Discrete-choice models are a powerful framework for analyzing decision-making behavior to provide valuable insights for policymakers and businesses. Multinomial logit models (MNLs) with linear utility functions have been used in practice because they are ease to use and interpretable. Recently, MNLs with neural networks (e.g., ASU-DNN) have been developed, and they have achieved higher prediction accuracy in behavior choice than classical MNLs. However, these models lack interpretability owing to complex structures. We developed utility functions with a novel neural-network architecture based on generalized additive models, named generalized additive utility network ( GAUNet), for discrete-choice models. We evaluated the performance of the MNL with GAUNet using the trip survey data collected in Tokyo. Our models were comparable to ASU-DNN in accuracy and exhibited improved interpretability compared to previous models.

Cooperation among different vehicles is a promising concept for route planning of Mobility as a Service (MaaS). For instance, vehicle platooning on highways decreases fuel consumption because it reduces the air resistance and several trucks cooperate with each other when planning. Traditional platooning, however, cannot model cooperation among different types of vehicles because it assumes the homogeneity of vehicle types. We study a model that permits heterogeneous cooperation and discuss a route optimization problem under assumption that the heterogeneous cooperation benefits the objective function. We experimentally evaluate the formulation through using synthetic and real graphs based on a modern integer programming solver with various parameter settings, which are not tried in previous studies. We also compare the results by the solves with simple heuristic method developed in this paper and discuss the results to reveal the properties of the optimization problem with heterogeneous vehicle types.

Freeway merging in congested traffic is a significant challenge toward fully automated driving. Merging vehicles need to decide not only how to merge into a spot, but also where to merge. We present a method for the freeway merging based on multi-policy decision making with a reinforcement learning method called {\em passive actor-critic} (pAC), which learns with less knowledge of the system and without active exploration. The method selects a merging spot candidate by using the state value learned with pAC. We evaluate our method using real traffic data. Our experiments show that pAC achieves 92\% success rate to merge into a freeway, which is comparable to human decision making.