A method of processing data for a driving automation system, the method comprising steps of: obtaining sound data from a microphone of an autonomous vehicle; processing the sound data to obtain a sound characteristic; and updating a context of the autonomous vehicle based on the sound characteristic.

A system for interpreting gestures may include one or more processors, at least three Doppler radar devices, and a memory device. The memory device may have a receiving module, a cube generating module, and a classifying module. The receiving module may include instructions that cause the one or more processors to receive Doppler information from the at least three Doppler radar devices. The cube generating module may include instructions that cause the one or more processors to generate a micro-Doppler cube by projecting Doppler information in X, Y, and Z-directions over a period of time into the micro-Doppler cube. The classifying module may include instructions that cause the one or more processors to classify one or more gestures performed by an extremity when located in the volume into a category of a plurality of categories based on the micro-Doppler cube.

In one embodiment, a process is performed during controlling Autonomous Driving Vehicle (ADV). Microphone signals sense sounds in an environment of the ADV. The microphone signals are combined and filtered to form an audio signal having the sounds sensed in the environment of the ADV. A neural network is applied to the audio signal to detect a presence of an audio signature of an emergency vehicle siren. If the siren is detected, a change in the audio signature to make a determination as to whether the emergency vehicle siren is a) moving towards the ADV, or b) not moving towards the ADV. The ADV can make a driving decision, such as slowing down, stopping, and/or steering to a side, based on if the emergency vehicle siren is moving towards the ADV.

An improved method for locating an acoustic source relative to a vehicle that requires, for example, only a single microphone is disclosed. The method comprises: obtaining an acoustic signal transmitted by the acoustic source; determining an observer frequency, referenced to the vehicle, of the acoustic signal; stipulating a velocity of the acoustic source; stipulating a relative position of the acoustic source relative to a position of the vehicle; determining a signal frequency; and locating the acoustic source by performing, n times, a Doppler calculation using the determined observer frequency, the stipulated velocity, the determined signal frequency, and the stipulated relative position.

The present disclosure describes a computer-implemented method for controlling a vehicle. In aspects, the computer-implemented method includes acquiring sensor data from a sensor, determining first processed data related to a first area around the vehicle based on the sensor data using a machine-learning method, and determining second processed data related to a second area around the vehicle based on the sensor data using a conventional method. The second area may include a subarea of the first area. In addition, the computer-implemented method includes controlling the vehicle based on the first processed data and the second processed data.

A system and method for selectively reducing or filtering data provided by one or more vehicle mounted sensors before using that data to detect, track and/or estimate a stationary object located along the side of a road, such as a guardrail or barrier. According to one example, the method reduces the amount of data by consolidating, classifying and pre-sorting data points from several forward looking radar sensors before using those data points to determine if a stationary roadside object is present. If the method determines that a stationary roadside object is present, then the reduced or filtered data points can be applied to a data fitting algorithm in order to estimate the size, shape and/or other parameters of the object. In one example, the output of the present method is provided to automated or autonomous driving systems.

A speed of a target vehicle can be detected. A difference in host vehicle speed and the speed of the target vehicle is determined. A target frequency is specified for a sound to be received at the target vehicle. A sending frequency is determined for the sound based on the target frequency and the difference in host vehicle speed and target vehicle speed. The sound is transmitted at the sending frequency.

A computer includes a processor and a memory storing instructions executable by the processor to collect at least one set of data with a first Doppler sensor, each set of data including a radial distance, an azimuth angle and a range rate between the first Doppler sensor and a target, collect at least one set of data with a second Doppler sensor, determine that the collected sets of data include a first, second, and third set, determine respective radial components of a ground velocity of the target based on the first, second and third sets of data a position on a host vehicle of the respective Doppler sensor that collected the sets of data, and determine a linear velocity of the target and a yaw rate of the target based on the radial components of the ground velocity of the target.

Disclosed is a driver assistance system including a first processor that receives a radar signal from a radar and detects one or more first objects based on the radar signal, a second processor that receives a camera signal from a camera and detects one or more second objects based on the camera signal, a laser controller that controls a beam generator to radiate the laser beam, a segmentation unit that extracts one or more first segments and one or more second segments corresponding to the one or more second objects, a mapping unit that maps at least one of the first segments and at least one of the second segments, a classification unit that classifies a target object based on an image signal and determines a possibility of collision with the target object, and a vehicle controller that controls a vehicle drive device based on the possibility of collision.

A control device to be applied to a vehicle equipped with an imaging device and a safety device is configured to, based on moving-object detection information detected from images captured by the imaging device, actuate the safety device for a moving object.

In the control device, a control unit is configured to, in response to any of certain information that it is certain that the object is a moving object and uncertain information indicating that it is not certain whether the object is a moving object being acquired as moving-object detection information, actuate the safety device based on a position of the object subjected to detection with the certain information or the uncertain information. An actuation region setting unit is configured to, when the moving-object detection information is the uncertain information, narrow an actuation region as compared to when the moving-object detection information is the certain information.