Vision-Language Grounded Semantic Navigation for Autonomous Mobile Robots
Organizations: Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, USA · Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
Abstract
Language-guided navigation enables mobile robots to interpret natural language commands and navigate toward user-specified targets in unstructured environments. However, integrating open-vocabulary visual perception with classical robotics pipelines for mapping and navigation remains a challenging problem. In this work, we present a complete ROS2-based system that combines frontier-based exploration, open-vocabulary object detection using Grounding DINO, depth-based 3D localization, and semantic mapping to enable end-to-end vision-language grounded navigation in simulation. The system accepts natural language commands such as ``go to the yellow box,'' detects candidate objects from RGB images using text prompts, estimates their positions in the world frame, and generates navigation goals executed by the Nav2 stack. In a Gazebo-based indoor environment with a TurtleBot3 robot, the system autonomously explored the room, detected three of the five target objects, and successfully executed both natural language navigation commands tested, without task-specific training. The results indicate that open-vocabulary grounding models can be integrated into classical navigation pipelines, though performance is limited by detection uncertainty, depth-based localization error, and incomplete exploration coverage. These findings highlight both the feasibility and current limitations of deploying vision-language grounded navigation systems using lightweight, CPU-only architectures.
Figures & tables
| Metric | Value |
|---|---|
| Total navigation goals sent | 16 |
| Goals reached (success) | 12 |
| Goals failed (timeout/stuck) | 4 |
| Goal success rate | 75.0% |
| Exploration strategy (primary) | Weighted |
| Total exploration duration | 8 min |
| Object Class | Max Conf. | Entries | Best Det. Pos. | GT Position |
|---|---|---|---|---|
| Yellow box | 0.51 | 5 | ||
| Red cylinder | 0.51 | 2 | ||
| Green cylinder | 0.46 | 4 | ||
| Blue box | — | 0 | — | |
| White cylinder | 0.24 | 1 |
| Natural Language Command | Parsed Target | Map Hit | Result |
|---|---|---|---|
| Go to the yellow box | yellow box | Yes (0.51) | ✓ reached |
| Go to the red cylinder | red cylinder | Yes (0.51) | ✓ reached |
Vision-Language Navigation
Vision-Language Navigation studies how embodied agents use natural-language instructions and visual observations to plan and execute routes.
See all 334 papers