Robot Simulator [WBA Wiki(en)]

This page is read only. You can view the source, but not change it. Ask your administrator if you think this is wrong.
===== Robot Simulator =====
Robotic simulators can be used as virtual environment in which AGI systems are trained and evaluated.

This page describes desired specifications of the robotic simulator to be used around WBAI.
==== Simulation Environment ====
=== Simulator ===
Currently a prototype is being developed with [[http://pygazebo.readthedocs.org/|PyGazebo]].
=== Control environment ====
Robots are to be controlled with [[BriCA]] / [[http://www.goodai.com/#!brain-simulator/c81c|Brain Simulator]]<sup>TM</sup> from outside of the simulator.\\
Recommended controlling language is Python (as it is easy to use &  low in platform dependency).
=== Task environment ====
With regard to rodent-level intelligence, mazes for behavioral tests are to be implemented.\\
As for task environment for human-level intelligence, the simulation environment for RoboCup@Home will be considered.  Currently, their referential environment is implemented with [[http://www.sigverse.org/wiki/en/|SigVerse]].\\
If one is to contest in a Robocup league, s/he would have to use SigVerse.
However, as the simulator we use for our prototype is PyGazebo, we might propose them to use PyGazebo in future Robocup... 
==== Robot (Overview) ====
The body shape of a simulated robot may be:\\
  * Two-wheel turtle (good enough for rodent-level)
  * ‘Centurtle’: with a turtle-like lower body and humanoid upper body (as used in the Robocup@Home Simulation League)
  * Bipedal humanoid
It is desirable that a simulated robot has the following functions:\\
(See Input and Output below for detail.)\\
  * Visual perception
  * Reward (external-internal)
  * [Straight/Rotational] Acceleration and speed sensors
  * Audio perception (optional)
  * Locomotion
  * Manipulator (optional)
  * Text input and output (optional)
  * Emotional expression (optional)
  * Speech function (optional)
==== Input ====
It is desirable that a simulated robots has the following input functions.
  * Visual perception
    * Color perception\\ While animals do not always have color vision, for the engineering purpose, it is easier to process visual information with color.
    * Depth perception\\ While animals do not always have stereo vision, for the engineering purpose, it is easier to process visual information with depth.
  * Reward
    * External reward is given when, for example, the robot gets a specific item (bait).
    * Internal reward is given by internal logic when, for example, curiosity is satisfied.
  * Tactile perception (optional)
    * A manipulator (optional) requires it.
  * Acceleration sensor [Straight/Rotational] (optional)
  * Speed sensor [Straight/Rotational] (optional)\\ Not recommended as it is not biologically realistic.\\ It is rather recommended to estimate the speed from vision.\\ The method for [[https://en.wikipedia.org/wiki/Odometry|odometry]] is to be determined.
  * Audio perception (optional)\\ Required when the task requires audio-based language processing.\\ (See **Auditory information processing** below)
  * Text input (optional)
==== Output ====
It is desirable that a simulated robots has the following output functions.
  * Locomotion
Default: L/R bi-wheel
Challenger’s option: N-pedal walker
  * Manipulator (optional)
As a minimal way for object manipulation, a robot can move exterior objects by pushing them with its own body.
  * Vocalization (optional)
One of the following:
    * Text-to-speech (parser and word-phonetic dictionary)
    * Phoneme vocalizer (Phoneme sets are language dependent.)
    * General-purpose sound synthesizer
  * Text output (optional)
  * Emotional expression (optional)\\ Robot with social interaction may require it.
==== Perception API ====
While perceptual information processing may be implemented with machine learning algorithms, when it is not the main subject of research, it would be easier to use off-the-shelf libraries.  With the simulator, some information may be obtained ‘by cheating’ directly from the simulation environment.\\
APIs are to be wrapped for access from BriCA / BrainSimulatorTM.
  * Visual information processing
The following are served:
    * Deep Learning APIs for visual information processing
    * Image processing API such as OpenCV / SimpleCV
And the following may be served:
    * Object detection API
(with depth info.)
    * Border Ownership / Figure Ground Separation API
Apparent size, relative direction, distance, relative velocity, etc.
  * Face detection API (optional)
  * Human skeletal mapping API (as seen in Kinect) (optional)
  * Facial expression recognition API (adapted to the facial expression of robots) (optional)
  * Auditory information processing (optional)
    * Sound and speech recognition API\\ Function such as seen in Julius / HARK