# SPICE触觉扩散策略实现密集植被95%穿越成功率

> 原文链接：https://robotics.hellobike.com/papers/2026-11-19-2611-23585-9e8d3e3e
> 频道：papers | 更新日期：2026-11-19 | 标签：auto, arxiv
> 核心摘要：针对农业采摘视觉遮挡难题，SPICE提出纯触觉条件扩散策略。180次实机测试中枝干规避成功率达95%，较最强基线提升50个百分点；零样本迁移至番茄与青柠植株成功率87.5%，验证了触觉生成式策略在遮蔽环境下的鲁棒性。

# SPICE触觉扩散策略实现密集植被95%穿越成功率

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[SPICE: Stochastic Policy for Interaction in Cluttered Environments](https://arxiv.org/abs/2611.23585)（arXiv 2611.23585）

## 核心内容

针对农业采收与修剪中密集枝叶导致的视觉遮挡及间歇接触难题，研究团队提出SPICE（Stochastic Policy for Interaction in Cluttered Environments），这是首个专用于物理 cluttered 植物冠层目标到达的触觉条件扩散策略。该策略仅依赖触觉反馈作为环境感知输入，在超过180次真实机器人试验中，实现了95%的枝干规避操作成功率，显著优于45%的最强触觉基线，且在完全视觉遮挡下仍保持有效，而图像条件扩散策略在此场景下彻底失效。

SPICE通过空间触觉信息与显式接触条件化机制，习得穿过柔性枝叶、绕过部分遮挡茎秆及操纵阻挡枝条三类行为。其核心优势在于解决了自由空间与富接触观测不平衡导致的学习困难。在针对未见过的番茄和青柠植株进行的40次零样本迁移测试中，系统取得87.5%的成功率，证明了触觉条件生成式策略在非结构化农业环境中具备跨物种泛化能力，为具身智能在极端感知受限场景下的作业提供了新范式。

## 关键看点

- **纯触觉感知架构**：摒弃视觉输入，仅以触觉传感作为唯一环境反馈，解决密集植被中视线受阻与光照变化导致的感知失效问题。
- **性能量化对比**：180次实机测试中枝干规避成功率达95%，最强触觉基线仅45%，图像条件DP在视觉遮挡下完全失败。
- **零样本泛化验证**：在未参与训练的番茄与青柠植株上完成40次零样本测试，成功率87.5%，证实策略具备跨植物种类迁移能力。
- **接触行为解耦**：通过显式接触条件化机制，成功学习穿透柔性枝叶、绕避硬茎及主动操纵障碍枝条三种差异化交互模式。

## 工程与产业观察

SPICE证明了在视觉完全不可靠的非结构化环境中，纯触觉条件扩散模型可作为具身操作的有效替代方案。其95%实机成功率与跨物种零样本泛化能力，为农业机器人及野外作业装备提供了摆脱对高精度视觉依赖的工程路径，提示行业应重视触觉生成式策略在感知退化场景中的数据价值与控制潜力。

## 英文摘要 (Abstract)

Agricultural tasks such as harvesting and pruning require robots to reach through dense foliage, where contact is often unavoidable and vision is obstructed. Intermittent contact creates an imbalance between free-space and contact-rich observations, complicating the learning of contact-responsive behaviours. We present SPICE, a tactileconditioned diffusion policy for reaching targets in dense plant canopies using tactile sensing as the sole environmental feedback. SPICE exhibits three behaviours: moving through compliant foliage, manoeuvring around partially obstructing stems, and manipulating branches that block the target path. To the best of our knowledge, SPICE is the first tactile-conditioned diffusion policy for target reaching through physically cluttered plant canopies. Across over 180 real-robot trials, SPICE was evaluated against tactile-conditioned, image-conditioned, and reactive-control baselines. Spatial tactile information and explicit contact conditioning proved important, with SPICE achieving 95% branch-manoeuvring success versus 45% for the strongest tactile baseline. SPICE also achieved branch manipulation beyond the reactive controller and remained effective under visual occlusion, where the image-conditioned DP failed. Zero-shot transfer across 40 trials on unseen tomato and lime plants achieved 87.5% success rate. These results demonstrate the potential of tactile-conditioned generative policies for interaction in visually occluded plant environments.

作者：Nidhi Parayil, Benjamin Greenland, Thierry Peynot, Chris Lehnert
:::

## 原始参考来源 (Sources)

- [arXiv 2611.23585：SPICE: Stochastic Policy for Interaction in Cluttered Environments](https://arxiv.org/abs/2611.23585)