An autonomous vehicle (AV) includes a radar sensor system and a computing system that computes velocities of an object in a driving environment of the AV based upon radar data that is representative of radar returns received by the radar sensor system. The AV can be configured to compute a first velocity of the object based upon first radar data that is representative of the radar return from a first time to a second time. The AV can further be configured to compute a second velocity of the object based upon second radar data that includes at least a portion of the first radar data and further includes additional radar data representative of a radar return received subsequent to the second time. The AV can further be configured to control one of a propulsion system, a steering system, or a braking system to effectuate motion of the AV based upon the computed velocities.

A system comprises a computer having a processor and a memory, the memory storing instructions executable by the processor to access sensor data of a sensor of a vehicle while an adaptive cruise control feature of the vehicle is active, detect, based on the sensor data, an object located along a path of travel of the vehicle, determine that the object is a moveable object based on a radar return of a radar reflector of the object, and responsive to the determination that the object is the moveable object, adjust, by the adaptive cruise control feature, the speed of the vehicle.

A radar-based system for determining the local position of a vehicle uses markers with at least one radar-reflective element, as well as a radar system and vehicle controller. The radar system transmits radio waves, which are reflected by nearby objects, including the radar markers. The radar system receives the reflected radio waves and detects the unique radar signatures from the radar markers, as well as range, azimuth, and/or elevation dimensions of the vehicle with respect to the radar markers. The unique radar signatures and dimensions are communicated to the vehicle controller, which then determines the local position of the vehicle from the unique radar signatures and dimensions.

Some radar sensors may provide a Doppler measurement indicating a relative velocity of an object to a velocity of the radar sensor. Techniques for determining a two-or-more-dimensional velocity from one or more radar measurements associated with an object may comprise determining a data structure that comprises a yaw assumption and a set of weights to tune the influence of the yaw assumption. Determining the two-or-more-dimensional velocity may further comprise using the data structure as part of regression algorithm to determine a velocity and/or yaw rate associated with the object.

The techniques and systems herein enable target-velocity estimation using position variance. Specifically, a plurality of detections of a target are received for respective times as the target moves relative to a host vehicle. Based on the detections, two-dimensional positions of the target relative to the host vehicle are determined for the respective times. Based on the positions of the target at the respective times, a first variance is determined for a first dimension of the positions, and a second variance is determined for a second dimension of the positions. Based on the first and second variances, an estimated velocity of the target is calculated. By basing the estimated velocity on the variances of the positions, more-accurate estimated velocities may be generated sooner, thus enabling better performance of downstream operations.

Disclosed are techniques for determining a motion state of a target object. In an aspect, an on-board computer of an ego vehicle detects the target object in one or more images, determines one or more first attributes of the target object based on measurements of the one or more images, determines one or more second attributes of the target object based on measurements of a map of a roadway on which the target object is travelling, and determines the motion state of the target object based on the one or more first attributes and the one or more second attributes of the target object.

A hybrid electric vehicle and a method of controlling the same are provided to avoid a collision thereof attributable to erroneous operation of an accelerator pedal. The method includes determining whether an accelerator pedal is erroneously operated in the situation in which an obstacle is detected to be present in the traveling path. In response to determining that the accelerator pedal is erroneously operated, the method includes switching the driving mode to a mode in which an engine is disconnected from a driving shaft and a motor generates driving force. The number of revolutions per minute (RPM) of the engine is then adjusted based on the extent to which the accelerator pedal is operated and the torque of the motor is adjusted based on a first vehicle speed and the distance to the obstacle.

A sensor information fusion device and a method thereof are provided. The sensor information fusion device includes a processor that generates a first track box and a second track box based on an object detected by a plurality of sensors and determines whether the first track box and the second track box are overlapped with each other and a storage storing data obtained by the processor and an algorithm run by the processor. The processor generates a merge gate expanded from the first track box and determines the first track box and the second track box are overlapped with each other when the second track box is included in the merge gate.

A method and system for validating the calculated localization (15) of a vehicle are devised. The vehicle (1) is equipped with P independent localization data sources (2-8), with P higher than or equal to 2. The method and system involve the step of comparing data provided by each one of a subset of M, with M lower than or equal to P, of the independent localization data sources with the calculated localization, by correlating an independent localization data source among the subset M if it is above a predetermined Reliability Threshold, and the distance between the data it provides and the calculated localization is lower than a predetermined Compatibility Threshold, and disregarding an independent localization data source among the subset M if either it is below the predetermined Reliability Threshold, or the distance between the data it provides and the calculated localization is higher than the predetermined Compatibility Threshold, and the step of modifying the speed of the vehicle (1) depending on the number of correlated independent localization data sources among the subset M relative to a predetermined Voting Threshold.

A vehicular forward-sensing system includes a radar sensor and a forward viewing image sensor disposed within a windshield electronics module that is removably installed within an interior cabin at a windshield of a vehicle. A control is responsive to outputs of the radar sensor and of the image sensor. The image sensor captures image data for an automatic headlamp control system of the vehicle and for a lane departure warning system of the vehicle. The image sensor views and the radar sensor senses an object present in the path of forward travel of the vehicle. The control determines that the object is an object of interest based at least in part on the image sensor viewing the object present in the path of forward travel of the vehicle and the radar sensor sensing the object present in the path of forward travel of the vehicle.