Backend
Recoverability, Not Invariance: Certified Safety for Robots at the Limits of Performance
arXiv cs.RO0 views
arXiv:2611.23589v1 Announce Type: new Abstract: Safety certification in robotics typically rests on forward invariance of the deployed controller, a property that demands high-fidelity models at the edge of the operating envelope, exactly where models are least reliable and robots perform best. As a result, many of the behaviors we most want robots to run, from learned policies to aggressive maneuvers at the limits of traction, cannot be certified at all. We introduce recoverability, a contraction-theoretic safety concept that resolves this tension by certifying a robot's ability to reengage a trusted recovery mode rather than the invariance of a deployed behavior. We prove that switching to the recovery mode from anywhere inside a certified tube guarantees exponential convergence, even under disturbances and model error. To decide when to switch, we derive the contraction insertion gradient, the first-order effect of a recovery insertion on the certificate, and embed it in a switching-time program in which feasibility alone guarantees safety and optimality only shapes performance. To supply the certificates, we develop sequential convex synthesis that monotonically grows the certified tube toward the exact viability kernel. We validate our approach in simulated quadrotor flight through uncertain obstacles, where it outperforms invariance-based safety filters, and in hardware deployments aboard a full-scale IndyNXT autonomous racecar, where it repeatedly recovers the car from an aggressive raceline at the limits of handling in the rain. Recoverability provides a certified exit strategy, extending formal safety guarantees to aggressive, learned, and experimental behaviors without requiring their invariance.
Source:https://arxiv.org/abs/2611.23589PreviousSPICE: Stochastic Policy for Interaction in Cluttered EnvironmentsNextHow Uncertain Is My Action? Self-Correcting Visual Planning with Frozen World Models
Related posts

Introducing Tool Retrieval in the Gemini API
0Google AI Blog
How to Scrape Websites in Python with Olostep
0freeCodeCamp

How I Built a 100% Local PDF RAG Assistant on CPU Using Python and Ollama
0dev.to
A 302 From Your Upstream Can Delist Your Service
0dev.to
Calling C from KingCobra: a hands-on FFI tutorial
0dev.to
Private Object Storage for SaaS Documents: Presigned Links, Isolation, and Recovery
0dev.to