Article

NavGPT-3: Connecting Language Models' Long-Horizon Reasoning to Robots' Real-Time Actions

NavGPT-3 proposes a vision-language navigation system for continuous environments, in which Harness (context management), Runtime (permission control), and NavGPT VLA (local waypoint prediction) work together to resolve the tension between long-horizon planning and high-frequency execution.

This page provides a summary and source link only.