Abstract: Detecting and addressing data spoofing in vehicle signal analysis is provided. A plurality of trust scores are calculated for a plurality of vehicle signals. Each of the trust scores measures a likelihood that a respective one of the plurality of vehicle signals is authentic and not spoofed. Aggregate trust scores are calculated for aggregate signals using the trust scores of the vehicle signals contributing to the aggregate signals, wherein the aggregate signals are created via a transformation performed using one or more of the plurality of the vehicle signals over time. It is determined whether the trust scores and/or the aggregate trust scores meet a predefined threshold. The vehicle signals and/or the aggregate signals are applied to an analysis model to determine metrics based on the trust scores and/or aggregate trust scores meeting a predefined minimum trust threshold.

Abstract: Validating vehicle signal integrity is performed. Combined signals including sensor signals and reference signals are received from a telematics control unit (TCU) of a vehicle. The reference signals are extracted from the combined signals based on a predefined timing pattern known to the server. A reference output is generated by processing predefined reference signals using an analysis model. A test output is generated by processing the extracted reference signals using the analysis model. An error signal is calculated as a difference between the reference output and the test output. The error signal is compared to a predefined threshold to determine whether a spoofing condition exists. A data select command is transmitted to the vehicle responsive to determining the spoofing condition to mitigate unreliable signals.

Abstract: A vehicle system comprising computing devices configured to generate an insurance risk assessment using a Sparse Gaussian Process Regression (SGPR) model. The SGPR model processes aggregated vehicle signals to provide memory-efficient and computationally optimized on-vehicle risk estimation. The system detects high-uncertainty events in model predictions based on variance thresholds and either updates the SGPR model locally or selectively transmits sparse data representations to an external usage-based insurance (UBI) server, reducing data transfer costs and preserving privacy.

Abstract: A vehicle system includes one or more computing devices configured to generate a drive characteristic probability distribution (CPD) using one or more aggregated vehicle signals, where the drive CPD associates one or more drive scenarios with one or more driver behaviors. The one or more computing devices is further configured to transmit, to a usage-based insurance (UBI) server, a drive CPD information including data indicative of a subsequent drive CPD in response to the subsequent drive CPD varying from a nominal CPD by a CPD threshold to cause an update of a UBI rate for a UBI policy associated with the vehicle.

Abstract: Disclosed examples include measuring, via a sensor, a brake torque generated by a braking system; determining an energy output of the braking system based on a mechanical power output of the braking system, the mechanical power output based on the brake torque; determining an efficiency based on the energy output and an energy input, the energy input corresponding to an electrical power input of a motor of the braking system; detecting a condition of the braking system based on the efficiency; and outputting an indication representative of the condition.

Abstract: Disclosed examples include measuring, via a sensor, a brake torque generated by a brake of a braking system; providing a first current to a motor to actuate the brake, the first current to cause the measured brake torque to satisfy a target brake torque; determining a residual value based on the first current and a second current of the motor associated with a first gap between a friction material and a braking surface of the brake; detecting a condition of the braking system based on the residual value and a difference between the second current and a third current of the motor, the third current associated with a second gap between the friction material and the braking surface; and outputting an indication representative of the detected condition.

Abstract: Using universal signals for determining vehicle metrics is provided. Based on vehicle signals received from one or more vehicles, a latent space model including an encoder and a decoder is trained, the encoder generating universal signals as a latent representation of the vehicle signals, the decoder generating reconstructed vehicle signals from the universal signals. The encoder is sent to the one or more vehicles. Universal signals are received from the one or more vehicles, the universal signals being generated through use of the encoder on the vehicle signals. The universal signals are applied to an analysis model to determine metrics with respect to the operation of the one or more vehicles from the latent representation.

Abstract: Assessing driver risk for usage-based insurance (UBI) is provided. Risk metrics are sent, to a plurality of vehicles from a cloud server, defining indications of driving events that may occur on the vehicles that are indicative of an effect on UBI rates for the vehicles. The cloud server receives, from the vehicles, aggregated data points collected by the vehicles use in determining UBI rate and high-fidelity data points collected by the vehicles responsive to occurrence of the driving events. The high-fidelity data points are analyzed using a vehicle data service to determine updated risk metrics using a multi-arm bandit approach with delayed feedback based on a risk model and claim data indicative of actual claims made with respect to the plurality of vehicles. The updated risk metrics are provided to the plurality of vehicles to aid in detection of the driving events that affect the UBI rates.

Abstract: Methods and apparatus to estimate brake pad wear are disclosed. An example apparatus includes at least one processor circuit to obtain temperature data and power data associated with a brake pad of a vehicle, execute a neural network based on the temperature data and the power data, the neural network trained based on a loss value corresponding to a difference between (a) a first rate of change of an output of the neural network when the neural network is executed based on training data, the first rate of change evaluated at a first temperature and a first power, and (b) a second rate of change proportional to a ratio between the first temperature and the first power, determine, based on a result of the execution of the neural network, a brake wear metric corresponding to the brake pad, and cause presentation of the brake pad metric via a user interface.

Abstract: Automatic generation of optimized aggregation metrics for usage-based insurance (UBI) includes performing a high-dimensional Bayesian optimization on a data archive, the data archive including a plurality of signals from vehicles and corresponding UBI effects, wherein the high-dimensional Bayesian optimization includes performing testing on weighted groups of the plurality of signals using one or more aggregation functions; and transmitting the one or more aggregation functions to a vehicle to cause the vehicle to provide aggregated signals for input to a UBI model to predict a UBI rate for the vehicle.