Efficient and Safe Planner for Automated Driving on Ramps Considering Unsatisfication

2025-04-20

AI Summary

In ramp scenarios, autonomous vehicles face a fundamental trade-off between safety and efficiency during lane-changing maneuvers. Method: This paper proposes a safety-efficiency co-optimized lane-changing planning framework. It introduces “dissatisfaction” as a novel metric to quantify efficiency objectives, overcoming the limitations of conventional time- or distance-based criteria. An arrow-cluster clustering sampling strategy is designed to efficiently evaluate collision risk at critical spatiotemporal points and generate low-risk trajectories. Furthermore, the method integrates velocity-constrained spatiotemporal optimization with probabilistic collision risk assessment to enable precise timing selection and smooth trajectory generation. Results: Evaluated in ramp-specific simulations, the approach achieves zero collisions while significantly improving the joint performance of safety margin and traffic throughput, demonstrating superior synergy between safety and efficiency.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Security and Privacy: Large-scale security measurements

Abstract

Automated driving on ramps presents significant challenges due to the need to balance both safety and efficiency during lane changes. This paper proposes an integrated planner for automated vehicles (AVs) on ramps, utilizing an unsatisfactory level metric for efficiency and arrow-cluster-based sampling for safety. The planner identifies optimal times for the AV to change lanes, taking into account the vehicle's velocity as a key factor in efficiency. Additionally, the integrated planner employs arrow-cluster-based sampling to evaluate collision risks and select an optimal lane-changing curve. Extensive simulations were conducted in a ramp scenario to verify the planner's efficient and safe performance. The results demonstrate that the proposed planner can effectively select an appropriate lane-changing time point and a safe lane-changing curve for AVs, without incurring any collisions during the maneuver.

Problem

• Balancing safety and efficiency in AV lane changes on ramps
• Identifying optimal lane-changing times using velocity factors
• Evaluating collision risks with arrow-cluster-based sampling

Innovation

• Unsatisfactory level metric for efficiency
• Arrow-cluster-based sampling for safety
• Velocity-based lane-changing time selection