Rigorous uncertainty quantification is essential for the safe deployment of autonomous systems in unconstrained environments. Conformal Prediction (CP) provides a distribution-free framework for this task, yet its standard formulations rely on exchangeability assumptions that are violated by the distribution shifts inherent in real-world robotics. Existing online CP methods maintain target coverage by adaptively scaling the conformal threshold, but typically employ a static nonconformity score function. We show that this fixed geometry leads to highly conservative, volume-inefficient prediction regions when environments undergo structural shifts. To address this, we propose \textbf{AdaptNC}, a framework for the joint online adaptation of both the nonconformity score parameters and the conformal threshold. AdaptNC leverages an adaptive reweighting scheme to optimize score functions, and introduces a replay buffer mechanism to mitigate the coverage instability that occurs during score transitions. We evaluate AdaptNC on diverse robotic benchmarks involving multi-agent policy changes, environmental changes and sensor degradation. Our results demonstrate that AdaptNC significantly reduces prediction region volume compared to state-of-the-art threshold-only baselines while maintaining target coverage levels.

翻译：严格的量化不确定性对于在无约束环境中安全部署自主系统至关重要。顺应性预测为此提供了一个无需分布假设的框架，但其标准公式依赖于可交换性假设，而现实世界机器人学固有的分布偏移会违反该假设。现有的在线CP方法通过自适应调整顺应性阈值来维持目标覆盖率，但通常采用静态的非一致性评分函数。我们证明，当环境发生结构性变化时，这种固定的几何结构会导致预测区域高度保守且体积效率低下。为解决这一问题，我们提出了\textbf{AdaptNC}，一个用于联合在线调整非一致性评分参数与顺应性阈值的框架。AdaptNC利用自适应重加权方案优化评分函数，并引入回放缓冲机制以缓解评分转换期间出现的覆盖率不稳定性。我们在涉及多智能体策略变化、环境变化和传感器退化的多样化机器人基准测试中评估AdaptNC。结果表明，与仅调整阈值的最先进基线方法相比，AdaptNC在保持目标覆盖率的同时，显著减少了预测区域的体积。