Skip to content

论文arXiv 2611.199125 天前

AgenticJevNav框架赋能钢镚L1四足机器人实现70%开放搜索成功率 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:AgenticJevNav: Agentic Object Search and Navigation via Event-Driven Verification(arXiv 2611.19912)

核心内容 ​

针对具身智能体在非结构化环境中因推理延迟或执行失败导致的目标丢失问题,研究团队提出AgenticJevNav导航框架。该系统在六类仿真任务中实现73.33%的成功率(SR),较次优Agent-only聚合控制方案高出21.67个百分点。在真实物理世界部署中,基于GENISOM L1四足机器人完成30次试验,取得70.0%的成功率,证明了该架构在处理不完整证据与动态环境干扰时的鲁棒性。

技术上,系统整合RGB视觉、里程计、证据记忆与反馈信号进行目标导向规划,并引入独立RGB反射层约束底层运动安全。核心创新在于事件触发验证模块(Jev),仅在动作阻塞、失败或连续低进展时激活结构化证据审查,通过版本校验与新鲜度检查防止过时决策。当目标修订时,系统自动撤销废弃请求与动作并触发重规划,确保Agent在长时序任务中保持目标所有权与执行边界的安全性。

关键看点 ​

  • 实机性能验证:在GENISOM L1四足机器人上完成30次物理试验,目标搜索成功率达70.0%,包含有界搜索报告功能,验证了算法从仿真到真机的迁移能力。
  • 仿真显著优势:在六类模拟任务族60次试验中SR为73.33%,相比不同历史协议下的次优Agent-only聚合控制基线提升21.67个百分点,确立了架构优越性。
  • 事件驱动验证:Jev模块仅在执行受阻、失败或连续两段低进展时触发结构化证据审查,结合版本与新鲜度检查机制,有效规避了高频推理带来的计算冗余与决策漂移。
  • 安全执行架构:采用单一执行器配合独立RGB反射层约束运动,支持目标修订时自动撤销过时请求与动作,确保Agent在动态环境中维持目标所有权与有界行动集。

工程与产业观察 ​

该工作为四足机器人在非结构化场景下的长时序自主作业提供了可复用的工程范式。其事件触发验证机制有效平衡了大模型推理延迟与实时控制需求,解决了传统端到端导航易受中间态干扰的痛点。对于具身智能开发者而言,将高层语义规划与底层安全反射解耦,并在真机验证中保持70%以上成功率,是评估开放式搜索算法落地价值的重要参考坐标。

英文摘要 (Abstract) ​

Agentic navigation must maintain goals and adapt actions from incomplete evidence despite execution failures and delayed inference. We present AgenticJevNav, which links goal-directed planning, evidence memory, event-triggered verification, and bounded execution. The Agent plans from RGB, odometry, memory, and feedback, retaining goal ownership while authorizing a bounded action set. Jev reviews structured evidence after blocked/failed execution or two consecutive low-progress segments. Version, freshness, and once-only checks govern decision application. A single executor and independent RGB reflex constrain motion. Goal revisions revoke obsolete requests and actions before replanning. Across six simulated task families, AgenticJevNav achieves 73.33% SR over 60 trials, 21.67 percentage points above the next-best Agent-only aggregate control under differing historical protocols. A real-world GENISOM L1 quadruped deployment achieves 70.0% success over 30 trials, including bounded search reporting. Together, the simulation and physical-robot results demonstrate the effectiveness of the proposed architecture, while remaining failures highlight opportunities to improve grounding, approach planning, and runtime.

作者:Shuning Zhang, Shuli Zhang, Yunheng Wang, Wei Lu, Jiaxi Zhang, Yihang Kang, Tao Wang, Xiangyu Chen, Yixiao Feng, Kai Sheng, Renjing Xu

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

外部来源

本页事实对应的公开页面,以原文为准。(点击将离开本站)

  1. arXiv 2611.19912:AgenticJevNav: Agentic Object Search and Navigation via Event-Driven Verification ↗访问 2026-11-18