In 2010, Rajinikanth-starrer Enthiran gave us a glimpse into the life of ‘Chitti’, an artificial intelligence (AI)-powered humanoid robot that can fight, clean and cook food but doesn’t eat or drink. Eating was not programmed.
By 2022, robot chefs are real, taking on ‘Chitti’. Researchers at Cambridge University’s Bio-Inspired Robotics Laboratory said on Wednesday that their robot chef can assess how salty a dish is at different stages of the chewing process, just as we humans do. The researchers worked closely with home appliance maker Beko to achieve this goal.
For humans, the sense of taste has evolved over millions of years and remains very subjective – some may prefer salty preparations, some spicy, and others less spicy, but a robot chef may prefer something so subjective as taste. How do you understand the complexities?
The researchers acknowledge that preparing and cooking food is a challenge “since it will have to deal with complex problems in robotic manipulation, computer vision, sensing and human-robot interactions in order to consistently produce end products. Robot chefs taste taste,” he said. The human processes of chewing and tasting. “When we taste, the process of chewing also provides a continuous response to our brains,” said co-author Arsene Abdulali, from the university’s Department of Engineering. that current methods of electronic testing are inadequate because they are time-consuming and take a single reading from a homogeneous sample.
In June 2020, researchers from the same university used machine learning to train a robot to understand the subjectivity of taste from the taste of an omelet. This time, the researchers attached a conduction probe with a salinity sensor to a robotic arm (conductivity is the movement of ions. Therefore, salinity increases with ion concentration, ion mobility, and ionic charge). He prepared scrambled eggs and tomatoes but added different amounts of salt and tomatoes to each dish. The robot was able to “taste” the preparations using the probe.
To reflect changes in texture due to limited chewing, unlike humans who constantly chew for flavor, the team put the egg mixture into a blender and the robot tested the dish again. Different readings at different points of ‘chewing’ produced taste maps for each dish. According to the researchers, the results showed a “significant improvement” in the robot’s ability to assess salt over other electronic tasting methods.
Similarly, according to a July 5, 2019 blog by Patrick Ruch, a member of IBM Research staff, IBM Research was developing HyperTest—an AI-assisted tongue—for the way men taste things. The idea was to cater to a range of industrial and scientific users who need to rapidly and reliably identify liquids without access to high-end laboratories. The ‘hypertest’ uses electrochemical sensors that involve pairs of electrodes covered with a polymer coating that emit voltage signals—the combined voltage signals of all pairs of electrodes represent the fingerprint of the liquid. Key to the functioning of the electrochemical sensor are the polymer coatings covering each electrode. Robot chefs have been in existence for almost a decade but are now gaining traction in India as Indians love to eat fresh food.
But robot chefs aren’t cheap—home versions debut 50,000, and the commercial model costs . can happen till 45 lakhs. For example, the smart robot from Bengaluru-based Euphotic Labs can cook a variety of simple Indian dishes like nosh, upma, poha, halwa, pasta, khichdi and fried rice. Users just have to feed the ingredients into individual compartments and select the dish from its mobile app which offers over 200 recipes.
Nosh uses a “recipe engine” to decide how to cook a food item or ingredient in a specific way. It also uses a vision algorithm that monitors the food as it cooks and, just like humans, takes the next steps in the cooking process accordingly. Doing. The first prototype for the Nosh was developed in 2018, and a commercially-ready model will be launched during Diwali this year. Nosh is compact in design and can be deployed at home.
Yatin Varachia, co-founder and product head of Euphotic Labs, which made Nosh, explains that “Nosh has the intelligence to detect whether the intermediate stage of cooking is done exactly according to recipes, i.e. the onion has turned golden brown or is translucent. Oil released from curry, rava turned brown, etc.” According to him, “Till now 500+ people have tasted the food and rated the food taste 4.4+ on average. Also, we have 650+ pre-orders and a long waiting list for people who want to spend their lives. I want the product.The pre-order cost was 40,000. Now, the price for India will be 49,999, and will be about US$999. We are not taking pre-orders right now.”
Another Chennai-based startup called Robochef has developed a robotic cooking machine with in-built Internet of Things (IoT) sensors. It’s huge and has a restaurant and cloud kitchen. Its commercial variant has a capacity of 37 liters and can cook 100 servings at a time. Created by Chennai-based engineer Saravanan Sundaramurthy, RoboChef is programmed to clean and chop vegetables, grind spices and cook using the right proportions.
Some robots have been developed with specific fast-food items in mind. That said, all these robo chefs have yet to develop taste buds. The Robot Chef from the University of Cambridge has promised to address this issue as well.