An obstacle shape estimating apparatus and a method thereof, includes: a processor configured to receive a the sensing signal from at least one ultrasonic sensor at a predetermined cycle, to generate positions of one or more obstacles according to distance values of an ultrasonic sensor by estimating the distance values of the ultrasonic sensor based on a sensing signal, and to generate obstacle shape information according to positions of remaining obstacles after deleting a position of an obstacle corresponding to a virtual distance value and a position of an obstacle which does not satisfy a validation condition among the positions of the one or more obstacles; and a storage configured to store data and an algorithm driven by the processor, and the obstacle shape information generated by the processor.

A computer-implemented method comprises: continuously monitoring, by an assisted-driving (AD) system using a sensor, surroundings of a vehicle being controlled by a driver; detecting, by the AD system using the sensor, a parking spot that is available; planning, by the AD system and in response to detecting the parking spot, a trajectory for the vehicle to park in the parking spot; and generating a prompt to the driver, by the AD system and in response to detecting the parking spot, to have the AD system handle parking of the vehicle in the parking spot, the prompt performed before the vehicle reaches the parking spot.

An object detection device that detects a corner of an object includes: a transmitter that transmits a search wave; receivers that receive a reflected wave reflected off the corner. The device determines a first path length of the search wave from the transmitter to a first receiver, and uses the positions of the transmitter and the first receiver as focal points to find a first ellipse whose distances from the transmitter and the first receiver add up to the first path length. The device determines a second path length of the search wave from the transmitter to a second receiver, and uses the positions of the transmitter and the second receiver as focal points to find a second ellipse whose distances from the transmitter and the second receiver add up to the second path length. The device finds an intersection point between the first and second ellipses as the corner.

An ultrasound sensor includes a frame, wherein the frame includes an outer perimeter, an inner perimeter, and a midsection, wherein the midsection extends across the inner perimeter. The sensor further includes two or more transducer elements, wherein the two or more transducer elements are located within the inner perimeter, and include one or more membranes that include a bottom portion that includes a first piezoelectric layer and second piezoelectric layer, wherein the two or more transducer elements are each separated from the midsection, wherein the two or more transducer elements are configured to each activate a transmit mode and receive mode, wherein the transmit mode is configured to transmit a signal and the receive mode is configured to receive a signal, wherein a first transducer element activates the transmit mode when a second transducer element does not activate the transmit mode.

An ultrasound transducer of a vehicle system, comprising a membrane configured to vibrate to generate an ultrasound when voltage is applied and further configured to vibrate in an out-of-plane movement, wherein the membrane includes a first piezoelectric film at a center of the membrane, a supporting member including a second piezoelectric film, the supporting member supporting and surrounding the membrane, wherein in response to a translation of motion or actuation from the membrane, the supporting member mode does not move when there is the out-of-plane movement from the membrane.

An ultrasound transducer of a vehicle system includes a support member that attaches to and connects to the bottom portion of a membrane of the ultrasound transducer and supports the membrane, wherein the support member includes one or more cantilevers with a first end attaching to the membrane and a second end attaching to a support portion of the support member that attaches to the substrate, wherein the cantilever extends across and floats above the substrate, wherein the first end of the cantilever includes a stub extending away from a surface of the cantilever, wherein the stub extends away from the surface without contacting the substrate, wherein the one or more cantilevers includes one or more piezoelectric layers on the surface of the cantilever.

An ultrasound transducer, wherein the ultrasound transducer includes a membrane including a top portion and a bottom portion, wherein the membrane is configured to vibrate and generate an ultrasound in response to voltage applied the transducer, wherein the membrane includes a perimeter including a plurality of sides and a top surface and a bottom surface with one or more feet extending away from the bottom surface; and a support member that attaches to and connects to the membrane and supports the membrane, wherein the support member includes one or more platforms extending to and attaching to the membrane and a substrate, wherein a first end of the platform connects to the membrane and includes a support portion, wherein the support portion away from the platform, wherein the platform includes the one or more piezoelectric layers, wherein the one or more platforms support and surround the membrane.

A method can be used for adaptive parking of a vehicle. A parking area is determined around a programmed destination of the vehicle. The parking area has more than one available parking spot for the vehicle. Parking data is acquired via a wireless communication network. The parking data for each parked vehicle includes a parking position and an individual sensing coverage of an environment sensor system of the respective parked vehicle scanning the traffic environment within the parking area. Available parking spots are ranked based on a calculated overall sensing coverage and a recommended parking spot is determined among the available parking spots based on overall sensing coverage of the traffic environment in the parking area.

A method and system is disclosed for creating a machine learning model that is reconfigurable. A fixed parameter model is created to include fixed feature values obtained during a training process for the machine learning model. The fixed parameter model may include a fixed base classifier used by the machine learning model to classify objects detected by an ultra-sonic system within a vicinity of a vehicle. A configurable parameter model may be created to include feature values that are different from the fixed feature values, the configurable parameter model including a modified base classifier. A vehicle controller may receive and update the fixed parameter model with the configurable parameter model. The machine learning model may be updated to use the configurable parameter model to classify the objects detected by the ultra-sonic system.

A method and system is disclosed for tuning a machine learning classifier. An object class requirement may be provided and include rank thresholds. The object class requirements may also include a range goal that defines a minimum distance from the object the machine learning algorithm should not provide false positive results. A base classifier may be trained using a weighted loss function that includes one or more weight values that are computed using the one or more object class requirements. An output of the weighted loss function may be evaluated using an objective function which may be established using the one or more object class requirements. The one or more weights may also be re-tuned using the weighted loss function if the output of the weighted loss function does not converge within a predetermined loss threshold.