CoreSense：可追溯的故障回忆与冲突感知信念门控，用于可审计的机器人决策
CoreSense: Traceable Failure Recall and Conflict-Aware Belief Gating for Auditable Robot Decisions
浏览论文内容
中文总结 AI 辅助
CoreSense通过冲突感知信念门控和可追溯证据，将机器人不安全继续操作率降至0%，实现可审计的故障回忆决策。
中文摘要 AI 辅助
机器人能够回忆先前的故障，但不知道所回忆的证据是否仍然有效、是否与当前观察相冲突，或者是否足以指导决策。我们提出了CoreSense，一种机器人系统集成架构，它将可追溯的情景证据与冲突感知信念门控以及有界、可审计的建议相结合。该门控在允许继续（PROCEED）、请求重新观察、弃权（不执行）或升级之前，会检查范围、来源、时间、矛盾和支持。评估遵循三个互补层次，无需指挥实体机器人：离线公共真实机器人数据、冻结的信号级模拟和实时云部署路径。在CableTrace-120和BotFails-200上，信念门控将协议定义的不安全继续操作从20%和40%降至0%。一个独立校准的原始视频策略也达到了0%的不安全继续操作，但过度阻止了每个名义事件。在公共数据上，ViFailback-BotFails视觉检测器达到0.778的AUROC，但仍然全阻止，而循环不相交的UR3遥测用于保护性停止则产生0%的不安全继续操作、36.1%的过度阻止和61.9%的覆盖率；夹持损失迁移仍然是一个负面结果。受控物理验证产生3.3%、0%和42.0%，而冲突感知融合产生4.7%、0%和42.8%。最后，20/20的云召回验证了CockroachDB Cloud-Amazon Bedrock部署路径。证据支持一种可审计的集成模式，而非自主恢复或认证安全。
英文摘要
Robots can recall prior failures without knowing whether recalled evidence remains valid, conflicts with current observations, or is sufficient to guide a decision. We present CoreSense, a robot-system integration architecture that combines traceable episodic evidence with a conflict-aware belief gate and bounded, auditable recommendations. The gate checks scope, provenance, time, contradiction, and support before it permits PROCEED, requests re-observation, abstains, or escalates. Evaluation follows three complementary layers without commanding a physical robot: offline public real-robot data, a frozen signal-level simulation, and a live cloud deployment path. On CableTrace-120 and BotFails-200, belief gating reduces protocol-defined unsafe proceeds from 20% and 40% to 0%. A disjointly calibrated raw-video policy also reaches 0% unsafe proceed, but overblocks every nominal episode. On public data, a ViFailback-BotFails visual detector reaches 0.778 AUROC yet remains all-blocking, whereas cycle-disjoint UR3 telemetry for protective stops yields 0% unsafe proceed, 36.1% overblocking, and 61.9% coverage; grip-loss transfer remains a negative result. Controlled physical corroboration yields 3.3%, 0%, and 42.0%, while conflict-aware fusion yields 4.7%, 0%, and 42.8%. Finally, 20/20 cloud recalls validate a CockroachDB Cloud-Amazon Bedrock deployment path. The evidence supports an auditable integration pattern, not autonomous recovery or certified safety.
