Systems, methods, and other embodiments described herein relate to automatically determining the size of a trailer being towed by a vehicle. In one embodiment, a method includes, responsive to determining that a trailer is aligned with a towing vehicle, analyzing radar returns from a radar of the towing vehicle to identify radar features within an area behind the towing vehicle. The method includes determining a trailer size of the trailer from the radar features. The method includes adjusting operation of the towing vehicle according to the trailer size.

A radar system (210) for a vehicle (200), comprising a plurality of radar transceivers (202, 203, 204, 205) and a control unit (208). Each radar transceiver (202, 203, 204, 205) is associated with a main pointing direction (P1, P2, P3, P4) and a certain frequency sub-band (A, B, C, D), where the sub-bands (A, B, C, D) together form a certain dedicated frequency band. The control unit (208) is adapted to define heading intervals which divide a full turn interval 0°-360° into sections, assign a corresponding sub-band (A, B, C, D) to each heading interval, determine a present vehicle heading (F), and to assign a corresponding sub-band (A, B, C, D) to each one of the radar transceivers (202, 203, 204, 205) in dependence of the heading interval that includes the present vehicle heading (F).

Parking sensor system for a vehicle (1). The system includes one or more sensor assemblies (4) for mounting to elevated mounting locations (8,9,10) on the vehicle (1), each including a RADAR sensor (7) having a downwardly facing field of view for detecting objects below the respective elevated mounting location (8,9,10) during a parking operation. At least one of the sensor assemblies (4) may further include a parking camera (6) having a downwardly facing field of view for viewing objects below the elevated mounting location (8,9,10) during the parking operation.

Various examples of the present disclosure include a stereoscopic deep neural network (DNN) that produces accurate and reliable results in real-time. Both LIDAR data (supervised training) and photometric error (unsupervised training) may be used to train the DNN in a semi-supervised manner. The stereoscopic DNN may use an exponential linear unit (ELU) activation function to increase processing speeds, as well as a machine learned argmax function that may include a plurality of convolutional layers having trainable parameters to account for context. The stereoscopic DNN may further include layers having an encoder/decoder architecture, where the encoder portion of the layers may include a combination of three-dimensional convolutional layers followed by two-dimensional convolutional layers.

A split-steer amplifier with an invertible phase output, includes a first transistor having its base coupled to a positive node of an input port, its emitter coupled to ground, and collector connected to a positive intermediate node; a second transistor having its base coupled to a negative node of the input port, its emitter coupled to ground, and collector connected to a negative intermediate node; and multiple output ports each having a transistor arrangement operable to couple a positive node of that output port to the positive intermediate node and a negative node of that output port to the negative intermediate node, operable to couple the positive node of that output port to the negative intermediate node and the negative node of that output port to the positive intermediate node, and operable to decouple the positive node and the negative node of that output port from the intermediate nodes.

A vehicle control device is mountable on a vehicle. The vehicle control device includes: a processor; and a memory storing instructions that, when executed by the processor, cause the vehicle control device to perform operations including: acquiring detection information obtained by detecting an obstacle around the vehicle; performing collision determination of evaluating a possibility of collision with the obstacle; generating, based on the detection information, information on an approaching object that is an obstacle approaching the vehicle and information on a detection point indicating an obstacle that does not move; estimating a position of a shielding object based on the information on the detection point; evaluating, based on the position of the shielding object and the information on the approaching object, a ghost likelihood indicating a possibility that the approaching object is a ghost; and excluding, based on the ghost likelihood, the approaching object from the collision determination.

Disclosed are systems that include a controller circuit in communication with a ranging sensor configured to detect objects proximate to a host vehicle. In an aspect, the controller circuit is configured to perform a first detection count of the detected objects, determine a first group of objects of the detected objects, determine a first distance to the first group of objects, utilize the first distance to determine a trailer distance between the host vehicle and a front of a trailer, determine a second group of objects of the detected objects, determine a second distance to the second group of objects, utilize the second distance to determine an axle distance between the front of the trailer and a trailer axle, and determine a trailer length based on the trailer distance and the axle distance. Methods are also disclosed.

A system and method for an on-demand shuttle, bus, or taxi service able to operate on private and public roads provides situational awareness and confidence displays. The shuttle may include ISO 26262 Level 4 or Level 5 functionality and can vary the route dynamically on-demand, and/or follow a predefined route or virtual rail. The shuttle is able to stop at any predetermined station along the route. The system allows passengers to request rides and interact with the system via a variety of interfaces, including without limitation a mobile device, desktop computer, or kiosks. Each shuttle preferably includes an in-vehicle controller, which preferably is an AI Supercomputer designed and optimized for autonomous vehicle functionality, with computer vision, deep learning, and real time ray tracing accelerators. An AI Dispatcher performs AI simulations to optimize system performance according to operator-specified system parameters.

An electronic device includes a controller that performs control to enable switching between a first band mode such that a transmission wave is in a first band and a second band mode such that the transmission wave is in a second band broader than the first band. The controller performs control to switch to the second band mode when an object is detected within a predetermined distance in the first band mode.

A vehicle radar device includes a radar control unit, a first antenna array, a second antenna array, a first circuit board and a second circuit board. The first antenna array is communicatively connected to the radar control unit. The first antenna array includes a plurality of first transmitting elements and a plurality of first receiving elements. The second antenna array is communicatively connected to the radar control unit. The second antenna array includes a plurality of second transmitting elements and a plurality of second receiving elements. The first antenna array is a plurality of circuit board antennas and disposed on the first circuit board. The second antenna array is a plurality of circuit board antennas and disposed on the second circuit board.