MORSE - The Modular OpenRobots Simulation Engine

MORSE video for the 1.0 release, in Feb. 2013
Lasts 1'42"
MORSE based on the open-source projects Blender, Bullet and Python
Blender primary a 3D modeller, provides a 3D game engine (with support of shaders)
BGE: written in C++, extensible in Python + logic bricks
Bullet integrated in BGE, state-of-the art open-source library
support for rigid bodies and soft bodies simulation
It has a human avator which you can control like in 3D computer games for HRI

Presentation outline

The MORSE project
Simulating with MORSE
MORSE Principles
- Components
- Inner loop
- Interfaces
- Serialization/Deserialization
Human-Robot Interaction
Distributed simulations
Still missing...

Structure of the talk as follows:
First generally introduce the MORSE project and give a little example of it use,
... then Pierrick will show you some more details and talk about HRI and distributed simulations.

The MORSE community

Academic project, baked by academics
Initiated at LAAS-CNRS in 2009
As of Apr. 2013, contributions by 12 institutions worldwide

MORSE evolved out of academics and was started in 2009 by LAAS CNRS in Toulouse...
... and as for now includes ...

MORSE specific features

Adjustable degree of realism
Human avatar for HRI scenarios
Completely scriptable via Python
Blender for modeling
Bullet physics engine
Middleware independence
Distributed multi-node simulation

ROS users know Gazebo, and while Gazebo is a great simulator, there are also good reasons to take a closer look at MORSE!
Explain why I use MORSE: Human component, High-level sensors make it easy to test high-level resoning algorithms whithout dealing too much with low-level components (perception etc.)
High-level sensors: If you don't want to deal with navigation, use waypoint actuator, if you want to skip perception, use semantic camera
+ other avantages

What if...

...we want to simulate a PR2 mapping a kitchen environment?

To show how easy it is to set up a scenario to perform 2D Mapping with standard ROS components, I want to demonstrate a bit the MORSE workflow by giving you an example of the steps you have to take on the MORSE side...

$ morse create pr2_kitchen

This example requires latest git version of MORSE

First choose a name for your scenario and create it. MORSE takes care about the rest and creates the needed files and folders...

$ vim pr2_kitchen/defaults.py

from morse.builder import *

robot = BasePR2() # Bare PR2 model
robot.add_default_interface('ros') # control PR2 via ROS

odometry = Odometry() # Sensor for Odometry information
odometry.add_interface('ros', topic="/odom")
robot.append(odometry)

keyboard = Keyboard() # Keyboard control
robot.append(keyboard)

scan = Hokuyo() # Hokuyo 2D laser scanner
scan.translate(x=0.275, z=0.252)
scan.add_interface('ros', topic='/scan')
robot.append(scan)

env = Environment("kitchen.blend") # load custom 3d model

In the auomatically generated defaults.py file, we can define our simulation scenario...
In the first 2 lines: PR2 + ROS
Odemetry sensor + keyboard control (mention PR2_keyboard_teleop)
Custom 3 model of the env (in this case blender, but 3D Studio etc. also possbile via Blender import)

$ morse run pr2_kitchen

Using standard ROS amcl localization

Having built the map, we can also use AMCL for localization...

Navigation using move_base and AMCL localization

[...]	
motion = MotionXYW() # Motion controller
motion.add_interface('ros', topic='/cmd_vel')
robot.append(motion)
[...]

MORSE Principles: Components

MORSE simulations are made of components
Base components are sensors, actuators and robots
They can be linked to interfaces, modifiers and overlays
They are defined by a mandatory Python description
They optionally come with a (Blender) 3D mesh

MORSE components specify those classes respectively
I'll speak about interfaces later (in 3 slides)
Python description: refered as Builder class in the documentation
Blender allows to import most 3D file-format

MORSE Principles: Inner loop

2 interactions modalities: datastreams and services,
datastreams: published by MORSE for sensors, read for actuators,
strong decoupling: components are not aware of surrounding interfaces/modifiers,
modifiers alter the sensors/actuators data, typically to add noise,
components' local data are exported/imported by external interfaces like sockets or ROS
services: RPC-style interaction, can be synchronous or asynchronous

- main_loop.svg

MORSE Principles: Interfaces

Generic: sockets, text,
Specific to robotics: middlewares
- GenoM/pocolibs
- OpenRTM
- MOOS
Mapping to interaction semantics: RPC-oriented or datastream-oriented
Language bindings available for Python. Easy to develop for other languages through the socket interface.
Simulation introspection possible through sockets interface

ROS: well, you know... // YARP: Yet Another Robot Platform
GenoM/pocolibs: Generator of Modules and its communication layer, developed at LAAS
OpenRTM: Open source Robotic Technology Middleware, developed by Japan's National Institute of Advanced Industrial Science and Technology
MOOS: Mission Oriented Software Suite, developed at Oxford University
MORSE is middleware independant ! (bindings are modules)

MORSE Principles: Serialization/Deserialization

Generally speaking, each pair (component, interface) requires specific serialization/deserialization
Practically, many cases are automated (eg, JSON on sockets)
Specific marshalling functions can be provided to MORSE.

Human-Robot interaction

Human avatar, that can be controlled from the keyboard or RGB-D skeleton tracker
Simulated object recognition using MORSE "semantic camera" and ROS TF
Visibility of objects given by the semantic cameras (human block the view)
interactive environment, coded with Blender BGE logic bricks

MORSE Workshop 2013

June 6/7, 2013, Europe (Leuven, TBC)
~30 people
Tutorial track to get you started
Design meeting, discussions
Bug hunting party
Introduction to development with MORSE
Register now: morse.openrobots.org

Introducing MORSE

Presentation outline

The MORSE project

The MORSE community

The MORSE community

MORSE specific features

What if...

...we want to simulate a PR2 mapping a kitchen environment?

$ morse create pr2_kitchen

$ vim pr2_kitchen/defaults.py

$ morse run pr2_kitchen

$ morse run pr2_kitchen

Navigation using move_base and AMCL localization

$ morse run pr2_kitchen

MORSE Principles: Components

Available Robot Components

MORSE Principles: Inner loop

MORSE Principles: Interfaces

MORSE Principles: Serialization/Deserialization

Multi-node

Still missing...

MORSE Workshop 2013

Questions?