle is greater than a predetermined threshold at the value representing the speed of the flow of vehicles on the adjacent lane, detecting a hazardous situation for the host vehicle.

A surrounding vehicle monitoring device includes an acquiring unit configured to acquire a midpoint between a rear left end position and a rear right end position of another vehicle, acquire a width of the other vehicle, and change a current position of a great change position to a corrected position and acquire a midpoint between a current position of a small change position and the corrected position as a position of the other vehicle in a case where a changing amount of the width is equal to or more than a first threshold. The great change position is one of the rear left end position and the rear right end position whose changing amount is the greater of the two. The small change position is another of the rear left end position and the rear right end position whose changing amount is the smaller of the two.

A vehicle may include a communicator configured to receive driver state information from a surrounding vehicle, a detector configured to obtain driving information related to surrounding vehicle, a driving assistance module configured to control at least one of a driving speed or a driving direction and a controller configured to determine whether a driver of the surrounding vehicle is in drowsiness state based on whether the received driver state information satisfies a predetermined condition and if the driver of the surrounding vehicle is determined as drowsiness state, control the driving assistance module to avoid the surrounding vehicle.

A control device detects a first vehicle traveling in front of an own vehicle using a front looking radar device, and detects a second vehicle which is predicted to cut in between the own vehicle and the first vehicle using the front looking radar device and/or front-side looking radar devices. The control device calculates a first target acceleration required for the own vehicle to maintain an inter-vehicle distance between the own vehicle and the first vehicle at a first set inter-vehicle distance; and calculates a second target acceleration required for the own vehicle to maintain an inter-vehicle distance between the own vehicle and the second vehicle at a second set inter-vehicle distance. The control device selects either the first target acceleration or the second target acceleration and controls the own vehicle in such a manner that an actual acceleration of the own vehicle becomes closer to the mediated target acceleration.

A vehicle control device recognizes an intersection present in front of a vehicle proceeding in a first direction on a first road, a first another vehicle proceeding in a second direction opposite to the first direction on the first road to approach the intersection, and a second another vehicle traveling after the first another vehicle, controls the vehicle based on a first relative relation between the first another vehicle and the vehicle and a second relative relation between the second another vehicle and the vehicle, determines, when the first and second another vehicles are expected to enter the second road, whether the vehicle enters the second road after the first another vehicle and before the second another vehicle or after the second another vehicle based on relative relations between a basis position and the vehicle, the first and second another vehicles, and controls the vehicle based on a determining result.