FuguReport

IntentNav: Learning Spatial-Visual Object Navigation from Human Demonstrations

Authors Yuxin Cai, Zongtai Li, Maonan Wang, Muyi Bao, Haokun Zhu, Ruofei Bai, Ding Zhao, Zirui Li, Wenshan Wang, Wei-Yun Yau, Ji Zhang, Chen Lv
Affiliations Nanyang Technological University / Carnegie Mellon University / The Chinese University of Hong Kong / A*STAR Institute for Infocomm Research
Categories Method / Object Navigation / Spatial-visual navigation policy learning, Evaluation / Benchmarking / ObjectNav benchmark performance, Application / Robotics / Navigation tasks with human-like policies
License CC BY 4.0

Abstract Overview

IntentNav is a framework for ObjectNav that learns human-like search policies from human demonstrations rather than relying on low-level action imitation alone. The method converts low-level human trajectories into candidate-level supervision with Frontier-based Human-Intent Labeling, which infers which frontier best matches the demonstrator’s future search direction. It represents navigation decisions in a shared bird’s-eye-view candidate space that combines persistent spatial memory, candidate-specific egocentric visual memory, and agent-centric geometry. A vision-language model is then trained to select among grounded frontier or target candidates using an Intent-Aligned Objective designed to preserve directional consistency during exploration.

Novelty

The paper’s main novelty is a candidate-level spatial-visual imitation framework that infers high-level search intent from low-level human demonstrations through frontier evolution. It also introduces a unified BEV candidate interface that grounds both exploration frontiers and target commitments with paired visual memory and geometry, rather than predicting free-form coordinates or low-level actions.

Results

IntentNav reports state-of-the-art performance among learning-based methods on MP3D, HM3D-v1, and HM3D-v2 ObjectNav benchmarks, achieving 53.8/23.1 SR/SPL on MP3D, 70.5/34.6 on HM3D-v1, and 82.2/38.5 on HM3D-v2. Ablations indicate that candidate visual memory, agent-centric geometry, reserved candidate-ID selection, and the Intent-Aligned Objective each contribute to stronger performance and more directed search behavior. The same MP3D-trained checkpoint is also deployed zero-shot on wheeled, quadruped, and humanoid robots, with approximately 0.8 s per high-level policy inference.

Key Points

  1. Frontier-based Human-Intent Labeling turns low-level human demonstrations into candidate-level supervision by reasoning over future frontier evolution.
  2. IntentNav’s policy operates in a BEV candidate space that jointly uses spatial memory, candidate-aligned egocentric visual evidence, and explicit relative geometry.
  3. The method shows strong benchmark generalization and real-world transfer, with reported state-of-the-art learning-based results on three ObjectNav benchmarks and zero-shot deployment across multiple robot embodiments.

References

This page was created using generative AI such as GPT-5, Claude Opus 4, Gemini 3, Gemini 3.1 Flash Image, and their higher-end successor versions. No guarantee can be made regarding its contents.