Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces CARVE, a novel certification layer designed to address the limitations of existing autonomous driving systems in handling vetoed maneuvers during interactive driving scenarios. By formulating the concept of interactive repair certification, CARVE enables the identification of feasible maneuvers that respect right-of-way rules without relying on predictions of other agents' behavior. The results demonstrate that CARVE-Greedy successfully accepts 98.64% of initially vetoed maneuvers while maintaining compliance with right-of-way regulations and minimizing false positives and stress-inducing vetoes.
CARVE can recover nearly all human-resolved vetoes in interactive driving scenarios without relying on predictions, ensuring safer and more efficient maneuvering.
Interactive driving exposes a failure mode that is easy to miss in rule-aware autonomous-driving stacks: a hard-rule margin can be negative for an ego candidate even though a small lawful accommodation by a non-priority agent would restore feasibility. Existing rulebooks, shields, and reachability filters are strong at vetoing unsafe actions, while prediction-based planners model likely responses. Neither returns a runtime proof object that states which bounded multi-agent edit repairs the maneuver, who owns the edit, whether the request is right-of-way affordable, and what ego fallback remains if the request is not observed. We formulate this missing object as *interactive repair certification* and introduce *CARVE*, a prediction-free certificate layer over a finite lattice of ego-owned and agent-owned tactical operators. Agent-owned requests are admissible only inside \(B_j(s) = \beta(\pi_j)\alpha_j^{\max}(s)\), a cooperation envelope that separates kinematic reachability from normative priority. The resulting certificate records the binding rule, repair category, repair set, responsibility-weighted cost split, and fallback. On 589 Lanelet2-geometry-grounded INTERACTION replay episodes, CARVE-Greedy accepts 98.64% of initially vetoed maneuvers and recovers 370/378 human-resolved false vetoes, while preserving 589/589 right-of-way respect, zero priority-agent false positives, and 400/400 negative-stress vetoes. We prove certificate soundness, structural right-of-way respect, exact finite-lattice minimality, fallback contingency, and blame-consistency conditions. CARVE does not predict or require another driver's compliance; it certifies whether a proposed interaction is bounded, attributable, and normatively admissible under declared assumptions.