December 02, 2016
#ERW2016: PAL Robotics’ Open Day, Robots at Your Service & HispaRob Day!

This year’s European Robotics Week broke all records in terms of organized events and participation. At PAL Robotics we also broke records of the assistance at our Open Day, last Friday 25th of November. Two tours were held at our offices, gathering together more than 150 people that were interested in robotics and wanted to know more about PAL Robotics’ projects and platforms.

Attendees could discover our mission, origins, robots and the projects we are involved in. The most exciting part came with the live demonstrations of the humanoids REEM-C and REEM, TIAGo and StockBot, where people could control the robots, play with their applications and ask any doubt to their Product Managers.

At the end of the tour the visitors and the PAL Robotics’ team shared a catering where they could exchange opinions and ask more questions about the company. We hope you enjoyed the visit as much as us. Looking forward to receiving you next year at PAL Robotics!

PAL Robotics at Robots at your Service and HispaRob Day

PAL Robotics also attended to the EU Robotics Week central event in Amsterdam, the Robots at your Service conference about assistive robotics, where TIAGo was presented as one useful platform for Ambient-Assisted Living environments, and the EU Project GrowMeUp was introduced too. Very interesting debates took place at the Maritime Museum. You can find some of the panel discussions ideas given by robotics experts on this RoboHub article.

The first HispaRob Day was also celebrated in Madrid, bringing together the main robotics universities, companies and institutions. HispaRob Day analyzed the robotics sector in Spain and debated on how robots are going to transform our lives in both domestic and industrial environments.

The post #ERW2016: PAL Robotics’ Open Day, Robots at Your Service & HispaRob Day! appeared first on PAL Robotics Blog.

by Judith Viladomat on December 02, 2016 04:28 PM

November 28, 2016
A robot localization system solely based on distance sensors

A robust localization system that uses only distances to a small set of non-synchronized radio beacons at very small update rates. This innovative location system has been developed by Professor Fernando Caballero (Universidad de Sevilla) and Professor Luis Merino (Universidad Pablo de Olavide) with the collaboration of PAL Robotics, in a successful example of the benefits of University/Industry cooperation. We had the pleasure to receive both Professors at PAL Robotics’ offices, where they gave us a presentation on their achievements.

The localization system’s code is open-source and ROS-based, it is publicly available at GitHub. During the visit Prof. Caballero, Prof. Merino and our team successfully integrated the location system with StockBot, using PAL Robotics’ radio beacons from Idolink.

Even without synchronization of the radio beacons, and at a low measure frequency of 0.1Hz, the localization system proved to be very robust and efficient, successfully replacing AMCL. The video shows Stockbot using the range_only_localization system for navigation (no AMCL) and how this localization system can recover the robot from a wrong initial position.

Possible applications of this system are countless, as localizing the robot in very dynamic and cluttered environments or as a recovery tool for AMCL, for example. We are confident that this is an important and very useful contribution to the robotics community.

Prof. Fernando Caballero and Luis Merino with StockBot team for localization system integration ROS

Prof. Fernando Caballero (University of Sevilla) and Luis Merino (University Pablo Olavide) with StockBot team after the integration of the localization system to StockBot.

The post A robot localization system solely based on distance sensors appeared first on PAL Robotics Blog.

by Judith Viladomat on November 28, 2016 12:37 PM

November 18, 2016
EU Robotics Week 2016: Find PAL Robotics in Amsterdam, Madrid and Barcelona!

This Friday the European Robotics Week begins! Europe will be full of robotics events with more than 500 activities registered, which make sure that robots are the continent’s focus. PAL Robotics will be present in Amsterdam, Madrid and Barcelona, where you can meet us and interact with our robots.

PAL Robotics with the EU Robotics Week 2016

 

  • Robots at your service: ERW2016 Central Event (Amsterdam, Nov 18-22)

The ERW2016 Central Event, Robots at your service, is starting today in Amsterdam. Robots at your service is debating about the role of assistant robots in our future and how they can benefit people by taking care of the elderly, ill and disabled people at home. The event brings robots closer to society with Meet the robots exhibition. PAL Robotics’ TIAGo will be there, a robot suitable for Ambient Assisted Living applications which is used for different EU Projects on this area.

Since the event is focused in healthcare and robotic assistance, it will also be a good moment to present the EU Project GrowMeUp, which has the goal of creating a robot companion to assist the elderly at home. The robot, called GrowMu, is aimed to encourage old people to stay longer active, live independently and be socially involved.

The panel discussion Our Robotics Future (14h) will count on the participation of PAL Robotics’ CEO, Francesco Ferro. Debate will be focused on what we can expect of robots, Europe’s role in the robotics evolution and the effects that this transformation will bring.

  • Jornada HispaRob (Madrid, Nov 22)

Are you in Madrid next week? Meet PAL Robotics’ team and TIAGo collaborative robot at the HispaRob Robotics Day, held in the Carlos III University (Leganés campus) on Tuesday 22nd. The event highlights the Spanish role in robotics and will discuss about assistive and collaborative robots, as well as its function contributing with education and society’s cohesion.

TIAGo’s Product Manager, PhD Jordi Pagès will also participate on a panel discussion about collaborative robotics. TIAGo will perform live demonstrations at the collaborative robots demo time, showing how easy it is to command this modular robot for Industry 4.0.

  • PAL Robotics Open Day (Barcelona, Nov 25)

PAL Robotics Open Day ERW2016

The week will end with PAL Robotics’ Open Day on Friday 25th. We are opening our doors to everyone who wants to discover our passion!  We want to share with you our vision regarding the role of robotics, and the knowledge and expertise we have gathered in this field since 2004. The humanoids REEM-C and REEM, the collaborative robot TIAGo and the inventory-taking robot StockBot will perform live demos for all the attendees.

Join us by sending an e-mail at marketing@pal-robotics.com and let us know which tour you would be interested in:

  • Technical tour (12:00-14:00h)
  • General tour (16:30-18:00h)

Looking forward to receiving you at PAL Robotics!

The post EU Robotics Week 2016: Find PAL Robotics in Amsterdam, Madrid and Barcelona! appeared first on PAL Robotics Blog.

by Judith Viladomat on November 18, 2016 10:47 AM

November 17, 2016
FZI Forschungszentrum Informatik and ROS-Industrial
the ros-i powered fanuc m710 on display at Automatica 2016

the ros-i powered fanuc m710 on display at Automatica 2016

The FZI Forschungszentrum Informatik (FZI Research Center for Information Technology), an independent research institute associated with the Karlsruhe Institute of Technology in Karlsruhe, Germany, has a long standing history of working with various robotic frameworks for a number of robot platforms. From special kinematics, like a six-legged walking robot or two-armed service robot with body joints on a mobile platform, to service and industrial robots like the UR 10 and the Fanuc M710. Since 2000, FZI has developed its own robotic framework MCA (Modular Controller Architecture) which later became MCA2 and which is still used on many robot systems today also outside of FZI. With the increasing popularity and maturity of ROS, however, the focus has shifted towards using and expanding ROS rather than further improving the in-house framework (which is still used for many low-level tasks).

With the release of ROS Diamondback, FZI started to use ROS on the robotic Platforms KAIRO III, a snake-like inspection robot, and LAURON IV, a six legged walking robot in conjunction with MCA2. The FZI UAV fleet consisting of Parrot AR-Drones and the Asctec UAVs Pelican and Falcon 8 used ROS Fuerte as the main framework from the start. It was also commonly used to analyze data of the autonomous car CoCar, for which the available visualization tools proved to be very valuable.

The development efforts of ROS components by FZI also increased together with its extended usage. During the preparation of LAURON V for the first SpaceBot Cup by the German Aerospace Center DLR in 2013, initial fixes were provided for libraries such as the SMACH viewer and the robot_web_tools, as they were used extensively to enable autonomous exploration by the walking robot of a Mars-like environment. In October 2014 a larger contribution, the schunk_svh_driver package, was released on behalf of Schunk. It is providing hardware support for one of the most mechanically advanced robotic hands today. In 2016 a driver for the LWA4P with CanOpen support followed. Today the FZI also offers workshops teaching ROS to companies when developers need a concise introduction or just specific help with their projects.

ROS has also become a major research topic in public funded projects. The Human Brain Project (HBP), which FZI takes part in, relies heavily on gazebo as a simulation environment, for which tools like a blender-based intuitive robot designer are being developed. The project ReApp (Reusable robotic Applications for flexible robots), puts ROS-Industrial at its core, and is in fact a team effort with other ROS-focused institutions like Fraunhofer IPA. By adding semantically-enriched models to ROS packages, ReApp further enhances the already reuse-friendly structure of ROS by enabling easier search and automatic replacement of packages. During preparations for Automatica 2016, FZI used the ROS Industrial stack for a Fanuc M710 and implemented the ROS-Industrial-IO REP for Fanuc robots as first contribution to the ROS-Industrial community, which is currently being finalized.

Since August 2016 FZI is part of the ROS-Industrial Consortium Europe, through which it plans to further increase its activities around ROS and ROS-Industrial.

Permalink

by Mirko Bordignon on November 17, 2016 04:26 PM

November 15, 2016
TIAGo Simulation Tutorial 1 – How to control the cobot?

TIAGo’s ROS open tutorials for its open-source simulation in the Gazebo start with TIAGo’s control. This collaborative robot is open in simulation to anyone who has an idea for him. PAL Robotics describes everything needed to use TIAGo in simulation, from the basic steps to control it to more complex motions and commands. Tutorial blocks will be detailed periodically at the blog, starting with the robot’s control.

How can TIAGo cobot be controlled?

Three tutorials show different options to command TIAGo’s Degrees of Freedom:

move_joints_title_PAL_Robotics

 

Make TIAGo wave, shake hands… even lift weights!

TIAGo_gazebo_play_motion_reach_max

TIAGo reaching its maximum in a pre-recorded motion in Gazebo.

PAL Robotics makes available a list of pre-defined upper body motions of TIAGo, based on simultaneous trajectories in multiple groups of joints. TIAGo can play various movements with the hand besides closing and opening it, like pinch, point or put the thumb up. Other motions show its large manipulation workspace, reaching the floor or lifting the arm up to 1.75 m high. On this tutorial you can also command TIAGo to make movements such as TIAGo waving, shaking hands, or even lifting weights!

Find other tutorials on Navigation, MoveIt!, Open CV and PCL at TIAGo’s ROS Wiki, which will be detailed soon in our blog as well.

PAL Robotics TIAGo robot controlled by velocity commands.

TIAGo robot controlled by velocity commands leftwards.

PAL Robotics Open Day 2016

Remember that on Friday, November 25th PAL Robotics opens its doors to everyone! Two tours will take place at our offices, with a presentation of the company and some demos with REEM-C, TIAGo and StockBot. The tours are divided according to the attendee’s profile:

  • Technical tour (12:00-14:00h)
  • General tour (16:30-18:00h)

Register to the Open Day tour you would like to attend by sending an e-mail at marketing@pal-robotics.com. Don’t miss the opportunity!

PAL Robotics Open Day

The post TIAGo Simulation Tutorial 1 – How to control the cobot? appeared first on PAL Robotics Blog.

by Judith Viladomat on November 15, 2016 02:07 PM

November 09, 2016
Continuation of Series on ROS-Industrial Development Process - Code Review

This is the continuation of a multiple-post series detailing the ROS-Industrial software development process. The first post in the series described the process of contributing code to the project (steps 1-3 in the figure above). This post is focused on the steps involved in reviewing code up to the point where is can be submitted for release as a ROS package. Note that the starred numbers in the outline correspond to steps in the software development process illustrated above.

  1. When a Pull Request (PR) is issued there is the Travis Continuous Integrations (CI) step (step 4) which happens automatically in the background. The Travis CI performs several operations and if any of the steps below fail, then the PR is marked accordingly for the maintainer. Travis:
    1. Installs a barebones ROS distribution on a fresh Ubuntu virtual machine.
    2. Creates a catkin workspace and puts the repository in it.
    3. Uses wstool to check out any from-source dependencies (i.e. other repositories).
    4. Resolves package dependencies using rosdep (i.e. install packages using apt-get).
    5. Compiles the catkin workspace
    6. Runs all available unit tests

  2. If the PR passes Travis CI and one of the maintainers is satisfied with the changes they post a +1 as a comment on the PR (step 5). The +1 signifies that the PR is ready to be merged all PR require at least one +1 and pass Travis CI before it can be merged.
  3. The next step (step 6) is for the PR to be merged into the main branch. This is done through the GitHub web interface by selecting the “Merge pull request” button. After the PR is merged, all status badges are updated automatically.
  4. Periodically the maintainer will release the package (step 7), which then gets sent to the ROS build farm for Debian creation (more on this next time).
Stay tuned for our final post in the series on steps 8-10 about Debian creation.

Permalink

by Paul Hvass on November 09, 2016 09:03 PM

PAL Robotics at 2016 ROS-Industrial Conference

ROS-Industrial project aims to apply ROS (Robot Operating System), the de facto standard in robotics, to the industry. Having a shared open operative system in robotics gains relevance when it is applied to manufacturing applications and opens new possibilities for robots to be integrated in assembly chains.

PAL Robotics was invited to the annual ROS-Industrial Conference held last week in Fraunhofer IPA (Stuttgart, Germany) as a company that successfully bases all of its robots in ROS and uses tools such as Rviz or ros_control. PAL Robotics’ CTO Luca Marchionni shared our expertise in the field and explained the advantages and challenges of applying open-source software to the robots we develop and commercialize.

TIAGo robot in simulation performing a pick&place task.

TIAGo robot in the open-source simulation performing a pick&place task.

The active community that contributes to ROS is key for creating a common reference and share the knowledge in robotics to push its evolution. At PAL Robotics we believe on a general-purpose robot operating system that can benefit multiple fields, industry among them. That is why we base all of our robots in ROS and provide their simulation packages in freely available on github. The new open TIAGo tutorials are the latest initiatives we are doing in the direction of extending ROS usage to absolutely everyone.

Come to the PAL Robotics Open Day!

The EU Robotics Week is coming and PAL Robotics is preparing many different activities in Amsterdam, Madrid and Barcelona! On Friday, Nov 25th, we are opening the doors to everyone who has the same passion as us. Our team wants to share with you our vision, knowledge and expertise in robotics, and REEM-C, TIAGo and StockBot will perform live demos. Join us by sending an e-mail at marketing@pal-robotics.com and let us know in which tour you would be interested in:

  • Technical tour (12:00-14:00h)
  • General tour (16:30-18:00h)

We are waiting for you at PAL Robotics!

PAL Robotics Open Day

The post PAL Robotics at 2016 ROS-Industrial Conference appeared first on PAL Robotics Blog.

by Judith Viladomat on November 09, 2016 11:21 AM

November 01, 2016
MoveIt! Community Meeting Oct. 2016

by Paul Hvass on November 01, 2016 08:01 PM

October 26, 2016
Towards ROS-native drones

From Medium:

Announcing alpha support for the PX4 flight stack in a path towards drones that speak ROS natively

The drones field is an interesting one to analyze from a robotics perspective. While capable flying robots are reasonably new, RC-hobbyists have been around for a much longer time building flying machines developing communities around the so called flight stacks or software autopilots.

Among these, there're popular options such as the Paparazzi, the APM (commonly known as ardupilot) or the PX4. These autopilots matured to the point of acquiring autonomous capabilities and turning these flying machines into actual drones. Many of these open source flight stacks provide a general codebase for building basic drone behaviors however modifications are generally needed when one has the intention of tackling traditional problems in robotics such as navigation, mapping, obstacle avoidance and so on. These modifications are not straightforward when performed directly in the autopilot code thereby, in an attempt to enhance (or sometimes just simplify) the capabilities of autopilots, abstraction layers such as DroneKit started appearing.

For a roboticist however, the common language is the Robot Operating System (ROS). Getting ROS to talk to these flight stacks natively would require a decent amount of resources and effort thereby, generally, roboticists use a bridge such as the mavros ROS package to talk to the flight stacks.

We at Erle Robotics have been offering services with flying robots using such architecture but we've always wondered what would be the path towards a ROS-native drone. In order to explore this possibility we've added support for the PX4 Pro flight stack. 


Supporting the PX4 Pro flight stack

The PX4 Pro drone autopilot is an open source (BSD) flight control solution for drones that can "fly anything from a racing to a cargo drone?--?be it a multi copter, plane or VTOL". PX4 has been built with a philosophy similar to ROS, composed by different software blocks where each one of these modules communicates using a publish/subscribe architecture (currently, a simplified pub/sub middleware called uORB).

In an internal attempt to research the path of getting ROS-native flight stacks and to open up this work to the community I'm happy to announce official alpha support for the PX4 Pro in all our products meant for developers such as the PXFmini, Erle-Brain 2 or Erle-Copter. Our team has put together a new set of Operating System images for our products that will help you switch between flight stacks easily.

To install PX4 Pro, just type the following:

sudo apt-get purge -y apm-* # e.g.: apm-copter-erlebrain 
sudo apt-get update 
sudo apt-get install px4-erle-robotics


ROS-native flight stacks 

Using the PX4 Pro flight stack as a starting point, our team will be dedicating resources to prototype the concept of a drone autopilot that speaks ROS natively, that is, that uses ROS nodes to abstract each submodule within the autopilot's logic (attitude estimator, position control, navigator, ...) and ROS topics/services to communicate with the rest of the blocks within the autopilot. Ultimately, this initiative should deliver a software autopilot capable of creating a variety of drones that merges nicely with all the traditional ROS interfaces that roboticists have been building for over a decade now. 

If you're interested in participating with this initiative, reach us out at http://erlerobotics.com/blog/contact/.

by Víctor Mayoral Vilches on October 26, 2016 06:04 PM

PAL Robotics, host of the Factory in a Day Project meeting

Factory in a Day EU FP7 Project continues to move forward! Last week PAL Robotics held the project meeting of Factory in a Day. All European partners were gathered in Barcelona to discuss about the next steps to follow during the project’s final year. Great progress has been made towards the goal of the project: to reduce the system integration time of a robotics solution to one single day for dynamic assembly chains.

Factory in a Day is focused on making profitable the automatization of temporary product lines for SMEs that constantly need to modify or change the production, and find it difficult to capitalize the investment. Very simple modular robots that can be quickly modified and rapidly adjusted to the new needs – in both hardware and software – are ideal for that. Find more about the project here!

Factory in a Day project consortium at PAL Robotics

Factory in a Day project consortium at PAL Robotics

Advances on use cases, integration steps and business-related issues were made during the meeting. Partners could also meet and experience demos with PAL Robotics’ robots and the team behind. PAL Robotics was glad to receive Factory in a Day team and will keep working hard to contribute to this common objective. More information about the meeting at Factory in a Day webpage!

The post PAL Robotics, host of the Factory in a Day Project meeting appeared first on PAL Robotics Blog.

by Judith Viladomat on October 26, 2016 01:17 PM

October 25, 2016
New ROS tutorials to simulate with TIAGo easily!

Would you like to try to command a robot? Do you have in mind robotics applications but don’t have a robot? Want to try TIAGo? PAL Robotics puts an accessible tool available for anyone that wants to try TIAGo, a collaborative robot highly skilled for accomplishing complex tasks. TIAGo’s official ROS Wiki has been completely reshaped and a comprehensive set of TIAGo tutorials in ROS and Gazebo can be found there too.TIAGo is designed to be a useful companion in many contexts thanks to its combination of abilities.

Simulate with TIAGo, the collaborative robot

Simulate with TIAGo, the collaborative robot

The tutorials are distributed in the following areas:

  • Control
  • Navigation
  • MoveIt!
  • Open CV
  • PCL

TIAGo’s tutorials include how to apply two of the biggest standard perception libraries to a robot in ROS: Open CV and PCL. This list will be extended in the future and is also open to anyone’s proposals and suggestions! As easy as sending an e-mail to: tiago-support@pal-robotics.com.

Don’t have TIAGo physically? That’s not a limit!

TIAGo’s simulation is open-source, perfect for anyone that would like to make developments with a collaborative robot in navigation, manipulation, perception or Human-Robot Interactions. The simulation also enables to test TIAGo’s capabilities in order to evaluate if it fits any research needs or its abilities to perform complex tasks.

PAL Robotics: dedicated to ROS since the very beginning

The Robot Operating System (ROS) has become a de facto standard to join efforts and expand robotics, making it accessible for everyone. In PAL Robotics we are very glad with this evolution, since we believe ROS has a huge potential to universalize and democratize robotics, with the final goal of closing the gap that exists between research and real life. That is why PAL Robotics team is a ROS supporter and contributor since the very beginning, and makes available the open-source simulations of all robots online on their official ROS Wiki.

Everybody can simulate with TIAGo robot

From robotics engineers that want to try TIAGo’s capabilities to people who is new in this world: TIAGo tutorials are open to anyone willing to easy learn and try! Tutorials have detailed explanations and will improve over time.

Share your work with us and we will publish any cool development you are capable of! Send it by e-mail to: tiago-support@pal-robotics.com.

TIAGo robot in simulation

TIAGo robot in simulation

The post New ROS tutorials to simulate with TIAGo easily! appeared first on PAL Robotics Blog.

by Judith Viladomat on October 25, 2016 02:57 PM

October 24, 2016
Save the date for the second MoveIt! Community Meeting: Oct. 27 (Online)

From Dave Coleman

Our second MoveIt! community meeting webcast will be on October 27th at 8am Pacific to discuss the latest developments and uses of MoveIt! around the world. Join us online to hear from research groups and industry on their perspectives of motion planning in ROS. Confirmed speakers include:

  • Recent Developments in MoveIt! - Dave Coleman
  • The Search-Based Planning Library (SBPL) - Dr. Maxim Likhachev and Andrew Dornbush
  • Updates from the Flexible Collision Checking Library (FCL) - Dr. Dinesh Manocha
  • Delft's Winning Amazon Picking Challenge Entry - Mukunda Bharatheesha
  • MoveIt! @ Fetch Robotics - Michael Ferguson
  • Q&A with original MoveIt! Developer & Founder - Dr. Ioan Sucan

Final agenda and details on how to join the AnyMeeting webcast will be sent out closer to the event. If you are interested in presenting your work to the community please contact me by October 21st.

by Tully Foote on October 24, 2016 10:43 PM

The Nuclear Robotics Group Goes Public!

Submitted by: Dr. Andrew Zelenak and Dr. Mitch Pryor, UT Austin Nuclear and Applied Robotics Group (NRG)

Cross posted from: http://robotics.me.utexas.edu/nuclear-robotics-group-goes-public

We are happy to announce a code release! The Nuclear Robotics Group at UT-Austin was an early adopter of ROS software, but until recently, most of our software was private. However, our main sponsor (Los Alamos National Laboratory) recently gave the green light to open-source our code. With that approval, we are slowly rolling code over to a public repository and will be indexing the packages with ROS as appropriate. This was first announced to the ROS-Industrial community in June 2016. A couple little gems which might already be useful for the public include:

  • The netft_utils package for ATI force/torque sensors:
    • Set the data collection rate
    • Transform force data between TF frames as a robot moves
    • Compensate for gravity forces on the end-effector
  • A driver for LeapMotion
    • The LeapMotion hardware tracks a human’s hands, making for some really cool demos and user interfaces
  • A driver for the Griffin Powermate user interface device A contact control GUI

In the future, we’ll be open-sourcing even more, so keep your eyes open! The video below shows a little demo incorporating the above-mentioned packages.

by Paul Hvass on October 24, 2016 08:54 PM

October 21, 2016
Google Summer of Code Project – Workspace Analysis and Base Placement

Submitted by: Abhijit Makhal, Idaho State University

For the Google Summer of Code Project (GSoC) 2016, with coordination with Open Source Robotics Foundation (OSRF) and ROS-I Consortium, a toolkit Reuleaux, has been developed for the purpose of workspace analysis and base placement for a specified task. The workspace analysis is highly beneficial for any robotic system as it provides information about the reachability of the manipulator. The base placement system uses the workspace analysis tool and provides optimal base position for a specified task providing predefined end-effector positions.

The first project goal was to develop a tool that can define reachability of any manipulator with existing robot definition such as URDF (Unified Robot Description Format). With an URDF of the robot and resolution based on user needs, the tool can provide multiple maps representing the information about the workspace such as a reachability map, capability map and inverse reachability map. Several new ROS messages have been generated for workspace analysis which represents the coordinates of the workspace spheres, poses in the spheres and reachability of that spheres.

