SmellDiffusion：基于扩散模型的四足导航与嗅觉场景图
SmellDiffusion: Diffusion-Based Quadruped Navigation with Olfactory Scene Graphs
- Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
SmellDiffusion提出一种基于扩散模型的四足机器人导航模拟管线，利用嗅觉场景图表示气体区域，通过几何门控修正源估计，在保持低气体暴露的同时实现高效导航。
AI中文摘要：
派往指定气体泄漏点的机器人必须保持气体身份、估计源位置，并导航至由此产生的目标。我们提出SmellDiffusion，一个模拟管线，它在开放词汇的嗅觉场景图中表示物种特定的气体区域，并在经典规划器和扩散规划器之间共享所选目标。其关键组件是一个用于选择性源修正的峰值局部几何门控，以及基于扩散的气体引导轨迹生成。在已求解流场中的424种独特源-风配置中，有28种配置的浓度峰值偏离源超过0.5米。一个与源无关的几何门控，仅在训练集上校准并在观测到的峰值处评估，以0.64的精确率检测出10个保留位移中的9个。对预计算的前向匹配修正进行门控，将位移情况下的平均误差从1.468米降至0.592米（降低60%），且仅在204例中的14例使用匹配。所有情况的平均误差从0.205米降至0.180米。所有规划器都接收相同的场景图源估计作为其目标。在受控比较中，最佳十次扩散的平均气体暴露与气体引导的A*相当（0.0476对0.0455）。单次扩散提议耗时41.7毫秒，而气体引导的A*为72.3毫秒，尽管最佳十次顺序采样增加了总运行时间。普通A*也能到达相同目标，并且仍然是最快且路径最短的方法。六次匹配的Gazebo运行给出A*的机器人到源平均误差为0.39米，扩散为0.31米。
英文摘要：
A robot sent to a named gas leak must preserve gas identity, estimate the source, and navigate to the resulting goal. We present SmellDiffusion, a simulation pipeline that represents species-specific gas zones in an open-vocabulary olfactory scene graph and shares the selected goal between classical and diffusion planners. Its key components are a peak-local geometric gate for selective source correction and diffusion-based, gas-guided trajectory generation. Among 424 unique source-wind configurations in solved flow, 28 have a concentration peak displaced more than 0.5m from the source. A source-independent geometric gate, calibrated only on the training split and evaluated at the observed peak, detects 9 of 10 held-out displacements at 0.64 precision. Gating a precomputed forward-matching correction reduces mean error on the displaced cases from 1.468m to 0.592m (60%), using matching for only 14/204 cases. All-case mean error falls from 0.205m to 0.180m. All planners receive the same scene-graph source estimate as their goal. In a controlled comparison, best-of-ten diffusion achieves mean gas exposure comparable to gas-guided A* (0.0476 versus 0.0455). A single diffusion proposal takes 41.7ms, compared with 72.3ms for gas-guided A*, although best-of-ten sequential sampling increases total runtime. Plain A* also reaches the same goal and remains the fastest and shortest-path method. Six matched Gazebo runs give mean robot-to-source errors of 0.39m for A* and 0.31m for diffusion.
