HarnessVLN: training-free embodied navigation agent sets SOTA on four benchmarks
Yang Chen · hf · 2026-09-16
- Approach: HarnessVLN is a zero-shot, training-free embodied navigation framework whose Agent Harness coordinates perception, retrieval, grounding, navigation, recovery, and termination via a unified tool interface.
- Verification: Planner proposals are validated against spatial evidence, geometric feasibility, and subgoal consistency; hierarchical event memory tracks progress while a persistent spatiotemporal graph stores reusable spatial evidence and failure annotations.
- Results: 60.8% / 53.9% / 76.0% / 59.3% success rates on R2R, RxR, HM3D-v2, and HM3D-OVON, surpassing prior training-free SOTA.
- Deployment: A replaceable Navigation Executor supports both instruction-following and object-goal navigation, demonstrated on a humanoid robot in real-world environments.
More from Embodied
- ETH Zürich robotic hand walks on its own fingers, no legs or wheels needed — lukas_m_ziegler · 2026-09-16
- Reach Robotics' 4.5kg electric subsea arm lifts 10kg at 450m, displacing hydraulics — lukas_m_ziegler · 2026-09-16
- Doubao phone assistant consumer version ships on Nubia NaviX Ultra from ¥5,999 — 数字生命卡兹克 · 2026-09-16
- AD then vs now: 1990s Mercedes hit 180kph on autobahn; a talk on measuring driving policy progress — abursuc · 2026-09-16
- Awesome Robot Use Agent: A Curated Collection of Papers, Tools and Demos for Robot Agents — AdinaYakup · 2026-09-16
- PlayCanvas beats Spark in LoD perf: 220-240 fps vs 170-180 fps — willeastcott · 2026-09-16