Follow us on social

Latest Posts

Stay in Touch With Us

For Advertising, media partnerships, sponsorship, associations, and alliances, please connect to us below


+91 40 230 552 15

540/6, 3rd Floor, Geetanjali Towers,
KPHB-6, Hyderabad 500072

Follow us on social


  /  Latest News   /  A Technique that Allows Robots to Detect When Humans Need Help

A Technique that Allows Robots to Detect When Humans Need Help

Robots now help humans in need

As robots are presented in an expanding number of true settings, they should have the option to adequately help out human users. As well as speaking with people and helping them in regular tasks, it may subsequently be valuable for robots to independently decide if their assistance is required or not.

Researchers at Franklin and Marshall College have as of late been attempting to foster computational tools that could upgrade the exhibition of socially assistive robots, by permitting them to deal with expressive gestures given by people and react appropriately. In a paper pre-published on arXiv and introduced at the AI-HRI conference 2021 last week, they presented another method that permits robots to independently distinguish when it is proper for them to step in and help users.

“I am interested in designing robots that help people with everyday tasks, such as cooking dinner, learning math, or assembling Ikea furniture,” Jason R. Wilson, one of the researchers who carried out the study, told TechXplore. “I’m not looking to replace people that help with these tasks. Instead, I want robots to be able to supplement human assistance, especially in cases where we do not have enough people to help.”

Wilson trusts that when a robot assists people with finishing a given job, it ought to do as such in a ‘dignified’ manner. As such, he believes that robots ought to in a perfect world be touchy to their users’ humankind, regarding their dignity and independence.

There are multiple manners by which roboticists can think about the nobility and independence of clients in their plans. In their new work, Wilson and his students Phyo Thuta Aung and Isabelle Boucher explicitly centred around safeguarding a user’s independence.

“One way for a robot to support autonomy is to ensure that the robot finds a balance between helping too much and too little,”

“One way for a robot to help independence/autonomy is to guarantee that the robot tracks down a harmony between helping excessively and excessively little,” Wilson clarified. Wilson explained. “My prior work has looked at algorithms for adjusting the robot’s amount of assistance based on how much help the user needs. Our recent study focused on estimating how much help the user needs.”

At the point when people need assistance with a given task, they can expressly request help or pass on that they are battling in verifiable ways. For instance, they could offer remarks, for example, “well, I don’t know,” or communicate their disappointment through their looks or non-verbal communication. Other understood techniques utilized by people to impart that they need assistance include the utilization of their eye stare.

“For instance, an individual might check out the task they are dealing with, then, at that point, take a step backward at an individual that can help them and afterward glance back at the task,” Wilson said. “This gaze pattern, called confirmatory gaze, is utilized to demand that the other individual glance at what they are looking at, maybe on the grounds that they are uncertain in case it is right.”

The vital target of the new review did by Wilson, Aung and Boucher was to permit robots to naturally handle eye-gaze related prompts in helpful ways. The strategy they made can investigate various sorts of prompts, including a user’s speech and eye gaze patterns.

“The engineering we are developing naturally perceives the user’s speech and investigates it to decide whether they are communicating that they need or need assistance,” Wilson clarified. “Simultaneously, the framework likewise recognizes clients’ eye gaze patterns, deciding whether they are showing a gaze pattern related with requiring help.”

Interestingly, with different strategies to upgrade human-robot collaborations, the methodology doesn’t need information about the particular task that users are finishing. This implies that it very well may be effortlessly applied to robots working in different real-time settings and prepared to handle various tasks.

While the model made by Wilson and his partners can improve users encounters without the requirement for task-specific details, developers can in any case give these subtleties to upgrade its accuracy and performance. In initial tests, the structure accomplished highly promising outcomes, so it could before long be utilized to work on the presentation of both existing and recently created social robots.

“We are now continuing to explore what social cues would best allow a robot to determine when a user needs help and how much help they want,” Wilson said. “One important form of nonverbal communication that we are not using yet is emotional expression. More specifically, we are looking at analysing facial expressions to see when a user feels frustrated, bored, engaged or challenged.”