Using Wi-Fi everyday to help robots better see and navigate indoors

Engineers at the University of California, San Diego have developed low-cost, low-power technology to help robots accurately map their way indoors, even in low-light conditions without landmarks or recognizable characteristics.

The technology consists of sensors that use WiFi signals to help the robot map where it is going. It’s a new approach to indoor robot navigation. Most systems rely on optical light sensors such as cameras and LiDARs. In this case, the so-called “WiFi sensors” use radio frequency signals rather than light or visual signals to see, so they can work in conditions where cameras and LiDARs struggle – in environments with low light, changing light and repetitive such as long hallways and warehouses.

And by using WiFi, the technology could offer a cost-effective alternative to expensive and power-hungry LiDARs, the researchers noted.

A team of researchers from the Wireless Communication Sensing and Networking Group, led by UC San Diego Electrical and Computer Engineering Professor Dinesh Bharadia, will present their work at the International Conference on Robotics and Automation (ICRA) 2022 , which will take place from May 23. at 27 in Philadelphia.

“We are surrounded by wireless signals almost everywhere we go. The beauty of this work is that we can use these everyday signals to do indoor location and mapping with robots,” Bharadia said.

“Using WiFi, we’ve built a new kind of sensing modality that fills the gaps left by today’s light-based sensors, and it can allow robots to navigate scenarios they can’t. not currently,” added Aditya Arun, who is an electrician. and Ph.D. in Computer Engineering. student in Bharadia’s lab and first author of the study.

The researchers built their prototype system using off-the-shelf hardware. The system consists of a robot that has been fitted with WiFi sensors, which are built from commercially available WiFi transceivers. These devices transmit and receive wireless signals to and from WiFi access points in the environment. What makes these WiFi sensors unique is that they use this constant communication with WiFi access points to map the robot’s location and direction of movement.

“This two-way communication already happens all the time between mobile devices like your phone and WiFi hotspots – it just doesn’t tell you where you are,” said Roshan Ayyalasomayajula, who also has a Ph.D. in electrical and computer engineering. student in Bharadia’s lab and co-author of the study. “Our technology relies on this communication to perform localization and mapping in an unfamiliar environment.”

This is how it works. At first, WiFi sensors do not know the location of the robot or the location of WiFi access points in the environment. Understanding this is like playing a game of Marco Polo – as the robot moves, the sensors call the access points and listen to their responses, using them as landmarks. The key here is that each incoming and outgoing wireless signal carries its own unique physical information – an angle of arrival and direct path length to (or from) an access point – which can be used to determine where the robot and the access points are related to each other. Algorithms developed by the Bharadia team allow WiFi sensors to extract this information and perform these calculations. As the call and response continues, the sensors collect more information and can accurately locate the direction of the robot.

The researchers tested their technology on one floor of an office building. They placed several access points around the space and equipped a robot with the WiFi sensors, as well as a camera and LiDAR to perform measurements for comparison. The team controlled their robot to move around the floor multiple times, taking turns, going down long, narrow hallways, and through bright and dimly lit spaces.

In these tests, the location and mapping accuracy provided by the WiFi sensors was comparable to that of the commercial camera and LiDAR sensors.

“We can use WiFi signals, which are essentially free, to perform robust and reliable sensing in visually challenging environments,” Arun said. “Wi-Fi sensing could potentially replace expensive LiDARs and complement other low-cost sensors such as cameras in these scenarios.”

This is what the team is currently exploring. Researchers will combine Wi-Fi sensors (which provide accuracy and reliability) with cameras (which provide visual and contextual information about the environment) to develop more comprehensive, yet inexpensive, mapping technology.

Comments are closed.