A vehicle can include throttle, braking, and steering systems. The vehicle can further include a computing system that obtains, from one or more sensors, data representing one or more of a velocity or an acceleration of the vehicle. The computing system can further determine an estimated weight of the vehicle based on the one or more of the velocity or the acceleration of the vehicle, and autonomously operate the throttle, braking, and steering systems of the vehicle based on the estimated weight of the vehicle.

A computing system determines an estimated weight of a vehicle by measuring kinematic data of the vehicle, including at least one of a velocity or an acceleration of the vehicle. The computing system processes the data to determine an estimated weight of the vehicle. Based on the estimated weight of the vehicle, the computing system can autonomously operate the throttle, braking, and steering systems of the vehicle.

A method for determining non-directly measurable driving status variables of a vehicle reads in by a sensor device and transmits to a computing device the following: wheel speed of each vehicle wheel, steering angle of the vehicle, yaw angle rate, longitudinal road inclination of the vehicle, transverse road inclination of the vehicle.

Driving status variables are calculated by the computing device with a computational model, so that further driving variables that are difficult to measure or not directly measurable can be determined on the basis of the calculated driving status variables. The calculated and determined variables are transmitted to an actuator device to control and/or regulate the vehicle. The computational model contains a vehicle model, a tire model, and a wheel suspension model and are solved together in the computing device according to the following differential equation system:

[00001]$\left(M_F+\underset{i=1}{\overset{n?3}{.Math.}}{M}_{\mathrm{Ri}}\right)\stackrel{.fwdarw.}{\stackrel{.}{q}}+\left({\stackrel{.fwdarw.}{k}}_F+\underset{i=1}{\overset{n?3}{.Math.}}{\stackrel{.fwdarw.}{k}}_{\mathrm{Ri}}\right)+\left({\stackrel{.fwdarw.}{b}}_g\underset{i=1}{\overset{n?3}{.Math.}}{\stackrel{.fwdarw.}{b}}_i\right)=\stackrel{.fwdarw.}{0}$

The present invention consists in determining at least one dangerous driving indicator (IND) by means of a physical model (MOD) based on the dynamics of the vehicle. According to the invention, the dynamic model (MOD) of the vehicle makes it possible to determine a slip parameter (, SR) of the vehicle, which is used to deduce a representative dangerous driving indicator (IND).

Methods of estimating a weight of a vehicle and using the information are provided. Kinematic data of the vehicle, including at least one of a velocity or an acceleration of the vehicle, can be measured at a time. This data can be processed to estimate a weight of the vehicle. This data can be used to adjust autonomous driving, confirm a weight of freight carried by the vehicle, transmitted to external devices, or used in other ways.

Systems and methods of visualizing predicted driving risk are provided herein. Vehicle sensor data associated with a vehicle operator may be analyzed. Based on the analysis of the vehicle sensor data, one or more vehicle operation risks associated with the vehicle operator may be predicted. Each vehicle operation risk may be associated with a portion of a vehicle associated with the vehicle operator. Additionally, each vehicle operation risk may be assigned a priority level, e.g., based on predicted likelihood of occurrence, predicted danger of the vehicle operator, predicted damage to the vehicle, etc. A display overview of the vehicle may be presented to the vehicle operator. In the display overview of the vehicle portions of the vehicle associated with each of the predicted vehicle operation risks may be highlighted. The portions may be highlighted differently (using different colors, heavier/lighter shading, etc.) based on the priority level of their associated risks.

A system for use at a vehicle to estimate vehicle pitch angle and road grade angle, in real time and generally simultaneously. The system includes a sensor configured to measure vehicle pitch rate, a processor, and a computer-readable medium. The medium includes computer-executable instructions that, when executed by the processor, cause the processor to perform operations comprising estimating, using an observer and the vehicle pitch rate measured by the sensor, an estimated vehicle pitch rate. The operations further comprise estimating, using an observer and the measured vehicle pitch rate, the vehicle pitch angle, and estimating, based on the estimated vehicle pitch rate and the vehicle pitch angle estimated, the road grade angle.

A computer-implemented method can include analyzing sensor data from a vehicle to determine one or more driving behaviors of a driver, determining one or more patterns in the one or more driving behaviors over a predetermined period, and determining probabilities of damaging portions of the vehicle based on the one or more patterns.

The present invention achieves a technique that not only makes it possible to reduce sensor-related cost but also makes it possible to estimate a ground contact load of a vehicle with sufficiently high accuracy. A ground contact load estimation device (100) causes an acquisition section to acquire a physical quantity related to a vehicle, causes a reference inertia load calculation section (111) to calculate a reference inertia load with use of the physical quantity, uses the physical quantity to cause a correction value calculation section (112) to calculate an inertia load correction value, and causes an inertia load estimation section (110) to estimate an inertia load by adding the inertia load correction value to the reference inertia load.