Skip to content

Event

Policy Confidence Modulates Safety Filter Conservativeness

1 reports · 1 sources

Javier Borquez and Jaime F. Fisac propose a filter-agnostic procedure that uses policy confidence at runtime to modulate the conservativeness of a safety filter: within the filter's operational design domain (ODD), confidence is traded for performance; outside the ODD, low confidence yields additional safety margin. The authors state that preliminary F1TENTH simulations show that this modulated filter combines the advantages of permissive and conservative filters. This conclusion currently derives only from simulation.

Report timeline

  1. Confidence-Modulated Safety Filtering for End-to-End Policies

    The authors propose a filter-agnostic pipeline that modulates the conservativeness of a safety filter at runtime using policy confidence: inside the filter's operational design domain (ODD), confidence is traded for performance; beyond the ODD, low confidence yields additional safety margin. Preliminary F1TENTH simulations show that the modulated filter combines the strengths of permissive and conservative filters.

    arXiv cs.RO ·

Related topics

Planning and decision makingRobot models and learningSafety and reliabilityResearch papers

Interest trend

Current
3
Peak
4Nov 4 01:00
Past 24 hours
–

The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.