Determining yaw parameter(s) (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 yaw parameter(s) of the additional vehicle. For example, autonomous steering, acceleration, and/or deceleration of the vehicle can be adapted based on a determined yaw rate of the additional vehicle. In many implementations, the yaw parameter(s) 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 apparatus including: a first detector configured to detect another vehicle information including a longitudinal velocity and a lateral velocity of another vehicle, and distance information including a longitudinal distance and a lateral distance from another vehicle; a second detector configured to detect subject vehicle information including a velocity and a yaw rate of the subject vehicle; a calculator configured to determine whether steering avoidance is executable, on the basis of the another vehicle information, the subject vehicle information, and the distance information, and when steering avoidance is executable, calculate steering avoidance information on steering avoidance of the subject vehicle; and a control unit configured to control the subject vehicle to travel according to the steering avoidance information. Therefore, it is possible to prevent execution of steering avoidance in a case where steering avoidance is not needed or is inexecutable, and safer steering avoidance can be performed.

A vehicle for estimating a moving path of an object approaching from behind, and determining a probability for entering a rear lane and a probability of collision is provided. The vehicle includes a speed sensor that detects speed information, a direction sensor that detects driving direction information, and a radar that senses an object approaching the vehicle. A controller then estimates a moving path of an object traveling on a rear lane and approaching the vehicle from behind and determines whether the vehicle is able to enter the rear lane, based on the speed information acquired by the speed sensor, the driving direction information acquired by the direction sensor, and data of the object sensed by the radar. Accordingly, the controller detects a probability of collision with the object approaching the vehicle on the rear lane.

An apparatus configured for determining an intention to cut in in a vehicle may include a navigation module, a camera, a radar configured to obtain data about an external vehicle, a sensor configured to obtain data about behavior of the vehicle, and a processor configured to be electrically connected to the navigation module, the camera, the radar, and the sensor, wherein the processor is configured to obtain information associated with at least a portion of a road environment, traffic, or road curvature based on data obtained using at least a portion of the navigation module, the camera, the radar, or the sensor and adjust a parameter for determining an intention for a surrounding vehicle which is traveling in a second lane adjacent to a first lane where the vehicle is traveling to cut in, based on the obtained information.

Disclosed is a collision avoidance assisting apparatus which can execute an automatic braking process and an automatic steering process for avoiding collision with an obstacle. When the magnitude of a steering angle exceeds a predetermined threshold, the collision avoidance assisting apparatus determines that a driver has an intention of avoiding the collision by a steering operation and stops the automatic braking process and the automatic steering process. However, in such a case, the automatic braking process and the automatic steering process may be stopped when the steering angle exceeds the threshold as a result of execution of the automatic steering process. In view of this, when both the automatic braking process and the automatic steering process are being executed, the collision avoidance assisting apparatus continues the automatic braking process and the automatic steering process even when the magnitude of the steering angle is greater than the predetermined threshold.

A self-driving safety evaluation method, including determining R.sub.B based on a risk value of a vehicle in a shadow driving mode in a first measurement unit, where R.sub.B is a risk value of the vehicle in the shadow driving mode in a plurality of measurement units, and determining R.sub.C based on a risk value of the vehicle in a self-driving mode based on a preset route in the first measurement unit, where R.sub.C is a risk value of the vehicle in the self-driving mode based on the preset route in the measurement units, where R.sub.B and R.sub.C are used to determine whether safety of the vehicle in the self-driving mode meets a requirement.

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.

The present application relates to a method and apparatus including a sensor for detecting a first vehicle speed, a camera operative to capture an image, a processor operative to determine a road curvature in response to the image, the processor further operative to determine a first predicted lateral acceleration in response to the road curvature and the first vehicle speed, the processor further operative to determine a second vehicle speed in response to the first predicted lateral acceleration exceeding a threshold value wherein the second vehicle speed results in a second predicted lateral acceleration being less than the threshold value, and to generate a control signal indicative of the second vehicle speed, and a vehicle controller operative to reduce a vehicle velocity to the second vehicle speed in response to the control signal.

A non-transitory computer readable storage medium has instructions executed by a processor to obtain the relative speed between a first traffic object and a second traffic object. The separation distance between the first traffic object and the second traffic object is received. The relative speed and the separation distance are combined to form a quantitative measure of hazard encountered by the first traffic object. The obtain, receive and combine operations are repeated to form cumulative measures of hazard associated with the first traffic object. The cumulative measures of hazard are analyzed to derive a first traffic object safety score for the first traffic object.

A vehicle driving assist apparatus acquires a longitudinal distance between an own vehicle and an oncoming vehicle, and a lateral distance between the own vehicle and the oncoming vehicle. The vehicle driving assist apparatus acquires a collision index value which decreases as a ratio of the longitudinal distance to the lateral distance decreases and determine that the own vehicle potentially collides with the oncoming vehicle when a turning condition is satisfied, and a collision condition is satisfied. The turning condition is a condition that the own vehicle turns, crossing an oncoming traffic lane. The collision condition is a condition that the collision index value is within a predetermined index value range. The predetermined index value range at least includes the collision index value acquired when the longitudinal distance is equal to the lateral distance.