IntentNav: Learning Spatial-Visual Object Navigation from Human Demonstrations
cs.RO
Submitted: 2026-06-06
Updated: 2026-11-03
Terminology
Sources
- ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
- On Evaluation of Embodied Navigation Agents
- ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation
- CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs
- STRIVE: Structured Representation Integrating VLM Reasoning for Efficient Object Navigation
- Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities
- Multimodal Large Language Model for Visual Navigation
- CompassNav: Steering From Path Imitation To Decision Understanding In Navigation
- Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning
- NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
- Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
- OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation
- SysNav: Multi-Level Systematic Cooperation Enables Real-World, Cross-Embodiment Object Navigation
- VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model
- TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
- TriHelper: Zero-Shot Object Navigation with Dynamic Assistance
- BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation