Proactive Emergency Collision Avoidance for Automated Driving in Highway Scenarios

TL;DR

This work tackles the problem of proactive emergency collision avoidance in highway driving under uncertainty. It introduces a Stochastic Model Predictive Control framework that incorporates nonlinear tire dynamics via MMPS approximations to enable real-time, risk-aware planning with hybridized chance constraints. The approach yields safer, more proactive trajectories and demonstrates favorable computational efficiency through MILP reformulation, validated against a state-of-the-art SMPC and high-fidelity IPG CarMaker simulations. The results show improved safety margins and maintainability of attainable trajectories under various hazardous scenarios, with practical implications for high-speed autonomous driving. The paper also outlines avenues for extending obstacle-intent modeling and providing formal guarantees on feasibility and suboptimality bounds.

Abstract

Uncertainty in the behavior of other traffic participants is a crucial factor in collision avoidance for automated driving; here, stochastic metrics could avoid overly conservative decisions. This paper introduces a Stochastic Model Predictive Control (SMPC) planner for emergency collision avoidance in highway scenarios to proactively minimize collision risk while ensuring safety through chance constraints. To guarantee that the emergency trajectory can be attained, we incorporate nonlinear tire dynamics in the prediction model of the ego vehicle. Further, we exploit Max-Min-Plus-Scaling (MMPS) approximations of the nonlinearities to avoid conservatism, enforce proactive collision avoidance, and improve computational efficiency in terms of performance and speed. Consequently, our contributions include integrating a dynamic ego vehicle model into the SMPC planner, introducing the MMPS approximation for real-time implementation in emergency scenarios, and integrating SMPC with hybridized chance constraints and risk minimization. We evaluate our SMPC formulation in terms of proactivity and efficiency in various hazardous scenarios. Moreover, we demonstrate the effectiveness of our proposed approach by comparing it with a state-of-the-art SMPC planner and we validate that the generated trajectories can be attained using a high-fidelity vehicle model in IPG CarMaker.

Figures (11)

• Figure 1: Example of proactive collision avoidance in a highway scenario: if its front vehicle suddenly brakes, the ego vehicle (pink) avoids front and rear-end collision with other road users (green) by safely moving to the left lane.
• Figure 2: Model configuration for the ego vehicle and the obstacles on the road.
• Figure 3: Pacejka tire model and its MMPS approximation
• Figure 4: Plots of example nonlinear terms in the ego vehicle prediction model and their MMPS approximations
• Figure 5: Conceptual illustration of the Gaussian probability function $\mathbb{P}$, of its MMPS approximation and of the MMPS proxy functions. The approximations are valid in the compact domain $\mathcal{D}$.

Theorems & Definitions (7)

• Remark 1
• Remark 2
• Remark 3
• Remark 4
• Remark 5
• Remark 6
• Remark 7