Courteous MPC for Autonomous Driving with CBF-Inspired Risk Assessment
🤖 AI Summary
To address the challenge of simultaneously ensuring safety and yielding behavior for autonomous vehicles (AVs) in mixed human–autonomous driving environments, this paper proposes a synergistic decision-making framework integrating noise-robust risk assessment with model predictive control (MPC). We introduce a Control Barrier Function (CBF)-inspired dynamic risk map that explicitly encodes “yielding” as an optimizable risk allocation objective. To our knowledge, this is the first work to jointly optimize third-party risk, ego-vehicle safety, and traffic throughput within a nonlinear MPC formulation, with theoretical guarantees on closed-loop safety and feasibility. Simulation results demonstrate an average 37% reduction in interactive risk, a 52% increase in lane-change yielding rate, and sustained traffic throughput at 98.6% of the baseline.
Application Category
📝 Abstract
With more autonomous vehicles (AVs) sharing roadways with human-driven vehicles (HVs), ensuring safe and courteous maneuvers that respect HVs' behavior becomes increasingly important. To promote both safety and courtesy in AV's behavior, an extension of Control Barrier Functions (CBFs)-inspired risk evaluation framework is proposed in this paper by considering both noisy observed positions and velocities of surrounding vehicles. The perceived risk by the ego vehicle can be visualized as a risk map that reflects the understanding of the surrounding environment and thus shows the potential for facilitating safe and courteous driving. By incorporating the risk evaluation framework into the Model Predictive Control (MPC) scheme, we propose a Courteous MPC for ego AV to generate courteous behaviors that 1) reduce the overall risk imposed on other vehicles and 2) respect the hard safety constraints and the original objective for efficiency. We demonstrate the performance of the proposed Courteous MPC via theoretical analysis and simulation experiments.
Problem
Research questions and friction points this paper is trying to address.
Ensuring safe and courteous AV maneuvers amidst human-driven vehicles
Extending CBF-inspired risk assessment for noisy vehicle position and velocity data
Integrating risk-aware MPC to balance safety, courtesy, and driving efficiency
Innovation
Methods, ideas, or system contributions that make the work stand out.
CBF-inspired risk evaluation for AV safety
Risk map visualization for environment understanding
Courteous MPC integrating risk and efficiency
🔎 Similar Papers
No similar papers found.
