Disclosed are systems and methods relating to providing intersection metrics based on road network data and telematic data.

The disclosure is directed to, among other things, distributed ledger systems for modular vehicles. The disclosure may involve receiving, at a first ledger associated with a first node, information regarding an interaction between the first node and a second node. The same transaction information may also be received at a second ledger associated with the second node, as well as ledgers associated with any other number of nodes. The first node, second node, and any other number of nodes may be modular vehicle components. Additionally, the first ledger, second ledger, and any other number of ledgers include a set of the same information. The first node, second node, and third node may be nodes on a distributed ledger network.

An turn detection system is configured to determine headings or a course of a vehicle over a period of time and evaluate whether the vehicle has registered a turn based on these headings/course. In some arrangements, upon detecting a turn, sensor data may be collected to determine one or more characteristics or attributes of the turn. Such data may indicate a loss event associated with the turn and be used to calculate a probability or risk of loss given the various characteristics of the turn. These probabilities may further be applied to determine various costs and premiums.

An automatic parking system instructs a plurality of autonomous driving vehicles in a parking lot such that each autonomous driving vehicle parks in a target parking space within the parking lot, and includes an instruction change target vehicle specifying unit configured to, in a case where the autonomous driving vehicle becomes a failed vehicle due to abnormality or communication interruption during automatic driving according to instruction, specify an instruction change target vehicle from normal autonomous driving vehicles based on parking lot map information, a location of the failed vehicle, and a location of the normal autonomous driving vehicles, and a vehicle instruction unit configured to, in a case where the instruction change target vehicle is specified, issue a route change instruction, an evacuation instruction, or a stop instruction to the instruction change target vehicle, such that the instruction change target vehicle gets away from the failed vehicle.

A database of high risk locations is formed and high risk causal factors for the high risk locations determined. Driver behavior is monitored at the sites in the database using data collection devices such as electronic logging devices or mobile phones to see if the drivers exhibit the same specific behaviors that are considered contributing factors to specific accident types at risk of occurrence at those sites. Warnings are provided to drivers approaching the specific sites to prompt behavioral changes which may further be monitored by the data collection devices.

The present disclosure describes a system for dynamically determining an accurate location of a light electric vehicle. For example, if a light electric vehicle is within a predetermined distance of a location for which an accurate location determination is needed or required, a light electric vehicle management system may update the determined location of the light electric vehicle with a location correction factor that is based, at least in part, on a reference location provided by a stationary reference point.

A vehicle conveyance control apparatus for controlling a plurality of conveyance devices, includes a processor and a memory coupled to the processor. Each of the plurality of conveyance devices is configured to lift each tire of a vehicle to convey the vehicle from a predetermined area of a parking lot to a parking space. The processor is configured to perform: acquiring vehicle information including tire position information of each tire of the vehicle detected in the predetermined area; selecting conveyance devices to convey the vehicle from among the plurality of conveyance devices different in conveyance capacity for lifting each tire of the vehicle to convey the vehicle based on the tire position information of the vehicle acquired in the acquiring; and instructing the conveyance devices selected in the selecting to convey the vehicle from the predetermined area to the parking space.

In one aspect, a system for automatically assigning vehicle identifiers for autonomous vehicles can include a registry server computing system configured to perform operations. The operations can include receiving, at the registry server computing system and from a vehicle computing system onboard an autonomous vehicle, data describing the autonomous vehicle and generating, at the registry server computing system, a vehicle identifier for the autonomous vehicle based on the data describing the autonomous vehicle. The vehicle identifier can be different than and distinct from the data describing the autonomous vehicle. The operations can include associating, at the registry server computing system, the data describing the autonomous vehicle with the vehicle identifier for the autonomous vehicle in a vehicle registry. The vehicle registry can include respective vehicle identifiers associated with a plurality of autonomous vehicles.

Systems and methods by a telematics server are provided. The method includes receiving, over a network, training data including model input data and a known output label corresponding to the model input data from a first device, training a centralized machine-learning model using the training data, determining, by the centralized machine-learning model, an output label prediction certainty based on the model input data, determining an increase in the output label prediction certainty over a prior predicted output label certainty of the centralized machine-learning model, and sending, over the network, a machine-learning model update to a second device in response to determining that the increase in the output label prediction certainty is greater than an output label prediction increase threshold.

A traffic planning method for controlling a plurality of vehicles, wherein each vehicle occupies one node in a shared set of planning nodes and is movable to other nodes along predefined edges between pairs of the nodes in accordance with a finite set of motion commands. In the method, initial node occupancies of the vehicles are obtained, and a sequence of motion commands are determined by optimizing a state-action value function which depends on node occupancies s and the motion commands a to be given. The state-action value function includes a command-dependent term, which is updated in each iteration based on a reward function, and a command-independent term, which penalizes node occupancies with too small inter-vehicle gaps and is exempted from said updating.