Robot navigation finds wi-fi signal sources without maps
Visual-Wi-Fi Navigation to Signal-Emitting Devices
Robotics
Summary
Finding a small or hidden device indoors by sight alone can be very hard. The authors show how a robot can use Wi-Fi signals that devices send out during normal use, alongside its camera’s view, to find those devices even in unknown environments. Their system combines smart Wi-Fi signal detection while moving with visual clues to guide the robot to the device. They trained and tested this approach in a simulator with detailed Wi-Fi modeling and then successfully ran it on a real robot using a common Wi-Fi router as a sensor. This approach works without connecting to the device or changing the building’s network.
What this means in practice
- •For robot developers: Build robots that navigate indoors to find wi-fi emitting targets without pre-mapped environments or new infrastructure.
- •For industrial automation teams: Deploy robots to locate hidden or visually indistinct devices in warehouses or factories using combined wi-fi and visual inputs.
Authors
Lihao Wang, Tianjian Xu, Tianmin Shu, Renjie Zhao
Abstract
Indoor navigation to task-relevant targets remains difficult when the target is small, occluded, or visually indistinct. Meanwhile, smart appliances, mobile devices, and IoT tags emit Wi-Fi signals during everyday communication, providing a pervasive but underused spatial cue. We study visual-Wi-Fi navigation, where a robot reaches a signal-emitting device in an unmapped environment using onboard visual observations and Wi-Fi packets overheard from the device, without connecting to the device or modifying infrastructure. Realizing this requires pose-dependent Wi-Fi observations during closed-loop policy learning and reliable spatial cues from bearing measurements corrupted by indoor multipath propagation on a moving robot. We present WiFiSpaces, which extends the Habitat embodied simulator with online ray-traced Wi-Fi sensing, rendering Wi-Fi observations for a robot-mounted antenna array at continuous poses during policy rollouts. On top of it, we build ViFiNav, a localization-aware navigation framework: an online source-localization algorithm exploits robot motion to disambiguate and robustly aggregate bearings from multiple viewpoints into a confidence-aware source estimate, and a learned policy fuses this evolving estimate with depth observations and learns to act on it as it is refined. Experiments show that exploiting robot motion is key to accurate source estimates, and that fine-tuning on ray-traced Wi-Fi observations in WiFiSpaces improves the success rate of ViFiNav. The policy transfers zero-shot to unseen scene datasets, and we deploy it on a real robot with a Wi-Fi sensor built from a commodity router, without any real-world training.