The Hybrid Extended Bicycle: A Simple Model for High Dynamic Vehicle Trajectory Planning

TL;DR

This work tackles safe trajectory planning under high-dynamic maneuvers by introducing the Hybrid Extended Bicycle Model (HEBM), which couples an Extended Bicycle Model with an LSTM-based slip-angle predictor to accurately describe vehicle state near handling limits. An MPPI-based planner leverages the HEBM dynamics to generate feasible trajectories, while low-level controllers execute the planned velocity and steering commands. The approach is validated against a kinematic bicycle baseline through oval and lane-change tests, demonstrating higher speeds and tighter path tracking, with a_y^{max} reaching up to 0.76 g and improved lateral accuracy. The results indicate the method’s potential for real-time, high-dynamic autonomous driving, with future work focusing on real-vehicle experiments and assessing limitations in more diverse scenarios.

Abstract

While highly automated driving relies most of the time on a smooth driving assumption, the possibility of a vehicle performing harsh maneuvers with high dynamic driving to face unexpected events is very likely. The modeling of the behavior of the vehicle in these events is crucial to proper planning and controlling; the used model should present accurate and computationally efficient properties to ensure consistency with the dynamics of the vehicle and to be employed in real-time systems. In this article, we propose an LSTM-based hybrid extended bicycle model able to present an accurate description of the state of the vehicle for both normal and aggressive situations. The introduced model is used in a Model Predictive Path Integral (MPPI) plan and control framework for performing trajectories in high-dynamic scenarios. The proposed model and framework prove their ability to plan feasible trajectories ensuring an accurate vehicle behavior even at the limits of handling.

Figures (9)

• Figure 1: Comparison between the vehicle behavior using the proposed hybrid extended bicycle planner and a kinematic bicycle planner to effect a harsh lane change maneuver ($V_{\text{ref}}=25m\per s$). The proposed method performs a more accurate maneuver with lateral accelerations reaching $a_y^\text{max} = 0.75\text{g}$.
• Figure 2: The four-wheel vehicle model.
• Figure 3: The kinematic bicycle model.
• Figure 4: The extended bicycle model.
• Figure 5: Wheel slip predictor architecture.