NavHarness: Towards Lifelong Embodied Navigation

arXiv:2609.34276 · cs.RO · Submitted 2026-09-28 · Read on arXiv

cs.RO

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/billzhao1030/NavHarness

Project page: https://billzhao1030.github.io

Terminology

• Verification — 59× in this paper · explained in 2 episodes
• Benchmark — 22× in this paper · explained in 2 episodes
• Verifier — 16× in this paper · explained in 2 episodes
• Actor — 12× in this paper · explained in 3 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Core — 7× in this paper · explained in 2 episodes
• Trace — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 5× in this paper
• Embodied AI — 3× in this paper · explained in 2 episodes
• Multimodal Reasoning — 3× in this paper · explained in 5 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• Agent Harness — 2× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 2× in this paper
• 3D Gaussian Splatting — 1× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• AgenticNav — 1× in this paper · explained in 1 episode
• Fidelity — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Gaussian Splatting — 1× in this paper · explained in 4 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• On Evaluation of Embodied Navigation Agents
• Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments
• Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigation
• HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
• Show-Harness: Just a VLM Agent Can Play Robots
• SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning
• RHO: Your Coding Agent is Secretly a Roboticist
• EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation
• End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering
• From Question Answering to Task Completion: A Survey on Agent System and Harness Design
• SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning
• Self-GC: Self-Governing Context for Long-Horizon LLM Agents
• RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning
• General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping
• AnyGoal: Vision-Language Guided Multi-Agent Exploration for Training-Free Lifelong Navigation
• DyNaVLM: Zero-Shot Vision-Language Navigation System with Dynamic Viewpoints and Self-Refining Graph Memory
• ACON: Optimizing Context Compression for Long-horizon LLM Agents
• ObsGraph: Hierarchical Observation Representation for Embodied Reasoning and Exploration

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving