GithubHelp home page GithubHelp logo

vislab-tecnico-lisboa / vizzy Goto Github PK

View Code? Open in Web Editor NEW
12.0 11.0 9.0 135.48 MB

The tools you need to interact with Vizzy robot.

CMake 5.44% MATLAB 6.78% C++ 71.18% Thrift 0.14% Python 14.76% Shell 1.71%
humanoid-robots yarp gazebo ros simulation robot

vizzy's People

Contributors

carlos-cardoso avatar joao-avelino avatar joao-borrego avatar joaosaramago avatar mikearagao avatar nigno17 avatar pliniomoreno avatar rafaelnunezcruz avatar richardson0811 avatar ruimgf avatar ruipimentelfigueiredo avatar tpaulino7 avatar vicentepedro avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

vizzy's Issues

Simplify robot collision model

The simulated robot is currently checking collisions with the high-polygon count meshes instead of using a simpler blocky model.
This may be why the performance is so low with gazebo.
Essentially means the urdf must be revised.

Vizzy manual and documentation

Hi @plinioMoreno (+ @ruipimentelfigueiredo @joao-avelino),

Last summer, we started copying the documentation of Vizzy on the wiki associated to this repository, here:
https://github.com/vislab-tecnico-lisboa/vizzy/wiki

Personally, I think it would be good to put the remaining documentation (i.e., the PDF manual) on the wiki too, in order to (1) have it all in one place, (2) make it easily and quickly updatable in the browser, (3) facilitate the transition of knowledge if some of you ever leave the lab (I hope not! but just in case :) ).

Furthermore, it will still be possible to generate printable PDFs (from GitHub wiki Markdown syntax) by using tools like this one: https://www.npmjs.com/package/markdown-pdf

Regenerate MoveIt! config files

Following the changes made in the gazebo-performance branch, since the urdf has been changed, the MoveIt! package needs to be regenerated before it can work once again.
Preferably we could have two versions: one which uses a simplified model of the hand and another with a more detailed mesh for collision (maybe even capable of grasping experiments).
As of right now, the detailed hand is not yet implemented, but the arm description file has an empty slot where it should be instanced.

Move large map files to Git Large File Storage

Hi @plinioMoreno @ruipimentelfigueiredo @joao-avelino!

I noticed that the whole vizzy repository takes about 200MB at the moment, the majority of which due to the larges files in vizzy_navigation/maps (115MB).

Suggestion: host those large files elsewhere using Git Large File Storage, which looks like a nice possibility for these cases. Cloning/Working with the vizzy repository will be faster, while those files will still be available and maintainable on the "external" LFS reference.

Error on running vizzy_simulation.launch when the flag use_yarp:=true

After downloading the content of the whole Vizzy repository, when I tried to run, I got the following error

$ roslaunch vizzy_launch vizzy_simulation.launch use_yarp:=true navigation:=true

< a lot of stuff and then the error >
roslaunch.substitution_args.ArgException: use_yarp
while processing /home/pedro/catworkspace/src/vizzy-master/vizzy_moveit_config/launch/moveit.launch:
while processing /home/pedro/catworkspace/src/vizzy-master/vizzy_moveit_config/launch/planning_context.launch:
Invalid tag: Cannot load command parameter [robot_description]: command [/opt/ros/hydro/share/xacro/xacro.py '/home/pedro/catworkspace/src/vizzy-master/vizzy_description/robots/vizzy.urdf.xacro'] returned with code [1].

Param xml is < param command="$(find xacro)/xacro.py '$(find vizzy_description)/robots/vizzy.urdf.xacro'" if="$(arg load_robot_description)" name="$(arg robot_description)"/>

It seems that the file vizzy-master/vizzy_moveit_config/launch/planning_context.launch is incomplete.

[iKinGazeCtrl] Fix "random" spikes during control

The Gaze changes abruptly during some demos when the points are sent in a continuous way.

Possible problems:

  • Target points with strange values.
  • Bridge ROS/YARP, since this happens when controlling from ROS (we need to test with YARP).
  • YARP BufferedPort reads only the last value (this can explain spikes during a sine trajectory).
  • The operating system is not controlling in real time.

/cc @joao-avelino

Change local planner

Update the local planner from the eband (Elastic Band) local planner to the teb_local_planner (Timed Elastic Band)

Add realistic navigation algorithm in simulation

The current navigation algorithm in simulation is the "fake_localization", which for initial debugging was very useful, but for testing code for the real robot does not consider the execution times of the amcl in the real robot.

The amcl should be available in simulation, in order to have a more realistic simulation of the navigation algorithm.

Fixation point and ball position (from yarp to ROS)

We should use Miguel Aragão's master thesis work to send vizzy's current fixation point (provided by the Ikin gaze controller) and the ball position (provided by Matteo's ball tracker) to ROS side, for visualization purposes.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.