发表机构
Kobe University; University of California, San Diego; University of Michigan（神户大学; 加利福尼亚大学圣迭戈分校; 密歇根大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出OcclusionCBF安全过滤器，将备份控制屏障函数扩展到隐藏动态障碍物的可达占用预测，通过仿射约束实现最小侵入性过滤，并保证递归可行性和碰撞避免，实验验证了其优于现有基线。
AI 中文摘要
在遮挡条件下导航的机器人可能进入这样的状态：一旦动态障碍物变得可见，任何可容许输入都无法避免与其碰撞。我们提出了OcclusionCBF，一种安全过滤器，将备份控制屏障函数扩展到遮挡区域中潜在隐藏动态障碍物的可达占用预测。该方法针对碰撞膨胀占用和已验证的终端集对规定的备份滚动进行认证，为最小侵入性二次规划过滤生成仿射约束。我们建立了所得安全过滤器的递归可行性，以及对占用预测所覆盖的每种隐藏障碍物运动的碰撞避免保证。随机基准测试、MetaUrban仿真和硬件实验表明，与反应式和遮挡感知预测基线相比，任务成功率有所提高，且计算时间在毫秒级。
英文摘要
Robots navigating under occlusion may enter states from which no admissible input can avoid a dynamic obstacle once it becomes visible. We present OcclusionCBF, a safety filter that extends backup control barrier functions to reachable-occupancy predictions for potentially hidden dynamic obstacles in occluded regions. The method certifies a prescribed backup rollout against collision-inflated occupancy and a verified terminal set, yielding affine constraints for minimally invasive quadratic-program filtering. We establish recursive feasibility of the resulting safety filter, and collision avoidance for every hidden-obstacle motion covered by the occupancy prediction. Randomized benchmarks, MetaUrban simulations, and hardware experiments demonstrate improved task success over reactive and occlusion-aware predictive baselines with millisecond-scale computation.
CommentsThe first two authors contributed equally to this work. Project page: https://www.taekyung.me/occlusion-cbf
