Sim-to-Real Room-Mediated Object-Goal Navigation with ROS 2 and Nav2
Organizations: Robotics Institute, Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia
Abstract
Although object-goal navigation (ObjectNav) approaches are usually evaluated in simulation, which offers scale and repeatable environments, real-world deployments are rarely examined beyond feasibility demonstrations. This paper presents the deployment of Room-Mediated Co-occurrence, an ObjectNav policy that reasons over Room Probability Vectors (RPVs), on two robotic platforms (Boston Dynamics Spot and Clearpath Robotics TurtleBot 4) through a robot-agnostic ROS 2 bridge. We study how these semantic priors generalise to physical environments and describe the adaptations required to transfer RPV from simulation to hardware, covering sensing, localisation, and the action interface. Across 66 trials on Spot, searching for 11 object categories from two starting positions in a university postgraduate research facility, RPV achieves a raw Success Rate (SR) of 0.455. Our analysis identifies undetected glass walls, entry into off-limits areas, limited usable depth range, target size, and mismatch between the room lexicon and physical layout as plausible contributors to the 8.4 percentage-point gap between the real-world SR and the reported simulated SR of 0.539. Code is available at https://github.com/Matthew-K-Chua/rpv-ros2-bridge.
Figures & tables
| Component | Simulation (Habitat) | Physical (Spot) |
|---|---|---|
| Room lexicon | 9 household rooms | 9 experiment-specific labels |
| Stage 1: Mask2Former masking | On | Off |
| Stage 2: YOLOE confidence | ||
| Stage 3: SAM 3 confidence | ||
| Perception cadence (explore) | Every 3rd step | Every step |
| Propagation limits | None | Truncated at and 6 m geodesic |
| Size | Target | SR | Detect ( ) | Stop ( ) | ||
|---|---|---|---|---|---|---|
| Large | Cabinet | 3 | 2 | 0.83 | 14.4 | 37.2 |
| Fridge | 3 | 2 | 0.83 | 40.6 | 93.6 | |
| Garbage bin | 3 | 0 | 0.50 | 3.0 | 78.3 | |
| Printer | 3 | 2 | 0.83 | 16.6 | 110.4 | |
| Medium | Backpack | 2 | 0 | 0.33 | 70.0 | 291.0 |
| Desktop monitor | 2 | 3 | 0.83 | 3.2 | 35.4 |
Object-Goal Navigation
Object-goal navigation studies how robots find and approach requested objects in unfamiliar environments using visual, spatial, and language cues.
See all 93 papers