GPT-6-Astra Lights Up Embodied Navigation: Evaluation in Zero-Shot Vision-and-Language Navigation in Continuous Environments
Technical report
We investigate whether GPT-6-Astra, a general-purpose foundation model, can navigate unfamiliar environments using its own perception, reasoning, and decision-making capabilities. Our evaluation focues on zero-shot vision-and-language navigation in continuous environments (VLN-CE) through a minimal interface in the Codex harness, aiming to unleash GPT-6-Astra's full potential for navigation. Using monocular RGB, GPT-6-Astra decides when to observe, how to move, and when to stop, without navigation-specific fine-tuning, a trained waypoint predictor, or a pre-built scene map. Our evaluation yields four main findings. First, GPT-6-Astra achieves strong zero-shot navigation performance using only monocular RGB observations. On the common-adopted zero-shot R2R-CE benchmark, ultra reasoning achieves a success rate of 79.0%, exceeding the strongest reported zero-shot and supervised success rates by 13.0 and 6.9 percentage points, respectively. Second, GPT-6-Astra advances multi-stage language instructions into coherent, adaptive navigation by grounding spatial relations, tracking task progress, and revising its actions. Third, reliable route execution and goal verification remain challenging, even with ultra reasoning. Plausible local landmark matches do not consistently lead to correct task completion. Fourth, these capabilities motivate rethinking the role of embodied learning. Future VLN research should build on foundation models to advance generalizable and reliable embodied intelligence.
你点赞过：TANGO: Humanoid Navigation in Cluttered Environments with a