Vehicle following system and method for simulating driving style based on deep inverse reinforcement learning

Abstract

The invention belongs to the technical field of intelligent driving, and discloses a vehicle following system and method for simulating a driving style based on deep inverse reinforcement learning. The vehicle following system comprises a millimeter-wave radar which collects the information of the distance between a vehicle and a front vehicle, the lateral distance between the vehicle and the front vehicle, the relative speed and the azimuth angle, a vehicle speed collection device which collects the speed of the vehicle, and a vehicle-mounted industrial personal computer. A vehicle followingdata processor in the vehicle-mounted industrial personal computer processes information acquired by the millimeter wave radar and the vehicle speed collection device, extracts a vehicle following data fragment required by vehicle following model training, and performs vehicle following model training on the vehicle following data fragment to obtain a vehicle following strategy model; the vehiclefollowing system is simple in structure, a reward function is learned from the historical vehicle following data of a driver through the deep inverse reinforcement learning method, the vehicle following strategy of the driver is solved through the reward function and the reinforcement learning method, the obtained vehicle following model can simulate the driving styles of different drivers and understand the preference of the driver in the vehicle following process, and a personified vehicle following behavior is generated.

Description

technical field [0001] The invention relates to the technical field of intelligent driving, in particular to a car-following system and method for simulating driving styles based on deep inverse reinforcement learning. Background technique [0002] Car following refers to the driver driving the vehicle to follow the vehicle in front, which is the most common situation in daily driving. In urban traffic conditions, the proportion of the time that the driver follows the car is generally greater than 50%. In order to realize traffic simulation, driving assistance system testing, and automatic driving, a large number of studies have built car-following models for drivers' car-following behavior. [0003] The role of the following model is to simulate the driver's following behavior and characteristics, so that the vehicle can follow the vehicle in front according to the driver's driving style. At present, the existing car-following models include two types: one is the traditio...

AI Technical Summary

Problems solved by technology

The behavior cloning method has been proved to be able to achieve more accurate behavior simulation under the condition of sufficient amount of data. However, when the amount of data is insufficient, behavior cloning will lead to compound error problems, that is, when the amount of data is insufficient, the model fits poorly, and its There will be some errors in the prediction results, and the errors will accumulate during the simulation process, eventually causing the model to face some states that are not included in the training data. In this case, the model will output worse prediction results

Images