A system to reduce VRU unreferenced heading drift error is disclosed. The VRU comprises an IMU and a processor, which hosts first and second modules for bias cancelation. The first module reads inertial data from the IMU when the VRU is powered on; determines whether the VRU is static for a time period; if the VRU is static, corrects gyroscope bias by subtracting an initial bias value from a previous bias value; sets a predefined initial yaw value. The second module reads inertial data from the IMU during in-run operation of the VRU; updates roll, pitch and yaw data, based on input data from a sensor fusion algorithm; outputs updated roll, pitch and yaw data; determines whether the VRU is static for a time period; and if the VRU is static, corrects the bias by subtracting a current bias value, multiplied by a predefined parameter, from a previous bias value.

A system and corresponding method for autonomous driving of a vehicle are provided. The system comprises at least one neural network (NN) that generates at least one output for controlling the autonomous driving. The system further comprises a main data path that routes bulk sensor data to the at least one NN and a low-latency data path with reduced latency relative to the main data path. The low-latency data path routes limited sensor data to the at least one NN which, in turn, employs the limited sensor data to improve performance of the at least one NN's processing of the bulk sensor data for generating the at least one output. Improving performance of the at least one NN's processing of the bulk sensor data enables the system to, for example, identify a safety hazard sooner, enabling the autonomous driving to divert the vehicle and avoid contact with the safety hazard.

A suspension characteristic is changed depending on a travel state by a simple structure. An ECU uses a vehicle speed-spring constant setting part to calculate a target spring constant depending on a vehicle speed, and uses a spring constant-frequency setting part to calculate a set frequency corresponding to the target spring constant. An oscillation input calculation part generates a signal representing an oscillation input oscillating at the set frequency. A superimposition part sets a value acquired by superimposing the oscillation input on a target driving force to a new target driving force. As a result, the wheel exhibits a minute oscillation in a longitudinal direction, resulting in an input of the minute oscillation to a suspension bush. The suspension bush changes in a spring constant and a damping coefficient depending on the frequency of the input minute oscillation. As a result, the suspension characteristic can be changed.

A method is described for determining a position of a two-wheeled vehicle. The single-track vehicle has a vehicle path yaw rate when driving along curves and a yaw rate according to the inclined orientation which differs from the vehicle path yaw rate. An inclined orientation of the single-track vehicle and a speed of the single-track vehicle are measured. The vehicle path yaw rate of the single-track vehicle is determined from the measured inclined orientation and the measured speed. A device for carrying out the method is also described.

Sensor data is received at a processor of a vehicle including at least one sensor, a plurality of axles, and a plurality of tires coupled to the plurality of axles. A determination is made by the processor if at least one tire from the plurality of tires is faulty based on the sensor data. A determination is made by the processor of at least one side of the vehicle and at least one axle from the set of axles associated with the at least one tire in response to the determining that the at least one tire is faulty. A determination is made by the processor of at least one remedial action to be performed by the vehicle based on the sensor data, the at least one side, and the at least one axle.

Excess fuel consumption monitor and feedback systems for vehicles include sensor arrays of two primary types including those sensors deployed as part of a vehicle manufacturer established sensor suite and sensors deployed as after-market sensors. Together, these sensor suites include sensors coupled to vehicle subsystems and operating environments associated with the vehicle. Data from these sensors may be used as parametric inputs to drive algorithmic calculations which have outputs that express excess fuel consumption. Expressions of excess fuel consumption may be made instantaneously as real-time feedback to a vehicle operator/driver and/or a fleet manager as part of a summary report.

A lane-keeping system suitable for use on an automated vehicle includes a camera, an inertial-measurement-unit, and a controller. The camera is configured to detect a lane-marking of a roadway traveled by a vehicle. The inertial-measurement-unit is configured to determine relative-motion of the vehicle. The controller in communication with the camera and the inertial-measurement-unit. When the lane-marking is detected the controller is configured to steer the vehicle towards a centerline of the roadway based on a last-position, and determine an offset-vector indicative of motion of the vehicle relative to the centerline of the roadway. When the lane-marking is not detected the controller is configured to: determine an offset-position relative to the last-position based on information from the inertial-measurement-unit, determine a correction-vector used to steer the vehicle from the offset-position towards the centerline of the roadway based on the last-position and the offset-vector, and steer the vehicle according to the correction-vector.

There is provided a straddle type vehicle including a processing circuit. The processing circuit is configured to: change, upon receiving a boost signal from a boost input device, a target torque from a normal torque to a boost torque obtained by adding a predetermined boost amount to the normal torque; and correct, upon receiving a predetermined inclination signal from the posture detector, the target torque such that a torque change of the drive wheel when the target torque is changed from the normal torque to the boost torque is decreased as compared with a case where the inclination signal is not received.

An autonomous vehicle is provided that includes one or more sensors coupled to the autonomous vehicle, and a computing device configured to: (i) receive, from the one or more sensors, operational data related to an operation of the autonomous vehicle, (ii) receive geographical data related to an anticipated route of the autonomous vehicle, (iii) generate, for the anticipated route and based on the operational data and the geographical data, an operational response model representing respective operational constraints for one or more operational parameters of the autonomous vehicle, wherein values for the one or more operational parameters are represented along coordinate axes of a geometrical shape, and wherein the one or more operational parameters are mutually coupled to each other, and (iv) responsively execute, based on the operational response model, an autonomous control strategy comprising one or more adjustments to the operation of the vehicle within the respective operational constraints.

A system and method for localization of an autonomous vehicle based on 3D point cloud are disclosed. The system includes a processor and a memory coupled to the processor, the memory tangibly storing thereon executable instructions that, when executed by the processor, cause the processor to: receive an initial position of a vehicle; receive a data file representative of a three-dimensional (3D) point cloud from a LIDAR scanning subsystem of the vehicle; divide the 3D point cloud into a plurality of tiles and compute a plurality of key points for each tile; generate an estimated low frequency 2D position and yaw angle for the vehicle based on a particle filter process and a dynamically downloaded 2D reference map; and generate a position and orientation of the vehicle.