THPL: A Vision-to-Language Decision Support Framework for Rainbow Trout Feeding Management in RAS
作者: Meng Liang, Guanbo Feng, Haozhuang Chi, Shilong Zhao, Zhixin Xiong, Yuhang He, Wenfeng Han, Tianhao Zhao, Zhihong Ma, Ying Liu
分类: cs.AI
发布日期: 2026-10-01
备注: Meng Liang and Guanbo Feng contributed equally. Corresponding authors: Zhihong Ma and Ying Liu. 50 pages, 10 figures, 3 tables. Supplementary video: https://youtu.be/Tg2Qk7m46-A
💡 一句话要点
提出THPL框架以解决循环水养殖系统中虹鳟鱼喂养管理问题
🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture) 支柱八:物理动画 (Physics-based Animation) 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 精准喂养 循环水养殖 虹鳟鱼 多模态决策 因果推理 大型语言模型 行为编码 活动系数
📋 核心要点
- 现有方法在鱼类行为与管理知识之间缺乏认知对齐,导致喂养决策的可执行性和可解释性不足。
- THPL框架通过提取鱼类轨迹和建立活动系数,结合层次行为编码器和大型语言模型,提供了新的喂养决策支持。
- 实验结果显示,使用双证据标记的决策准确率从33.33%提升至93.33%,并通过反事实mDPO进一步提升至96.67%。
📝 摘要(中文)
在循环水养殖系统(RAS)中,精准喂养对于降低成本和改善鱼类福利至关重要。然而,现有方法缺乏鱼类行为与管理知识之间的认知对齐,阻碍了可执行和可解释的喂养决策的形成。为此,本文提出了THPL,一个针对虹鳟鱼(Oncorhynchus mykiss)的生成喂养决策框架。首先,Fishsort提取鱼类轨迹以建立活动系数(AC),量化喂养强度。其次,层次行为编码器(HBE)利用时间和集合变换器建模个体时间进程和集体动态,将轨迹张量转化为显性物理和隐性软标记的双证据表示。最后,这些标记与环境参数、元数据和专家规则结合,通过LoRA微调大型语言模型(LLM),并通过反事实多模态直接偏好优化(mDPO)增强因果推理。结果表明,AC与专家标注的喂养强度之间存在显著的单调正相关(Spearman $ρ= 0.925$, $p < 0.001$)。
🔬 方法详解
问题定义:本文旨在解决循环水养殖系统中虹鳟鱼喂养管理的决策问题,现有方法在鱼类行为与管理知识的认知对齐上存在不足,影响了决策的可执行性和可解释性。
核心思路:THPL框架通过提取鱼类的活动轨迹,建立活动系数(AC)来量化喂养强度,并结合层次行为编码器(HBE)和大型语言模型(LLM),实现精准的喂养决策支持。
技术框架:该框架主要包括三个模块:1) Fishsort模块用于提取鱼类轨迹并计算活动系数;2) HBE模块利用时间和集合变换器建模鱼类行为;3) 最后通过LoRA微调LLM,并使用反事实mDPO增强因果推理。
关键创新:最重要的创新在于将连续运动学与LLM推理相结合,形成双证据表示,显著提升了决策的准确性和可解释性。
关键设计:在模型设计中,采用了时间和集合变换器来处理鱼类行为数据,使用LoRA进行模型微调,并通过反事实mDPO优化决策过程,确保因果一致性和操作安全性。
🖼️ 关键图片
📊 实验亮点
实验结果显示,活动系数(AC)与专家标注的喂养强度之间存在显著的正相关,决策准确率从33.33%提升至93.33%,使用反事实mDPO后进一步提升至96.67%。此外,METEOR指标从58.10%提升至85.30%,有效抑制了模板化和激活偏差。
🎯 应用场景
该研究为精准水产养殖提供了新的决策支持范式,具有广泛的应用潜力,能够有效降低养殖成本,提高鱼类福利。未来,该框架可扩展至其他水产养殖品种和管理场景,推动智能养殖技术的发展。
📄 摘要(原文)
In Recirculating Aquaculture Systems (RAS), precision feeding is critical for minimizing costs and improving fish welfare. However, existing methods lack cognitive alignment between fish behaviors and management knowledge, impeding translation into executable, interpretable feeding decisions. To address this, we propose THPL, a generative feeding decision framework tailored for rainbow trout (Oncorhynchus mykiss) in RAS. First, Fishsort extracts trajectories to establish an Activity Coefficient (AC) quantifying feeding intensity. Second, a Hierarchical Behavior Encoder (HBE) models individual temporal progression and collective dynamics using Temporal and Set Transformers, transforming trajectory tensors into dual-evidence representations of explicit physical and implicit soft tokens. Finally, these tokens are integrated with environmental parameters, metadata, and expert rules to fine-tune an LLM via LoRA, followed by counterfactual multimodal Direct Preference Optimization (mDPO) to reinforce causal reasoning. Results show that AC exhibits a statistically significant monotonic positive correlation with expert-annotated feeding intensity (Spearman $ρ= 0.925$, $p < 0.001$). Ablations indicate that decision accuracy improves from 33.33% (text-only baseline) to 93.33% with dual-evidence tokens, confirming that continuous spatiotemporal tokens provide necessary physical grounding for LLMs. Compared with standard LoRA, counterfactual mDPO elevates decision accuracy from 93.33% to 96.67%, advances METEOR from 58.10% to 85.30%, reduces Self-BLEU-2 from 58.79% to 52.88%, and increases Distinct-3 from 6.68% to 7.81%, suppressing templating and actuation biases while reinforcing causal consistency and operational safety. Overall, by integrating continuous kinematics with LLM reasoning, this study provides a novel decision support paradigm for precision aquaculture.