Robots Keep Spotless Score

Researchers from Singapore have designed a sensor for autonomous cleaning robots making them better cleaners.

AsianScientist (Mar. 1, 2022) – Autonomous robots are already helping keep homes and public spaces squeaky clean in some parts of Asia. To take their cleaning abilities a notch above, researchers at the Singapore University of Technology and Design (SUTD) have developed a sensor system that helps the robots detect dirt efficiently and prioritize dirtier areas over the less dirty ones. The invention was reported in Sensors.

The development of automated machines and robots has greatly benefited housekeeping tasks. The old vacuum cleaners are being replaced by disc-shaped cleaning robots that navigate floor layouts and run over carpets all on their own. While such robots can easily keep home floors pristine, large public spaces like airports pose a different challenge altogether with uneven surfaces and differences in the levels of cleanliness in the entire area.

Moreover, people typically evaluate cleanliness by looking at or touching a surface and checking for visible dust particles but there is no set standard for determining how clean is clean.

To address this, SUTD researchers designed a novel sensor system and computing framework that would enable autonomous robots to assess cleanliness systematically and efficiently. Supported by Singapore’s National Robotics Program, their work takes inspiration from the manual touch-and-inspect method and measures the dirt score per area covered.

The sensor presses a clear adhesive tape onto a surface and compares the cleanliness of the tape before and after pressing. It then assigns a benchmark score, with 0 as the dirtiest and 100 as the cleanest relative to the initial appearance of the tape, and then cleans the area.

However, some areas are dirtier than others. Having the robot check every nook and cranny would therefore render the method highly inefficient. So, the researchers also developed a dirt-probability algorithm combined with a frontier exploration algorithm to improve navigation and cleaning.

This would prompt the robot to seek out unexplored surfaces and maximize its coverage. At the same time, it can identify the areas that are more likely to be dirty based on various indicators such as changes in the floor’s visual patterns. The robot then moves toward the dirty regions and prioritizes cleaning those areas.

While the strategy presents a novel way to tackle the age-old problem of cleaning, the team also recognized the limitations of their current system. For example, semi-outdoor areas had lower scores than indoor equivalents as the coarse surfaces prevented some dirt particles from sticking to the tape. False detections were also observed upon moving between different floor textures. The tests highlighted the need for further research and improvement of these cleaning audit robots.

“In the future, we are looking to comprehensively audit the quality of cleaning, taking into account not just the visual and tactile aspects, but also the olfactory aspects and microbial density,” said SUTD Assistant Professor Mohan Rajesh Elara.

The article can be found at: Pathmakumar et al. (2021) An Autonomous Robot-Aided Auditing Scheme for Floor Cleaning.


Source: Singapore University of Technology and Design; Photo: Shutterstock.
Disclaimer: This article does not necessarily reflect the views of AsianScientist or its staff.

Asian Scientist Magazine is an award-winning science and technology magazine that highlights R&D news stories from Asia to a global audience. The magazine is published by Singapore-headquartered Wildtype Media Group.

Related Stories from Asian Scientist