How do robots know that a person has been well-fed? The setting is set in the near future where helper robots have become commonplace and are often assigned to help around households, hospitals, retirement homes and animal shelters. Despite the advancements in AI and robotics these machines aren't sentient and operate purely on a set of rules and guidelines. For a lack of a better word, they lack 'common sense'. A robot tasked with making meals and feeding a person won't distinguish between a well-fed and a starving person unless it was designed to do so. Considering the 5 basic human needs (food, water, air, and shelter), the ability to tell a person's nutritional status should be there by default.

The frame challenge for this particular question is that the average robot lacks the specialized medical equipment to make these quick assessments. Short of pricking everyone's hand every few hours, the robots have no way to tell what's going on inside the person. Not only would equipping every single household robot with blood monitors be prohibitively expensive but it would also add an additional fear factor to the already stigmatised robots (fear of needles + fear of robots). Robots need to evoke a sense of well-being, so a method of scanning a human without them knowing would be ideal.

Common examples of when this would be useful: What if that person has just eaten a meal but gets a sudden drop or spike in blood sugar? What if a human has a case of malabsorption due to an inflamed gut? What if their owner is anorectic and is only pretending to eat? What if a kid hasn't eaten their greens in a while?

Basically this would prevent humans from lying to the robots. "Oh! I'm sorry, I haven't eaten anything today" the human would say and the robot would retort with "my sensors indicate that you've been snacking again, Samantha".

Ideally the robots would make use of their already existing senses to evaluate a human's health. Those senses would include sight, hearing, touch as well as infrared and electromagnetism.

  • $\begingroup$ This seems to be about a third-party property, off-topic here. $\endgroup$ Commented May 23, 2023 at 21:33
  • $\begingroup$ How can a robot tell whether a person is alive? How can a robot tell whether a car needs oil? How can a non-car robot tell whether something is a car? How can a grey metal robot tell whether something is blue or yellow? $\endgroup$ Commented May 23, 2023 at 21:43
  • 1
    $\begingroup$ @JBH I’ll make an edit right away! $\endgroup$ Commented May 23, 2023 at 21:50
  • 1
    $\begingroup$ Voting to keep open. I believe JBH has made a quite good point on meta, be it for this "3rd-party sugarcoated" version or the first one. The facts you give the robots' default senses and that unlike Asimov's whole storyline your story is limited to the near-future indicates that you're building something, not asking how it is working in Asimov's world. $\endgroup$ Commented May 24, 2023 at 21:33
  • 1
    $\begingroup$ @Cadence Have you used a GPS repeating every 3s that you need to turn left at the crossroad? That's kinda the same issue : If the robot keeps asking (even only once a day), it will get annoying quickly. That's a strong part of the user experience which gives (or nullify) the robot its value. Also, there are anorexic people who will deliberately lie, and diabetic ones and others who need accurate treatment. People are not very reliable at honestly and precisely telling their health or feelings. $\endgroup$ Commented May 25, 2023 at 15:53

5 Answers 5


1: Sight.

Okay, I don't know the exact method your robot uses, but presumably there will be some form of visual sensor - whether it uses electromagnetic (like our eyes) or a sonar type system - the point is - We can look at people and within a pretty good range tell if they are under or overweight. There's nothing to stop our Robot doing the same. Additionally a Robot that has been programmed with or has calculated the exact height of the person, would be able to use their sense to determine a pretty accurate assessment of a persons measurements around the waist, arms etc. to determine if they were gaining or loosing weight

2: Inventory tracking.

Look in fridge/pantry - see what has been used (or not used) - pretty simple. Also looking in the Rubbish to see what has been thrown out or thrown away. This is something where a Robot (with perfect memory/tracking ability) would excel at.

3: Non-intrusive measurements.

Bathroom scales, observations around movement/mobility, observations around clothing and fitting etc. etc.

These are all things that a robot (with a perfect ability to calculate distance/measurement) would excel at doing and then be able to track over time.


4: Behavioral changes.

The Hangry is real. People get irritable when they are hungry, they get lethargic when they have eaten too much. There's no reason why a Robot could use a baseline emotional response (in combination with other observable data) to infer that someone is hungry and needs to eat.

5: Time.

Robots are able to keep perfect time, they aren't subject to getting engrossed in a task so completely that they forget to eat - and so a Robot would be able to say 'it's been 4.3 hours since your last nutritional intact. Previous data suggests that without intake, you will become emotionally compromised in 23 minutes'.

This would give a Robot enough data to reasonably care for a human in all but certain areas (where there is deliberate deception or a condition that requires an invasive test - like Diabetes).

  • $\begingroup$ Maybe an extremely sensitive gravitometer? $\endgroup$
    – user86462
    Commented May 25, 2023 at 6:24
  • $\begingroup$ 4. They have a Ph.D in psychology with a google hours of AI training behind it; they can tell you what your parents had for dinner the night before. $\endgroup$
    – Mazura
    Commented Jun 4, 2023 at 19:14

They sync with your wearable fitness device

Wearable fitness devices lcan already monitor enough metabolic health factors to be able to tell if a person is eating enough. You would just Bluetooth your WFD to your android (robot) the way that people today sync them up with their android (phones).

In this way the Robot does not need any sort of special hardware or software to figure out how healthy a human is, because they can simply "look it up".


Smart toilets

What goes in, comes out.

Your "Mr Crapper" (tm) smart toilet wireless links to network and tells your bot about your health status.

It's already happening

Smart Toilet

Plan B is smell.

Dogs can be trained to alert to many different types of medical issues by smell. A bot could be fitted with a olfactory sensor to remotely detect your health status

Also already happening

Electronic noses


They touch you

They have infrared sensors and such built into their hands that let them scan blood flow and detect signs of poor health.

This means that the humans won't feel it's a super invasive scan- they can avoid it by avoiding the robot- and by resting their hand on your forehead for a few seconds or shaking your hand they can tell if you're healthy.


Built into the system

No one wants a system that will feed them without reference to their needs, age, size, and activity.

First, they would be told the humans' ages, and any medical information needed. They would probably have access to activity monitors that humans carry to keep track of how much exercise they are getting.

Second, they would load any modules to evaluate known health problems and risks, customized to each human. This may include not only such signs as can be viewed by human sight but also infrared and other such detectors.

Third, humans would customize them to the level of nanny oversight they want. If a human wants the robot to help with the diet, the robot will have to be given a monitoring device.


You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .