Beijing Didi Infinity Technology and Development Co., Ltd.

Jieping Ye

Zhiwei Qin

Zheng Wang

Xiaocheng Tang

Shujuan Sun

Qingyang Li

Guojun Wu

Yan Jiao

Yang Yu

Hai Yang

Hongtu Zhu

Jintao Ke

Wenjie Shang

Yiping Meng

Yafeng YiN

Zhaodong Wang

Zhengtian Xu

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for constructing a virtual environment for a ride-hailing platform are disclosed. An exemplary method comprises: obtaining a plurality of historical interaction trajectories each comprising one or more interaction records between a driver and a ride-hailing platform, each interaction record comprising a program recommendation of the ride-hailing platform to the driver and a reaction of the driver in response to the program recommendation; training a simulator based on the plurality of historical interaction trajectories; and integrating a reward function with the simulator to construct the virtual environment, wherein the plurality of first program recommendations and the plurality of reactions form a plurality of simulated interactions, and a data distribution of the plurality of simulated interactions approximates a data distribution of a plurality of interaction records in the plurality of historical interaction trajectories.

Method and system for constructing virtual environment for ride-hailing platforms

Deep reinforcement learning may be used for vehicle repositioning on mobility-on-demand platforms. Information may be obtained. The information may include a current location of a vehicle on a ride-sharing platform. A set of paths originated from the current location of the vehicle may be obtained. Each of the set of paths may have a length less than a preset maximum path length. A set of expected cumulative rewards along the set of paths may be obtained based on a trained deep value-network. A best path from the set of paths may be selected based on a heuristic tree search of the set of expected cumulative rewards. A next step along the best path may be recommended as a reposition action for the vehicle.

Vehicle repositioning on mobility-on-demand platforms

A system and method of determining a policy to prevent fading drivers is described. The system and method creates virtual trajectories of incentives such as coupons offered to drivers in a transportation hailing system and corresponding states of drivers in response to the incentives. A joint policy simulator is created from an incentive policy, a confounding incentive policy, and an incentive object policy to generate the simulated actions of drivers in response to different incentives. The rewards of the simulated actions of the drivers is determined by a discriminator. The incentive policy for preventing fading drivers is optimized by reinforcement learning based on the virtual trajectories generated by the joint policy simulator and discriminator.

Reinforcement learning method for driver incentives: generative adversarial network for driver-system interactions

Systems and methods are provided for ride order dispatching. Such method may comprise obtaining information on a location of a vehicle and a time to input into a trained neural network algorithm; and based on a policy generated from the trained neural network algorithm, obtaining action information for the vehicle, the action information comprising: staying at a current position of the vehicle, re-positioning the vehicle, or accepting a ride order.

System and method for ride order dispatching

A method comprises: obtaining historical vehicle service data in an area for a time period including historical locations of passenger-seeking vehicles with respect to time, historical locations of passenger orders with respect to time, and historical trip fares with respect to pick-up locations and time; discretizing the area into a plurality of zones and discretizing the time period into a plurality of time segments; aggregating the historical vehicle service data according the zones and time segments; obtaining an expected reward for a passenger-seeking vehicle to move from zone A to each neighboring zone of the zone A based on the aggregated historical vehicle service data; and obtaining a probability of a passenger-seeking vehicle moving from zone A to a neighboring zone B based on the expected reward for the passenger-seeking vehicle to move from zone A to the each neighboring zone of the zone A.

System and method for determining passenger-seeking ride-sourcing vehicle navigation

The present disclosure relates to systems and methods for determining an estimated time of arrival (ETA) for a route, based on a model of ETA. The systems may perform the methods to obtain a first electrical signal associated with at least one route having at least one road section; generate and save first structured data of at least one global feature vector and at least one historical duration associated with the at least one route based on the first electrical signal; generate second structured data of a model of ETA by training the model based on the at least one global feature vector and the at least one historical duration; and save the second structured data of the model of ETA in the at least one non-transitory computer-readable storage medium.

Systems and methods for recommending an estimated time of arrival

Growing community of inventors

Tianjin, China

Jieping Ye