Active Spatial Inspection for Effective and Efficient Embodied Exploration

arXiv:2609.22385 · cs.RO, cs.CV · Submitted 2026-09-18 · Read on arXiv

cs.RO, cs.CV

Submitted: 2026-09-18

Updated: 2026-09-18

Terminology

• Verification — 43× in this paper · explained in 2 episodes
• Ablation — 14× in this paper · explained in 1 episode
• Discriminative Probing — 13× in this paper
• Prospective Prioritization — 13× in this paper
• Retrospective Suppression — 12× in this paper
• Benchmark — 8× in this paper · explained in 2 episodes
• Foundation Model — 4× in this paper · explained in 3 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Active Information Seeking — 3× in this paper · explained in 1 episode
• Embodied AI — 3× in this paper · explained in 2 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• History-aware Low-progress Penalization — 3× in this paper
• AI Agents — 2× in this paper · explained in 2 episodes
• Active Hidden-Space — 2× in this paper
• Active Perception — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Gaussian Splatting — 2× in this paper · explained in 4 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Success Rate — 2× in this paper
• Vision-language models — 2× in this paper · explained in 2 episodes
• Visual Frontier Rejection — 2× in this paper
• Active Exploration — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Evidential Visual Point Localization and Verification — 1× in this paper
• Regret — 1× in this paper · explained in 3 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Truncated Signed Distance Function — 1× in this paper
• Unified Framework — 1× in this paper · explained in 5 episodes
• Verifier — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
• Qwen2.5-VL Technical Report
• GPT-4 Technical Report
• Explore until Confident: Efficient Exploration for Embodied Question Answering
• Memory-Centric Embodied Question Answering
• Stop Wandering: Efficient Vision-Language Navigation via Metacognitive Reasoning
• Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigation
• Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instances
• MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• LLaVA-OneVision: Easy Visual Task Transfer
• Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
• ConceptFusion: Open-set Multimodal 3D Mapping
• HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering
• GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning
• ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay
• Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation
• Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
• Qwen3.5-Omni Technical Report

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