🤖 AI Summary
In dense dynamic environments, real-time path planning faces challenges including high prediction computational overhead and coarse risk assessment. This paper proposes HyPRAP, a risk-aware hybrid path planning framework. First, it introduces a Prediction-based Collision Risk Index (P-CRI) to dynamically identify high-risk obstacles and allocate high-fidelity prediction models accordingly. Second, it employs multi-model conformal prediction to generate joint confidence bounds, enabling uncertainty quantification and synergistic optimization of computational resources guided by risk. Third, it integrates Model Predictive Control (MPC) for efficient real-time trajectory generation. Simulation results demonstrate that HyPRAP significantly reduces computational load while maintaining safety; P-CRI achieves higher risk discrimination accuracy than conventional distance-based metrics; and the overall framework outperforms single-predictor baselines in the safety–efficiency trade-off.
📝 Abstract
Real-time path planning in dense, uncertain environments remains a challenging problem, as predicting the future motions of numerous dynamic obstacles is computationally burdensome and unrealistic. To address this, we introduce Hybrid Prediction-based Risk-Aware Planning (HyPRAP), a prediction-based risk-aware path-planning framework which uses a hybrid combination of models to predict local obstacle movement. HyPRAP uses a novel Prediction-based Collision Risk Index (P-CRI) to evaluate the risk posed by each obstacle, enabling the selective use of predictors based on whether the agent prioritizes high predictive accuracy or low computational prediction overhead. This selective routing enables the agent to focus on high-risk obstacles while ignoring or simplifying low-risk ones, making it suitable for environments with a large number of obstacles. Moreover, HyPRAP incorporates uncertainty quantification through hybrid conformal prediction by deriving confidence bounds simultaneously achieved by multiple predictions across different models. Theoretical analysis demonstrates that HyPRAP effectively balances safety and computational efficiency by leveraging the diversity of prediction models. Extensive simulations validate these insights for more general settings, confirming that HyPRAP performs better compared to single predictor methods, and P-CRI performs better over naive proximity-based risk assessment.