Wiki source code of AI and ICT
Version 3.1 by Vladimir Rullens on 2025/09/16 14:31
Show last authors
| author | version | line-number | content |
|---|---|---|---|
| 1 | //<Describe the additional Artificial Intelligence (AI) and Information & Communication Technology (ICT) that may be included in your prototype, e.g. to generate personal music play lists, picture collections, or narratives (e.g. LLMs).>// | ||
| 2 | |||
| 3 | |||
| 4 | //Our robot is expected to communicate with its patients during the pill delivery process, ideally in a way that is tailored to its patients. Ideally, its responses are not static, so it feels more human. For this, an LLM is ideal.// The LLM will keep in mind the following: | ||
| 5 | |||
| 6 | - The patient it is talking to -> For this it needs an understanding of its current location, which is handled by the **robot **itself. | ||
| 7 | |||
| 8 | - The pills the patient needs, or the method of dispense -> For this, the **LLM** should be able to activate the dispenser using a command given in text (i.e. //<Dispense A 1>)//. This text should not be spoken out loud. | ||
| 9 | |||
| 10 | - The dispenser -> Ideally, the robot links up to it through **Bluetooth** or **USB**. Whenever it executes the command, the dispenser gives the corresponding pills. (For the sake of the experiment, it might be better if it simply does a short dance or some other signal) | ||
| 11 | |||
| 12 | - Due to the above, a separate **Text-to-speech** program should be involved, which states the spoken text without the included dispense command. | ||
| 13 | |||
| 14 | - A general idea of the patient's personality -> For this, it needs experience with the patient. Prior knowledge given by caregivers could also be useful. |