A method of monitoring quality of a road segment from driver data is provided. The method includes receiving, by a server over a network, the driver data for a road segment from one or more sensing units in one or more vehicles. The method also includes calculating, in one or more computing devices, one or more quantitative pavement surface characteristics of the road segment from the driver data using a probabilistic inverse analysis framework. The method also includes identifying, in the one or more computing devices, one or more quantitative vehicle properties of the one or more vehicles from the driver data using the probabilistic inverse analysis framework. The method then includes estimating, in the one or more computing devices, one or more road quality characteristics of the road segment based on at least one of the quantitative pavement surface characteristics of the road segment and the quantitative vehicle properties of the one or more vehicles.

A method for detecting safety of a driving behavior, an apparatus, a device and a storage medium are provided. The method includes acquiring current driving data of a vehicle during a driving process of the vehicle; determining current driving behavior feature data of the vehicle according to the current driving data of the vehicle; inputting the current driving behavior feature data of the vehicle into a real-time safety detection model and calculating a security score corresponding to current driving behavior of the vehicle; and determining whether the current driving behavior of the vehicle is safe according to the security score corresponding to the current driving behavior of the vehicle. The method can assist an optimization of a vehicle driving system, reduce a safety risk of vehicle driving, and improve a riding experience of the user.

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.

A computing system can be configured to generate, for an autonomous vehicle, a route through a transportation network comprising a plurality of segments. The method can include receiving sets of agent attention data from additional autonomous vehicles that are respectively currently located at one or more other segments of the transportation network. The method can include inputting the sets of agent attention data into a value iteration graph neural network that comprises a plurality of nodes that respectively correspond to the plurality of segments of the transportation network. The method can include receiving node values respectively for the segments as an output of the value iteration graph neural network. The method can include selecting a next segment to include in the route for the autonomous vehicle based at least in part on the node values.

A non-transitory storage medium for use in an information processing device in a vehicle control system. The storage medium stores: pieces of positional information; pieces of cumulative relative frequency distribution information associated with individual vehicle traveling directions, the pieces of cumulative relative frequency distribution information being related to data on traveling loads associated with the individual vehicle traveling directions on a plurality of vehicles having traveled through points indicated by the pieces of positional information, or data on traveling load amounts depending on a traveling time or a traveling distance from the points; and instructions that are executable by processors to perform functions comprising calculating a predicted value of the traveling load amount depending on the traveling time or the traveling distance from an arbitrary point based on the cumulative relative frequency distribution information associated with individual vehicle traveling directions at the arbitrary point.

A system comprises fuel consumption prediction circuitry and user interface circuitry. The fuel consumption prediction circuitry is operable to receive trip constraints for a trip to be made by a vehicle, and vehicle information for the vehicle. The fuel consumption prediction circuitry is operable to generate, based on the trip constraints and the vehicle information, a first trip option having a first predicted travel time and a first predicted fuel consumption, and a second trip option having a second predicted travel time and a second predicted fuel consumption. The fuel consumption prediction circuitry is operable to communicate the first trip option and the second trip option to user interface circuitry. The user interface circuitry is operable to receive the first trip option and the second trip option and present the options to a user.

A system and method to a vehicle control assist system of a vehicle to an operator of the vehicle includes: retrieving stored driver assistance settings of an identified operator for the vehicle control assist system of the vehicle; collecting operating behavior data about the identified operator during vehicle operation; and selecting a driver assistance setting of a vehicle control assist system based on inputting the operating behavior data of the identified operator to a machine learning program that has been trained with operating behavior data of a plurality of other operators collected during operation of a plurality of respective vehicles, wherein metadata about the other operators have values in common with the metadata of the identified operator.

Methods for management of a powertrain system in a vehicle. The methods receive data or signals from multiple sensors associated with the vehicle. Optimum thresholds for classifications of the sensor data can be changed based injecting signals into the powertrain system and receiving responsive signals. Expected priorities for the sensor signals can be altered based upon attributes of the signals and confirming actual priorities for the signals. Look-up tables for engine management can be modified based upon injecting signals into the powertrain system and measuring a utility of the responsive signals. The methods can thus dynamically alter and modify data for powertrain management, such as look-up tables, during vehicle operation under a wide range of conditions.

Through-the-road (TTR) hybrid designs using control strategies such as an equivalent consumption minimization strategy (ECMS) or adaptive ECMS are implemented at the supplemental torque delivering electrically-powered drive axle (or axles) in a manner that follows operational parameters or computationally estimates states of the primary drivetrain and/or fuel-fed engine, but does not itself participate in control of the fuel-fed engine or primary drivetrain. Crowdsourced distributions of adaptations and/or selections of BSFC type data allow ECMS implementations (or other similar control strategies) employ efficiency curves for a particular paired-with fuel-fed engine and/or operating conditions and to improve overall efficiencies of the TTR hybrid configuration. In some cases, signatures are used to identify appropriate BSFC type data for crowdsourced dissemination.

A system determines a baseline of at least one route segment based on measurement data received from a plurality of vehicles. The system receives first measurement data of a first vehicle that has traveled along the at least one route segment, and compares the first measurement data to the baseline. Based on the comparing, the system determines whether operation of the first vehicle is within an acceptable tolerance of a performance criterion, and determines whether the at least one route segment is an undesirable route segment according to a route criterion.