System and methods are provided for predicting, reacting to, and avoiding loss of traction events, such as hydroplaning for autonomous vehicles. For example, the method predicts a risk of an area being subject to hydroplaning using real-time data and/or historical data. The method may store possible hydroplaning events in a geographic map along with a risk assessment. The method provides lane level hydroplaning risk predictions and avoidance mechanisms.

A system for controlling vehicle power using big data is provided. The system includes a big data server that receives vehicle driving related data, processes and analyzes the received data to generate a driving power pattern of the vehicle, and stores the driving power pattern. A vehicle controller determines whether to limit charging/discharging power of a battery based on continuous charging/discharging time or an accumulation amount of continuous charging/discharging power of the battery and calculates battery charging/discharging power to be limited based on the driving power pattern received from the big data server when the charging/discharging power of the battery is limited.

A method for determining a transportation mode acquires magnetometer and speed data from a mobile device, correlates the magnetometer to the speed data in groupings, and performs spectral analysis on the groups of magnetometer data. Energy calculated for each of a set of frequency components obtained from the spectral analysis is compared to a baseline value to generate a difference, and a transportation mode type is assigned to the vehicle based on the difference.

A vehicle power control system using big data, may include a big-data server configured to receive driving-related data of a vehicle, generated by the vehicle, to generate a factor related to an acceleration pattern of the vehicle by processing the received driving-related data, and to store the generated factor, and a controller installed in the vehicle and configured to, when the vehicle is requested to be accelerated or propelled, change output power of a battery with reference to pre-stored available power of the battery and the factor stored in the big-data server.

Systems and methods are disclosed for identifying time-latency and subsystem control actuation dynamic delay due to second order dynamics that are neglected in control systems of the prior art. Embodiments identify time-latency and subsystem control actuation delays by developing a discrete-time dynamic model having parameters and estimating the parameters using a least-squares method over selected crowd-driving data. After estimating the model parameters, the model can be used to identify dynamic actuation delay metrics such as time-latency, rise time, settling time, overshoot, bandwidth, and resonant peak of the control subsystem. Control subsystems can include steering, braking, and throttling.

Systems and methods relate to, inter alia, calculating a collision risk index for an area based upon historical traffic data. The systems and methods may further generate a notification to automatically engage or disengage an autonomous, or semi-autonomous, vehicle control feature in a vehicle based upon the collision risk index for the area. The systems and methods may further transmit the notification to a device of the vehicle to facilitate automatically engaging or disengaging an autonomous, or semi-autonomous, vehicle control feature in the vehicle as the vehicle approaches the area. As a result, vehicle collisions may be reduced, and vehicle safety enhanced.

A transportation mobility system includes a data storage configured to maintain vehicle data indicating fuel consumption and count of passengers for vehicles of a transportation system, and user data describing movements of the passengers within the transportation system. The system also includes an emissions monitoring portal, programmed to provide, for vehicles of a fleet, estimates of pollutant emissions for the fleet and a percent share of miles completed by zero-emissions transportation for the fleet.

System and methods are provided for predicting, reacting to, and avoiding loss of traction events, such as hydroplaning for autonomous vehicles. For example, the method predicts a risk of an area being subject to hydroplaning using real-time data and/or historical data. The method may store possible hydroplaning events in a geographic map along with a risk assessment. The method provides lane level hydroplaning risk predictions and avoidance mechanisms.

Disclosed is a vehicle control system that includes a sensor that acquires data related to driving of a vehicle from the vehicle and an external environment, and a processor that processes the data related to the driving of the vehicle to determine trajectories, calculates a variance of a movement value of each trajectory measured by the sensor and determines a noise level of a road surface of the trajectory, calculates bidirectional trajectories information of a current point of a three-dimensional map, identifies whether a road width of the current point is greater than or equal to a first threshold value, identifies whether there is no overlapping section between the bidirectional trajectories in a vehicle width direction, updates the bidirectional trajectories information and the noise level, applies a weight based on the noise level to each trajectory, and applies a final valid trajectory to the three-dimensional map.

A fleet management server is configured to receive, via a wireless transceiver, driver and vehicle information from a plurality of vehicles relating to a plurality of drivers. The server computes, based on the received driver and vehicle information, occurrence rates for predetermined vehicle events and predetermined vehicle error codes that are associated with possible vehicle tampering, and then compares, based on the received driver and vehicle information, an occurrence rate for the predetermined vehicle events and predetermined vehicle error codes of a first driver to occurrence rates for the predetermined vehicle events and predetermined vehicle error codes of one or more of the other plurality of drivers. The server is further configured to determine, based on a result of said comparing, a tampering indicator for the first driver, and to output, to a user of the fleet management server, a confidence level that the first driver has tampered with at least one information component of at least one vehicle of the plurality of vehicles based at least in part on the tampering indicator.