Embodiments herein can determine an optimal route for an autonomous electric vehicle. The system may score viable routes between the start and end locations of a trip using a numeric or other scale that denotes how viable the route is for autonomy. The score is adjusted using a variety of factors where a learning process leverages both offline and online data. The scored routes are not based simply on the shortest distance between the start and end points but determine the best route based on the driving context for the vehicle and the user.

Methods and systems are disclosed for cross-validating a second sensor with a first sensor. Cross-validating the second sensor may include obtaining sensor readings from the first sensor and comparing the sensor readings from the first sensor with sensor readings obtained from the second sensor. In particular, the comparison of the sensor readings may include comparing state information about a vehicle detected by the first sensor and the second sensor. In addition, comparing the sensor readings may include obtaining a first image from the first sensor, obtaining a second image from the second sensor, and then comparing various characteristics of the images. One characteristic that may be compared are object labels applied to the vehicle detected by the first and second sensor. The first and second sensors may be different types of sensors.

A control device for a heater that is installed in at least a portion of a member constituting a part of an outer surface of a vehicle and that melts snow of the member by generating heat through energization, the portion through which a radio wave of a radar installed in the vehicle is transmitted, includes: a dirt determination value calculation unit that calculates a dirt determination value for determining whether dirt adheres to an outer surface of the portion of the member based on a reception level of a radio wave received by the radar; and a heater control unit that executes heating control to energize the heater when an outside air temperature is in a predetermined low temperature range and the dirt determination value is equal to or larger than a predetermined threshold value.

A method for calibrating a radar system includes generating an RF oscillator signal and distributing the RF oscillator signal to a plurality of phase shifters each providing a respective phase-shifted RF oscillator signal; receiving the phase-shifted RF oscillator signals by corresponding radar chips and radiating the phase-shifted RF oscillator signal via a first RF output channel of a first one of the radar chips; receiving a back-scattered signal by at least one RF input channel of each radar chip and generating a plurality of base-band signals by down-converting the received signals into a base band using the phase-shifted RF oscillator signals received by the corresponding radar chips; determining a phase for each base-band signal; and adjusting the phase shifts caused by the phase shifters such that the phases of the base-band signals match a predefined phase-over-antenna-position characteristic.

An image processing device 10 includes an image interface 18, a memory 19, and a controller 20. The image interface 18 acquires a captured image. The positions of specific feature points in a world coordinate system and reference positions of the specific feature points are stored in the memory 19. The controller 20 detects the specific feature points in the captured image. In a case where discrepancy between the position in the captured image and the reference position is found with regard to a predetermined percentage or more of the specific feature points, the controller 20 recalculates a calibration parameter.

An image processing device 10 includes an image interface 18, a memory 19, and a controller 20. The image interface 18 acquires a captured image. The positions of specific feature points in a world coordinate system and reference positions of the specific feature points are stored in the memory 19. The controller 20 detects the specific feature points in the captured image. In a case where discrepancy between the position in the captured image and the reference position is found with regard to a predetermined percentage or more of the specific feature points, the controller 20 recalculates a calibration parameter.

Provided is a scooter radar detection system for a scooter, including: a control module for controlling operation of the scooter radar detection system; two detection radars flanking a license plate, facing the rear of the scooter, and being in signal connection with the control module; two flash alert units disposed at rear-view mirrors on two sides of the scooter, respectively, and being in signal connection with the control module; and a vibration alert module disposed below a seat and being in signal connection with the control module.

A vehicle sensor device (1) includes an outer cover (12), a sensor unit (20) that transmits and receives an electromagnetic wave through the outer cover (12) and outputs a signal related to the electromagnetic wave incident on an inner side of the outer cover (12), a heater (30) that is provided in the outer cover (12) and heats a transmission region (AR) of the outer cover (12) through which the electromagnetic wave emitted from the sensor unit (20) passes, and a control unit (CO). The control unit (CO) outputs a detection signal of an object located outside the outer cover (12) based on the signal from the sensor unit (20) in at least a part of a period in which the heater (30) is OFF, and stops outputting of the detection signal in at least a part of a period in which the heater (30) is ON.

A vehicle sensor device (1) includes an outer cover (12), a sensor unit (20) that transmits and receives an electromagnetic wave through the outer cover (12) and outputs a signal related to the electromagnetic wave incident on an inner side of the outer cover (12), a heater (30) that is provided in the outer cover (12) and heats a transmission region (AR) of the outer cover (12) through which the electromagnetic wave emitted from the sensor unit (20) passes, and a control unit (CO). The control unit (CO) outputs a detection signal of an object located outside the outer cover (12) based on the signal from the sensor unit (20) in at least a part of a period in which the heater (30) is OFF, and stops outputting of the detection signal in at least a part of a period in which the heater (30) is ON.

This document describes techniques and systems of a radar system with sequential two-dimensional (2D) angle estimation. The radar system can efficiently estimate angles in two dimensions for detections. For example, a radar system includes a processor and an antenna that can receive electromagnetic energy reflected by one or more objects. The antenna includes a 2D array that includes antenna elements positioned in a first dimension and a second dimension. The processor can determine, using electromagnetic energy received by the 2D array, first angles in the first dimension associated with a detection of the one or more objects. The processor can then steer the 2D array to the first angle to generate a steered 1D array for each first angle. Using the steered 1D array, the processor can determine second angles associated with the first angle for the detection.