Other

Beijing Didi Infinity Technology and Development Co., Ltd.

Didi Research America, LLC

Xuewen Chen

Zhiwei Qin

Ishan Jindal

Systems and methods are provided for estimating travel time and distance. Such method may comprise obtaining a vehicle trip dataset comprising an origin, a destination, a time-of-day, a trip time, and a trip distance associated with each of a plurality of trips, and training a neural network model with the vehicle trip dataset to obtain a trained model. The neural network model may comprise a first module and a second module, the first module may comprise a first number of neuron layers, the first module may be configured to obtain the origin and the destination as first inputs to estimate a travel distance, the second module may comprise a second number of neuron layers, and the second module may be configured to obtain the information of a last layer of the first module and the time-of-day as second inputs to estimate a travel time.

System and method for estimating travel time and distance

A method may comprise recursively performing: (1) providing one or more states of a simulation environment to a simulated vehicle, and the states comprise a first current time and a first current location of the simulated vehicle; (2) obtaining an action by the simulated vehicle when the simulated vehicle has reached a milestone, wherein: the action is selected from: waiting at the first current location of the simulated vehicle, picking up a passenger group A at an origin of passenger group A's transportation, and dropping off a passenger group B at a destination of passenger group B's transportation, and the milestone is an origin or a destination of any passenger group's transportation; (3) determining a reward to the simulated vehicle for the action; and (4) updating the one or more states based on the action to obtain one or more updated states for providing to the simulated vehicle.

Method and device for providing vehicle navigation simulation environment

The present disclosure provides a bracket and a scooter storage box having same. The bracket is used for storing an electric scooter. The bracket includes: a chassis, the chassis being provided with a recess portion for receiving a wheel of the electric scooter, the chassis being further provided with a carrying surface urging against the lower surface of a scooter body of the electric scooter; and a charging portion, electrically connected to the electric scooter to charge the electric scooter. The electric scooter may be limited and carried by the cooperation of the recess portion on the chassis of the bracket and the carrying surface, so that the electric scooter may be steadily stored. Furthermore, the electric scooter may also be charged by the charging potion to meet the charging needs of the electric scooter.

Bracket and scooter storage box with bracket

The disclosure provides an electric scooter storage method based on a scooter storage box. The scooter storage box is configured to store at least one electric scooter, The scooter storage box includes a box body, a bracket arranged in the box body and used for storing the electric scooter, an access port, and an interaction device. The method further includes: if the interaction device detects a scooter taking-out instruction, verifying identity information of a scooter taking-out user; if the verification is passed, conveying the electric scooter to the access port, and opening the access port; and if it is detected that the electric scooter is taken out from the bracket, recording renting information of the electric scooter, the renting information at least including: user information of a scooter taking-out user who takes out the electric scooter, and identification information and renting time of the electric scooter. The disclosure solves the problem in the conventional art that an electric scooter is easily damaged during the open storage in public places.

Electric scooter storage method based on scooter storage box

A method for providing vehicle navigation simulation environment may comprise recursively performing steps (1)-(4) for a time period: (1) providing one or more states of a simulation environment to a simulated agent, wherein: the simulated agent comprises a simulated vehicle, and the states comprise a first current time and a first current location of the simulated vehicle; (2) obtaining an action by the simulated vehicle when the simulated vehicle has no passenger, wherein the action is selected from: waiting at the first current location of the simulated vehicle, and transporting M passenger groups; (3) determining a reward to the simulated vehicle for the action; and (4) updating the one or more states based on the action to obtain one or more updated states for providing to the simulated vehicle, wherein: the updated states comprise a second current time and a second current location of the simulated vehicle.

Growing community of inventors

Beijing, China

Xuewen Chen