Robot Technology News
ROBO SPACE
Giving robots a new way to see using radio signals
Freddy Liu, Haowen Lai and Mingmin Zhao, from left, setting up a robot equipped with PanoRadar for a test run.
Giving robots a new way to see using radio signals
by Clarence Oxford
Los Angeles CA (SPX) Nov 13, 2024

Robots face significant challenges in developing perception systems that function reliably in adverse weather and complex conditions. Conventional vision sensors, such as cameras and LiDAR, often struggle in environments with heavy smoke or fog, limiting their effectiveness.

Nature, however, shows that vision isn't limited to light. Bats use sound echoes for navigation, while sharks detect electric fields from their prey. Inspired by these natural adaptations, researchers have found that radio waves - with wavelengths much longer than light - offer capabilities beyond human sight, such as seeing through smoke, fog, and some solid objects.

Historically, robots have relied on cameras and LiDAR for high-resolution imaging or traditional radar for viewing through obstacles, though radar yields low-detail results. A team at the University of Pennsylvania's School of Engineering and Applied Science (Penn Engineering) has now developed PanoRadar, a new tool enabling robots to create detailed 3D maps using radio signals, enhancing their vision significantly.

"We wondered if we could integrate the robustness of radio signals with the high resolution provided by visual sensors," said Mingmin Zhao, Assistant Professor in Computer and Information Science.

In a paper set for presentation at the 2024 International Conference on Mobile Computing and Networking (MobiCom), Zhao and researchers from the Wireless, Audio, Vision, and Electronics for Sensing (WAVES) Lab and the PRECISE Center introduced PanoRadar. This system, developed with doctoral student Haowen Lai, graduate Gaoxiang Luo, and research assistant Yifei (Freddy) Liu, employs AI to help robots navigate difficult conditions such as smoke-filled interiors and foggy roads.

PanoRadar works similarly to a lighthouse, scanning the environment with a rotating array of antennas. These antennas emit radio waves and record reflections, which AI processes to build detailed, high-resolution images. Although the sensor costs significantly less than LiDAR systems, its method of collecting data from multiple angles boosts its resolution to a comparable level. "The breakthrough is in how we process radio wave measurements," Zhao explained. "Our algorithms extract rich 3D data from the surroundings."

A major challenge was maintaining high-resolution imaging as the robot moved. "Combining data from numerous positions with sub-millimeter precision was essential for LiDAR-level detail," said Lai, the paper's lead author. Motion errors had to be minimized to avoid compromising image quality.

Teaching PanoRadar to interpret its data was another key task. "Indoor spaces have patterns and structures we used to train our system," Luo noted. Initially, the AI cross-referenced LiDAR data to verify its accuracy, improving its capabilities over time.

Field tests demonstrated that PanoRadar excelled where conventional sensors struggled. "The system maintained precise tracking through smoke and even mapped areas with glass walls," Liu said. This is due to radio waves' resistance to being blocked by airborne particles and their ability to reflect off materials that confound LiDAR.

Future plans include integrating PanoRadar with other sensors like cameras and LiDAR for enhanced multi-sensor systems. The team will also test the system on different robotic and autonomous platforms. "Using multiple sensing methods is vital for complex tasks," Zhao said. "By combining them, we can create robots ready for real-world conditions."

Research Report:Enabling Visual Recognition at Radio Frequency

Related Links
University of Pennsylvania School of Engineering and Applied Science
All about the robots on Earth and beyond!

Subscribe Free To Our Daily Newsletters
Tweet

RELATED CONTENT
The following news reports may link to other Space Media Network websites.
ROBO SPACE
3D-printed rovers challenge students in Mars exploration training
Paris, France (SPX) Nov 07, 2024
University students participated in a hands-on ESA Academy training course at ESA's ESTEC technical center in the Netherlands last week, where they worked with 3D-printed rovers to develop autonomous navigation skills. Six teams were tasked with programming their rovers to detect and move towards a blue ball in a simulated Mars environment. The students were provided with ExoMy rovers, 3D-printed machines modeled after ESA's Rosalind Franklin rover. These devices featured six wheels, a camera, and ... read more

ROBO SPACE
Indian capital plans drone flights to combat smog crisis

U.S. Navy conducted live control flight demonstration of carrier-based UAVs

Taiwan students design drones for mock battle, as China threat looms

MARSS showcases advanced AI-driven CUAS system at Red Sands 2024

ROBO SPACE
Dating apps move to friend zone in search of profits

MIT engineers make converting CO2 into useful products more practical

Carbon recycling offers solution to plastic pollution

Startup turns mining waste into critical metals for the U.S.

ROBO SPACE
China's top chipmaker reports surge in profits

Nvidia surpasses Apple as world's biggest company

Nvidia asks S Korea SK hynix to pull forward chip deliveries

NRL Develops Innovative Method for Quantum Emitter Control

ROBO SPACE
Framatome and Nuclearelectrica partner to produce Lutetium-177 in Romania

Vietnam looks to restart nuclear power projects

US touts Trump-proof nuclear expansion plans at COP29

Nuclear energy gains importance in Europe's green energy plans

ROBO SPACE
Syrians, Iraqis archive IS jail crimes in virtual museum

U.S. military judge rules government plea deals with 9/11 suspects are 'enforceable contracts'

Poland alleges 'foreign agents' plotted using int'l parcel couriers to target transatlantic air traffic

American strikes killed up to 35 jihadists in Syria: US military

ROBO SPACE
Climate finance: who is being asked to pay what at COP29?

Bangladesh's Yunus seethes over climate cash fight; I.Coast to create $500 mn

Climate 'financing gap' is widening: ECB chief

Tax crypto and plastic to pay for climate, development, leaders urge

ROBO SPACE
Tackling the energy revolution, one sector at a time

NASA opens Power Systems essay contest for K12 students

In search of high-performance materials for fusion reactors

Texas A&M to train machine learning tools to design materials for fusion power plants

ROBO SPACE
Shenzhou 18 brings back samples for space habitability and materials research

Shenzhou 18 crew back in China after 6-month mission to Tiangong station

Chinese space station crew returns after six months in orbit

Shenzhou XIX Crew Joins Tiangong Space Station for Crew Rotation

Subscribe Free To Our Daily Newsletters




The content herein, unless otherwise known to be public domain, are Copyright 1995-2024 - Space Media Network. All websites are published in Australia and are solely subject to Australian law and governed by Fair Use principals for news reporting and research purposes. AFP, UPI and IANS news wire stories are copyright Agence France-Presse, United Press International and Indo-Asia News Service. ESA news reports are copyright European Space Agency. All NASA sourced material is public domain. Additional copyrights may apply in whole or part to other bona fide parties. All articles labeled "by Staff Writers" include reports supplied to Space Media Network by industry news wires, PR agencies, corporate press officers and the like. Such articles are individually curated and edited by Space Media Network staff on the basis of the report's information value to our industry and professional readership. Advertising does not imply endorsement, agreement or approval of any opinions, statements or information provided by Space Media Network on any Web page published or hosted by Space Media Network. General Data Protection Regulation (GDPR) Statement Our advertisers use various cookies and the like to deliver the best ad banner available at one time. All network advertising suppliers have GDPR policies (Legitimate Interest) that conform with EU regulations for data collection. By using our websites you consent to cookie based advertising. If you do not agree with this then you must stop using the websites from May 25, 2018. Privacy Statement. Additional information can be found here at About Us.