外观
论文arXiv 2610.1386219 天前
BT-Agent：使用行为树和多保真评估部署板载机器人智能体
原文链接：BT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity Evaluation（arXiv 2610.13862 · 发布日期：2026-10-09）
BT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity Evaluation
BT-Agent将LLM任务决策与预定义行为树技能结合，在四足机器人和多保真基准上验证板载智能体部署。
核心要点
- 面向移动机器人板载部署，需在有限算力和内存下兼顾任务推理与响应执行。
- 架构结合LLM任务决策与预定义BT技能，技能检查执行条件并返回结构化失败反馈。
- 在四足机器人五类任务上以9B模型全板载运行，干预测试可本地停止导航并保持智能体活跃。
- 161任务基准中，文本吞吐高10.9倍；4B和9B下相对最强基线成功率增益最大。
验证范围与局限：验证范围包括四足机器人五类任务的全板载运行，以及161个文本任务和39个Habitat仿真任务评测。
英文摘要 (Abstract)
Deploying language-model agents onboard mobile robots requires task reasoning and responsive execution within limited compute and memory. We propose BT-Agent, an onboard architecture combining LLM-driven task decisions with predefined behavior-tree (BT) skills. These skills enforce execution conditions and return structured failure feedback. We demonstrate fully onboard operation with a 9B model on a quadruped across five task categories. Intervention tests show that local checks stop ongoing navigation without waiting for another model decision, while the agent remains active to retry or report constraints. To compare agent designs efficiently, we introduce a 161-task multi-fidelity benchmark, evaluated in text on all tasks and in Habitat on 39. Text supports 10.9$\times$ higher evaluation throughput, while simulation reveals how perception and motion failures change task outcomes. BT-Agent's largest success gains over the strongest Act/ReAct baseline occur at 4B and 9B: approximately 10 and 5 percentage points. Ablations identify structured tool calls and informative failure feedback as the most useful components.
作者：Fabio Hubel, Adam Lilja, Yue Yin, Siming He, Claire Tomlin, S. Shankar Sastry, Jonas Frey, Marco Pavone
来源
本页事实对应的公开页面，以原文为准。