May 23 2022Reviewed by Alex Smith
Engineers from the University of California, San Diego, have created a low-cost, low-power device to assist robots in properly mapping their path indoors, even in low-light conditions and in the absence of identifiable landmarks or features.
Image credit: Proxima Studios/Shutterstock.com
Sensors that use WiFi signals to assist the robot make up the technology. It is an innovative method of indoor robot navigation. Optical light sensors, such as cameras and LiDARs, are used in the majority of systems.
The so-called “WiFi sensors,” sense radio frequency signals instead of light or visual cues, allowing them to operate in settings where cameras and LiDARs struggle, such as low light, shifting light, and repetitive environments like long corridors and warehouses.
The method might also provide a cost-effective alternative to expensive and power-hungry LiDARs, according to the researchers.
A group of researchers from UC San Diego’s Wireless Communication Sensing and Networking Group, led by electrical and computer engineering professor Dinesh Bharadia, will present their findings at the 2022 International Conference on Robotics and Automation (ICRA) that will be held in Philadelphia from May 23 to 27, 2022.
“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 localization and mapping with robots,” stated Bharadia.
Using WiFi, we have built a new kind of sensing modality that fills in the gaps left behind by today’s light-based sensors, and it can enable robots to navigate in scenarios where they currently cannot.
Aditya Arun, Study First Author and PhD Student, Department of Electrical and Computer Engineering, Bharadia’s Lab, University of California San Diego
The researchers used off-the-shelf gear to create their prototype system. The WiFi sensors, which are created using commercially available WiFi transceivers, are attached to a robot in the system. These devices broadcast and collect wireless signals to and from nearby WiFi access points. These WiFi sensors are unique in that they employ continual back-and-forth communication with WiFi access points to map the robot’s location and movement direction.
This two-way communication is already happening between mobile devices like your phone and WiFi access points all the time—it’s just not telling you where you are. Our technology piggybacks on that communication to do localization and mapping in an unknown environment.
Roshan Ayyalasomayajula, Study Co-Author and PhD Student, Department of Electrical and Computer Engineering, Bharadia’s Lab, University of California San Diego
This is how it goes. The WiFi sensors are initially uninformed of the robot’s location as well as the location of any WiFi access points in the area. It is like playing Marco Polo: the sensors call out to the entry points and listen for their responses as the robot progresses, utilizing them as landmarks.
The key is that each incoming and outgoing wireless signal has its distinct physical information—an angle of arrival as well as direct path length to (or from) an access point—that can be used to determine where the robot and access points are in respect to one another. The WiFi sensors can extract this data and do these computations thanks to algorithms created by Bharadia’s team.
The researchers put their technique to the test on a floor of a building. They set up many access points across the facility and outfitted a robot with WiFi sensors, as well as a camera and a LiDAR to take comparative measurements. The researchers programmed the robot to travel around the floor multiple times, turning corners, descending long corridors, and traveling through both bright and dimly illuminated areas.
In these experiments, the WiFi sensors’ accuracy of localization and mapping was comparable to that of commercial cameras and LiDAR sensors.
We can use WiFi signals, which are essentially free, to do robust and reliable sensing in visually challenging environments. WiFi sensing could potentially replace expensive LiDARs and complement other low cost sensors such as cameras in these scenarios.
Aditya Arun, Study First Author and PhD Student, Department of Electrical and Computer Engineering, Bharadia’s Lab, University of California San Diego
That is what the team is now investigating. To build a more comprehensive, yet affordable, mapping method, the researchers will combine WiFi sensors (which give accuracy and dependability) with cameras (which provide visual and contextual information about the area).
WiFi helps robots navigate indoors
UC San Diego engineers have developed a low-cost, low-power technology to help robots accurately map their way indoors, even in poor lighting and without recognizable landmarks or features. The technology uses WiFi signals, instead of light, to help the robot “see” where it’s going. Video Credit: UC San Diego Jacobs School of Engineering.
Journal Reference:
Arun, A., et al. (2022) P2SLAM: Bearing Based WiFi SLAM for Indoor Robots. IEEE Robotics and Automation Letters. doi.org/10.1109/LRA.2022.3144796.
Source: https://ucsd.edu/