Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation

Key points

The Pixel-to-3D Action Formulation lets the VLM operate through familiar 2D visual prompts, avoiding the spatial hallucinations and poor sample efficiency associated with learning 3D geometric transformations.
Selective reasoning activates only at critical nodes and compresses the remaining trajectories into space-time indicators, reducing both reasoning latency and memory overflow.
Two-level GRPO combines global outcome rewards with fine-grained process rewards to provide dense supervision and teach the model when to trigger reasoning based on the current state.
On R2R-CE, it achieved state-of-the-art performance with a 66.2% success rate while requiring only 90,000 training trajectories.
When deployed on a physical robot without additional tuning, it achieved a 60.0% success rate, outperforming StreamVLN at 49.0% and DualVLN at 53.0%.

External research summaries. These are not HDATF publications or measured product results.