Kernelized convolutional transformer network based driver behavior estimation for conflict resolution at unsignalized roundabout

The modeling of driver behavior plays an essential role in developing Advanced Driver Assistance Systems (ADAS) to support the driver in various complex driving scenarios. The behavior estimation of surrounding vehicles is crucial for an autonomous vehicle to safely navigate through an unsignalized intersection. This work proposes a novel kernelized convolutional transformer network (KCTN) with multi-head attention (MHA) mechanism to estimate driver behavior at a challenging unsignalized three-way roundabout. More emphasis has been placed on creating convolution in non-linear space by introducing a kervolution operation into the proposed network. It generalizes convolution, improves model capacity, and captures higher-order feature interactions by using Gaussian kernel function. The proposed model is validated using the real-world ACFR dataset, where it outperforms current state-of-the-art in terms of behavior prediction accuracy and provides a significant lead time before potential conflict situations. •Kervolution is combined with transformer to predict driving behavior at roundabouts.•The kernel trick generalizes convolution in non-linear space to increase accuracy.•Transformer network’s utility is illustrated to deal sequence to point problems.•The proposed model achieves higher accuracy compared to RNN-based sequential models.•The framework enables for the modeling of dynamic and complex intentions.