Situation-Aware Interactive MPC Switching for Autonomous Driving
For autonomous driving systems, this work provides a practical strategy to achieve high performance in interactive traffic scenarios without incurring prohibitive computational overhead.
The paper addresses the challenge of balancing performance and computational cost in autonomous driving by developing a neural network-based classifier that switches between MPC formulations of varying fidelity based on situational demands. The approach improves overall performance while significantly reducing computational load by invoking advanced interactive MPC only in rare critical situations.
Autonomous driving in interactive traffic scenarios remains challenging because of the mutual influence among vehicles and the inherent uncertainty of surrounding agents. Several model predictive control (MPC) formulations have been proposed to address this challenge, each adopting a different model of inter-agent interaction. While higher-fidelity interaction models enable more intelligent behavior, they incur substantially greater computational cost. Since strong interactions arise only occasionally in real traffic, a practical strategy for balancing performance and computational overhead is to invoke an appropriate controller based on situational demands. To this end, we first conduct a comparative study to assess and hierarchize the interactive capabilities of different MPC formulations. Building on this hierarchy, we then develop a neural network-based classifier for situation-aware switching among these controllers. We demonstrate that, by invoking the most advanced interactive MPC only in rare but critical situations and relying on a basic MPC in the majority of situations, situation-aware switching substantially improves overall performance while significantly reducing computational load.