Generic Prediction Architecture Considering both Rational and Irrational Driving Behaviors

Abstract

Accurately predicting future behaviors of surrounding vehicles is an essential capability for autonomous vehicles in order to plan safe and feasible trajectories. The behaviors of others, however, are full of uncertainties. Both rational and irrational behaviors exist, and the autonomous vehicles need to be aware of this in their prediction module. The prediction module is also expected to generate reasonable results in the presence of unseen and corner scenarios. Two types of prediction models are typically used to solve the prediction problem: learning-based model and planning-based model. Learning-based model utilizes real driving data to model the human behaviors. Depending on the structure of the data, learning-based models can predict both rational and irrational behaviors. But the balance between them cannot be customized, which creates challenges in generalizing the prediction results. Planning-based model, on the other hand, usually assumes human as a rational agent, i.e., it anticipates only rational behavior of human drivers. In this paper, a generic prediction architecture is proposed to address various rationalities in human behavior. We leverage the advantages from both learningbased and planning-based prediction models. The proposed approach is able to predict continuous trajectories that wellreflect possible future situations of other drivers. Moreover, the prediction performance remains stable under various unseen driving scenarios. A case study under a real-world roundabout scenario is provided to demonstrate the performance and capability of the proposed prediction architecture.

On Social Interactions of Merging Behaviors at Highway On-Ramps in Congested Traffic

“…Based on social gracefulness, Ren, et al [34] proposed a model predictive control method to tackle the two-player game, allowing autonomous vehicles to learn more social behaviors. By considering both rational and irrational social behaviors, Hu, et al [35] presented a prediction framework to estimate continuous trajectories of surrounding vehicles. By defining the optimal control problem and formulating the appropriate algorithm, Speidel, et al [36] proposed a planning framework to avoid too aggressive.…”

A Review on Intention-aware and Interaction-aware Trajectory Prediction for Autonomous Vehicles

“…A common approach for trajectory prediction using CVAE found in the analysis of primary studies was the trajectory prediction conditioned on the maneuvers' intention [59], [61], [143]. Hu, Zhan and Tomizuka [61] designed a hierarchical probabilistic framework with two modules, the upper and lower modules.…”

A Review on Intention-aware and Interaction-aware Trajectory Prediction for Autonomous Vehicles

“…Finally, the future trajectories of the target vehicle are also conditionally dependent on the future plans of the ego vehicle. Similarly, Hu, Sun and Tomizuka [143] proposed a planning-based framework using Continuous IRL, in which the results are also conditionally dependent on the future trajectory of the ego vehicle.…”