Adaptive Risk-Certified Event-Triggered Replanning for Dynamic Navigation

2026-10-06

AI Summary

This study addresses the challenge of safe navigation under predictive uncertainty in dynamic environments, where existing methods lack planning-level risk warning. We propose CERT-Replan, a framework integrating conformal prediction, control barrier functions, and model predictive control (MPC). By leveraging calibrated obstacle risks as early warning signals to trigger replanning and innovatively incorporating CVaR-based risk monitoring, CERT-Replan achieves a risk certification mechanism that adaptively switches between single-step control filtering and multi-step planning. Experimental results demonstrate that, compared to baselines, the proposed method reduces collision rates by 83.3% and safety interventions by 32.4%. Furthermore, when combined with Trajectron++, it attains a 96% collision-free rate while confirming computational feasibility.

Abstract

Safe navigation in dynamic environments requires robots to plan under obstacle predictions whose errors are uncertain, non-stationary, and can induce rare but safety-critical failures. Existing control-barrier-function safety filters can reject immediately unsafe controls, but they provide little guidance on when the current finite-horizon planning mode itself is becoming unsafe as prediction uncertainty evolves. We propose Conformal Event-Triggered Risk-Certified Replanning (\emph{CERT-Replan}), a framework that uses calibrated barrier risk as an early-warning signal for replanning. CERT-Replan calibrates horizon-indexed obstacle-prediction residuals online and uses the resulting uncertainty radii to evaluate dynamic-obstacle safety margins. A one-step safety filter protects the next applied control, while a horizon-level risk monitor evaluates the upper-tail CVaR of predicted barrier-violation losses along the current MPC rollout. When this risk exceeds an allocated budget, CERT-Replan rejects the current planning mode and selects a lower-risk alternative, such as a different speed profile, corridor, or homotopy class, rather than repeatedly correcting the same nominal plan. In a non-stationary benchmark, CERT-Replan achieves an \(83.3\%\) collision reduction relative to the safety-filter-only baseline \textcolor{black}{and a \(77.8\%\) reduction relative to simple replanning triggers}, while reducing average safety-filter intervention by \(32.4\%\). \textcolor{black}{With Trajectron++, CERT-Replan achieves \(96\%\) collision-free operation. Hardware experiments and onboard runtime profiling demonstrate computational feasibility.}

Problem

• Safe Navigation
• Dynamic Environments
• Prediction Uncertainty
• Control Barrier Function
• Replanning

Innovation

• Conformal Prediction
• Event-Triggered Replanning
• Conditional Value-at-Risk (CVaR)
• Control Barrier Function
• Dynamic Navigation