CARVE-Q: Quantum-Proposed, Classically Certified Interactive Driving Repair

CARVE-Q：量子建议、经典认证的交互式驾驶修复

Abstract: The critical question after a correct driving veto is not only whether a maneuver is unsafe, but whether the blocked interaction admits a lawful, auditable, and responsibility-bounded repair. Prediction and game-theoretic planners can suggest plausible cooperation, yet they do not return a proof that the repair respects hard rules, right-of-way, cost allocation, and ego fallback. We introduce CARVE, Certified Affordable Repair of Vetoed maneuvers via Envelopes, a certificate architecture for prediction-free interactive repair.

摘要： 在正确的驾驶否决（veto）之后，关键问题不仅在于该机动是否不安全，还在于被阻断的交互是否允许进行合法的、可审计的且责任明确的修复。预测规划器和博弈论规划器可以提出合理的协作方案，但它们无法提供证明来确保修复方案遵循硬性规则、通行权、成本分配以及自我后备（ego fallback）机制。我们引入了 CARVE（通过包络线进行否决机动的认证式经济修复），这是一种用于无预测交互式修复的证书架构。

Given a vetoed maneuver, CARVE constructs a finite repair lattice and emits a structured certificate recording the binding rule, selected joint repair, right-of-way-scaled cooperation envelope, responsibility-weighted cost split, and ego-only fallback. This certificate view reveals the algorithmic bottleneck: multi-owner repair induces a product lattice $M = \prod_j |\mathcal{A}_j|$. We therefore introduce CARVE-Q, a verifier-shielded quantum-AI search layer that applies quantum minimum finding only to this black-box lattice while leaving all safety authority classical.

给定一个被否决的机动，CARVE 会构建一个有限修复格（repair lattice），并生成一份结构化证书，记录约束规则、选定的联合修复方案、按通行权缩放的协作包络线、责任加权的成本分摊以及仅限自我的后备方案。这种证书视图揭示了算法瓶颈：多所有者修复会引发一个乘积格 $M = \prod_j |\mathcal{A}_j|$。因此，我们引入了 CARVE-Q，这是一个由验证器保护的量子人工智能搜索层，它仅将量子最小值查找应用于此黑盒格，同时将所有安全权限保留在经典计算范畴内。

In the conservative verifier-oracle model, exact classical minimum finding requires $\Theta(M)$ queries in the worst case, whereas Durr-Hoyer/Grover minimum finding uses $O(\sqrt{M})$ oracle queries with high probability. We prove verifier-shielded certificate soundness, priority non-elicitation, black-box query separation, and finite-precision reversible-oracle constructibility.

在保守的验证器-预言机模型中，精确的经典最小值查找在最坏情况下需要 $\Theta(M)$ 次查询，而 Durr-Hoyer/Grover 最小值查找在高概率下仅需 $O(\sqrt{M})$ 次预言机查询。我们证明了验证器保护下的证书可靠性、优先级非诱导性、黑盒查询分离性以及有限精度可逆预言机的可构建性。

We then demonstrate state-vector minimum finding on CARVE repair oracles up to 65,536 assignments and validate certificate preservation on Lanelet2-grounded INTERACTION replay with 100% right-of-way respect, 100% blame consistency, and zero priority false positives. The result is a trust-bounded quantum-AI pattern for certified autonomy: quantum proposes; CARVE certifies.

随后，我们在多达 65,536 个分配项的 CARVE 修复预言机上演示了状态向量最小值查找，并在基于 Lanelet2 的 INTERACTION 重放中验证了证书的有效性，实现了 100% 的通行权遵循、100% 的责任一致性以及零优先级误报。其结果是一种用于认证自动驾驶的信任受限型量子人工智能模式：量子负责提出方案，CARVE 负责进行认证。