Selene Baez Santamaria
Selene Baez Santamaria
Currently running on - [x] Windows 10 ("Pepper laptop"), local backend - [x] Windows 10 ("Pepper laptop"), pepper naoqi backend - [x] Mac OS, local backend - [x] Mac OS,...
See [the specifications](https://docs.google.com/spreadsheets/d/1TrRes-WEILkoEi_m1qJZ3n3pPk4ZbIdUKs6cqd9vVZ0/edit?usp=sharing) of the data to be stored per experiments: - [ ] Image https://cltl.github.io/pepper/build/html/pepper.framework.component.camera.html#pepper.framework.component.camera.CameraComponent.on_image - [ ] Audio https://cltl.github.io/pepper/build/html/pepper.framework.component.microphone.html#pepper.framework.component.microphone.MicrophoneComponent.on_audio - [ ] STT https://cltl.github.io/pepper/build/html/pepper.framework.component.speech_recognition.html#pepper.framework.component.speech_recognition.SpeechRecognitionComponent.on_transcript - [ ] Object...
Use pose recognition from: - https://github.com/tensorflow/tfjs-models/tree/master/posenet - https://github.com/deephdc/posenet-tf Available as pre-trained model: https://github.com/tensorflow/tfjs-models/tree/master/posenet#loading-a-pre-trained-posenet-model Available as Docker: https://github.com/deephdc/posenet-tf#docker-installation
Copy of #10 Our current Data Model is entity-centric, but this must be changed to be event-centric. For this we should use SEM
Since this project is becoming very big and complex, we would like to break it up into smaller services that can be managed in an easier way. The idea is...
Use scene classification from: https://github.com/IBM/MAX-Scene-Classifier Available as Docker
- [ ] Query for - [ ] - [ ] hunger for knowledge / exploration - [ ] broad: entity that I do not know much about - [...
Formal modelling of hyponomy as Python objects. These should work at the ontology level, including any learning the robot has acquired through conversation or linked data. For expanding the ontology,...
- [ ] This is a dog, not a cat: change object type and label to cat (give utterance, since we have context info there) - [ ] Add functionality...
Create extra backend to work with a NAO robot. Robust against functionality available in Pepper but not for Nao (e.g tablet)