Systems, methods, and other embodiments described herein relate to implementing and calibrating a learning model for inferring operator intent by estimating grip intensity. In one embodiment, a method includes estimating, using a learning model during a driving scenario, first grip intensity on a steering device for a vehicle according to initial image data depicting a hand of an operator gripping outside the set areas that have pressure sensors. The method also includes calibrating the learning model for the operator and the steering device using grip measurements and additional image data acquired from gripping inside the set areas. The method also includes computing, using the learning model during the driving scenario, second grip intensity outside the set areas on the steering device according to hand images acquired about the operator. The method also includes adapting a vehicle parameter of the vehicle according to the second grip intensity.

A utility vehicle includes: a travel structure including a front wheel, a rear wheel, a steering structure mounted to the front wheel, and a drive source that drives the front wheel and/or the rear wheel; at least one operator used to operate the travel structure; circuitry that controls the travel structure; and a mode switcher that switches the utility vehicle between a manned operation mode in which the utility vehicle travels in response to operations on the operator and an autonomous travel mode in which the circuitry allows the utility vehicle to autonomously travel on a given travel route without any operations on the operator.

A parking assist system of a vehicle includes a camera that, when disposed at the vehicle, has a field of view exterior of the vehicle. An image processor is operable to process image data captured by the camera to detect parking space markers indicative of a parking space and to identify empty or available parking spaces. The image processor includes a parking space detection algorithm that detects parking space markers by (i) extracting low level features from captured image data, (ii) classifying pixels as being part of a parking space line or not part of a parking space line, (iii) performing spatial line fitting to find lines in the captured images and to apply parking space geometry constraints, and (iv) detecting and selecting rectangles in the captured images.

A method for enhancing the sensing capabilities of an autonomous vehicle. The method includes extending an extension assembly mounted to the autonomous vehicle to position one or more sensors above the autonomous vehicle and receiving, from the one or more sensors, at least one sensor signal representing one or more vehicle environment conditions surrounding the autonomous vehicle. The method also includes generating a vehicle state for the autonomous vehicle based at least on a location of the autonomous vehicle, the vehicle state comprising the one or more vehicle environment conditions.

A method of developing a road conditioning monitoring model is disclosed. The method comprises utilizing vehicle sensors to collect data under controlled conditions over a road surface to develop a training data set. The training data set undergoes a data analysis to determine an absolute running mean associated with the first road surface under controlled conditions. Abnormalities in the road surface are detected by comparing the absolute running mean with the training data set. The detected abnormalities are classified to create road surface classification rules. A method of developing a road condition database is also disclosed, that comprises utilizing vehicle sensors during operation of a vehicle to collect data during the operation and feeding the data into the road conditioning monitoring model to classify the road conditions on which the vehicle is driven. A system for determining road condition impact on a vehicle is also disclosed.

It is advantageous for a vehicle to detect road wetness or related environmental conditions. This is particularly true for self-driving vehicles, which can then adjust the manner of automated operation of the vehicle to increase safety by reducing speed, braking earlier, adjusting internal estimates of road traction parameters, or adjusting autonomous operation in some other manner. It is difficult to directly measure road wetness (e.g., using spectroscopy or other methods directed at the road surface), however, it is possible to indirectly estimate road wetness based on road noise audio signals detected via one or more microphones disposed on the vehicle. The location of the microphones, the type of post-processing applied to the audio signals, or other factors can be adapted to increase the useful road wetness-related content of such audio signals while reducing the presence of engine noise, road noise, or other confounding signals.

The subject disclosure relates to estimating a chassis frame of an autonomous vehicle. A process of the disclosed technology can include receiving a position for each of a plurality of sensors on an autonomous vehicle, determining an ideal chassis point in relation to a constellation of model sensors in a CAD model associated with the autonomous vehicle, generating a constellation of the plurality of sensors based on the positions of the plurality of sensors in relation to the ideal chassis point, minimizing distortion between measured values associated with the constellation of the plurality of sensors and ideal values associated with the constellation of model sensors, determining an estimated real chassis point based on the minimized distortion between the measured values and the ideal values, and calibrating at least one of the plurality of sensors based on the estimated real chassis point.

Out of two areas divided by a virtual line passing through the center of gravity position in the front-back direction of a vehicle, a second acceleration sensor is arranged in an area different from the area where a first acceleration sensor is arranged. Out of two areas divided by a virtual line passing through the center of gravity position in the vehicle width direction, the third acceleration sensor is arranged in an area different from the area where the first acceleration sensor is arranged. At least one of the following conditions is satisfied: the first condition where the third acceleration sensor is located between the first acceleration sensor and the second acceleration sensor in the vehicle width direction; and the second condition where the second acceleration sensor is located between the first acceleration sensor and the third acceleration sensor in the front-back direction of the vehicle.

Vehicles may include a wide range of individual components and systems that work together to achieve advanced and high-performance states. A system correlates active faults arising among vehicle components to active constraints to determine what fault may be contributing to limited operations. In addition, an association between the active fault and active constraint may be presented to assist with diagnostics.

Example embodiments relate to techniques for adjusting vehicle behavior based on ambient ground relative wind estimations. An onboard computing system may receive wind data from one or multiple wind sensors positioned onboard a vehicle. The wind data can indicate a direction and a speed of wind propagating in the vehicle's environment. The computing system can also receive navigation data that represents a direction and a speed of the vehicle and then estimate an ambient ground relative wind speed based on the navigation data and the wind data. The computing system can adjust the behavior of the vehicle based on the ambient ground relative wind speed. For instance, the computing system may compare the speed of the ambient ground relative wind to a predefined behavior threshold curve and adjust the behavior of the vehicle based on the comparison.