Abstract: Provided is a method for driving behavior modeling based on spatio-temporal information fusion, relating to the field of driving behavior simulations. The method includes: constructing a driving behavior model, where the driving behavior model includes a spatial information encoding network, a temporal information encoding network, a feature fusion network, and a feature decoding network, with the feature fusion network being connected to both the spatial information encoding network and the temporal information encoding network, and the feature decoding network being connected to the feature fusion network; determining a future trajectory sequence of a target main vehicle at future time points based on the trained driving behavior model according to spatial information and temporal information of the target main vehicle, where the target main vehicle is controlled to travel according to the future trajectory sequence at the future time points.

Abstract: The present disclosure provides a driving video recorder for an automotive, which includes: a housing having a side wall, a top wall with an air outlet, and a bottom wall with an air inlet; a first electric fan arranged on the bottom wall above the air inlet and in a vertical middle plane of the housing for directing outside air into the housing; two sets of lenses for image capturing arranged at the side wall and positioned symmetrically on both sides of the vertical middle plane of the housing; and heat generating electrical components provided within the housing. The driving video recorder according to the present disclosure has a symmetrically distributed lens structure ensuring system stability, reliability, and enhanced functionality.

Abstract: This disclosure provides an automotive driving recorder for being installed on an automobile, comprising: a body; a first lens mounted on a front portion of the body, facing in the forward direction of an automobile when installed to record first videos; a second lens mounted on a rear portion of the body, facing in the backward direction of the automobile when installed to record second videos; a first sensor, mounted in the body for determining exposure settings of the first lens; and a second sensor, mounted in the body for determining exposure settings of the second lens independently from the first sensor.