CoralPlan：水下机器人检测的观测技能选择与执行
CoralPlan: Observation Skill Selection and Execution for Underwater Robotic Inspection
浏览论文内容
中文总结 AI 辅助
CoralPlan提出视觉-语言系统，从图像和任务文本选择观测技能，经模拟与硬件实验验证，实现水下机器人检测中观测完成率77.8%和联合成功率63.9%。
中文摘要 AI 辅助
水下机器人检测依赖于获取能够揭示任务相关结构的视图。对于结构复杂的珊瑚群落，识别目标仅是起点：机器人必须选择并执行适合检测任务的观测运动。我们提出了CoralPlan，一个视觉-语言系统，它从当前相机图像和任务清单提供的任务文本中选择观测技能。共享的运动接口以目标相对轨迹执行轨道（orbit）、补丁（patch）或调查（survey）；其余计划字段提供操作员指导。观测完成要求目标保持和特定于基元的覆盖，而联合成功还要求选择与记录的参考匹配。我们在144个模拟场景和36个匹配的模拟-硬件对中评估了该接口。在具有外部目标参考位姿的清水池中，硬件观测完成率达到77.8%，联合成功率达到63.9%。实验识别出参考不匹配的完成以及匹配技能选择后的不完整观测。这些结果将观测技能选择与可测量的水下执行结果联系起来，并确定了任务导向获取成功或失败的环节。
英文摘要
Underwater robotic inspection depends on acquiring views that reveal task-relevant structure. For a structurally complex coral colony, recognising the target is only the starting point: the robot must select and execute a viewing motion suited to the inspection task. We present CoralPlan, a vision-language system that selects an observation skill from a current camera image and task text supplied by an episode manifest. A shared motion interface executes orbit, patch, or survey as target-relative trajectories; the remaining plan fields provide operator guidance. Observation completion requires target keeping and primitive-specific coverage, while joint success also requires selection to match the recorded reference. We evaluate this interface in 144 simulated episodes and 36 matched simulation-hardware pairs. In a clear-water pool with external target-reference poses, hardware observation completion reaches 77.8% and joint success reaches 63.9%. The experiments identify both reference-mismatched completions and incomplete observations after a matching skill selection. These results connect observation-skill choice to measurable underwater execution outcomes and identify where task-directed acquisition succeeds or fails.
发表机构
- The Hong Kong University of Science and Technology (HKUST)（香港科技大学）
机构由 AI 辅助整理，请以论文原文为准。