Reachability Map

The reachability map describes the reachability of a given robot model by discretizing its environment, creating poses in the environment and calculating valid IK solutions for the poses. The poses which are reachable by robot are associated with discretized spheres. The reachability of each sphere in the environment are parameterized by a reachability index. The output is saved as an hdf5 file.

Reachability map colored by reachability index (left), and solid colors (right).

Reachability map colored by reachability index (left), and solid colors (right).

Reachable positions for a robot (left), and 6 DOF poses superimposed on reachable positions (right).

Reachable positions for a robot (left), and 6 DOF poses superimposed on reachable positions (right).

Capability Map:

The capability map is an extension of reachability where the outer spheres of the reachability map, is set as cones. So the reachability limit of the robot is well visualized. All the outer spheres are decided for a principal axes and iterates over different values for opening angles for cones.

Inverse Reachability Map

The purpose of the inverse reachability map is to find suitable base positions for a robot with given task poses. The inverse reachability map is a general inverse transformation of all the reachable poses of the reachability map of the robot. The inverse Reachability map is dependent on generated reachability map. With a visualization toolbox for Reuleaux, the workspace can be visualized in RViz. The visualization tool also provides scope of representing the workspace with different structures (spheres, cones, cylinder and box), colors (based on reachability or solid colors) and reachability index (spheres with high/low reachability)

Spheres with low Reachability (left), and high reachability (right)

Spheres with low Reachability (left), and high reachability (right)

Dense cross-section of the workspace (left), and sparse Cross-Section  (right)

Dense cross-section of the workspace (left), and sparse Cross-Section  (right)

The second goal of the project was to develop a user interface by which the user can provide task poses needed for a specified task and the system will try to find optimal base position/ positions for that task from where the robot can reach all the positions. The system tries to create a combined inverse reachability map of all the task poses and finds optimal base location by one of the following methods.

  1. Principal Component Analysis (PCA)
  2. Grasp reachability score
  3. Ik solution score
Magenta arrows represent the task positions and green arrows are possible base placement positions (left, center). Combined inverse reachability map for three task poses (right).

Magenta arrows represent the task positions and green arrows are possible base placement positions (left, center). Combined inverse reachability map for three task poses (right).

At this time, the Reuleaux toolkit is far away from completion. There are various scopes of improvement for the tool in terms of visualization, algorithm and computation. I would like to encourage the Robotics Community to contribute to this project by providing suggestions and improvements. Detailed information and instructions for running the tool can be found at: http://wiki.ros.org/reuleaux

Please let me know if there is any issue in running the codes or if you have any suggestions: makhabhi@isu.edu

I would like to share my gratitude for the ROS-I community members and my mentor Alex K. Goins and Shaun Edwards, who shared their valuable suggestions during the project development and guided me in the right direction. I hope that this project can be very useful for robotics community.

by Paul Hvass on October 21, 2016 11:16 PM

October 19, 2016
ROSCon 2016 Videos and Slides Posted

ROSCon was record-breaking in every way, with over 450 attendees and a 60% increase over last year in sponsorship.

Thanks to everyone for coming and for your support! And thank you to our sponsors for the financial support that enabled the conference to grow!

We're happy to announce that we've posted recordings of all the talks on the program. You can find them linked at: http://roscon.ros.org/2016/#program As well we have collected the slides from most of the presenters as well which are linked there as well.

If you would like to browse through the videos alone you can also find all 56 videos here: https://vimeopro.com/osrfoundation/roscon-2016

by Tully Foote on October 19, 2016 03:38 PM

October 18, 2016
Second MoveIt! Community Meeting: Oct. 27 (Online)

Submitted by: Dave Coleman, CU Boulder

Time: October 27, 2016 starting at 10 AM CDT

Our second MoveIt! community meeting webcast will be on October 27th at 8am Pacific to discuss the latest developments and uses of MoveIt! around the world. Join us online to hear from research groups and industry on their perspectives of motion planning in ROS. Confirmed speakers include:

  • Recent Developments in MoveIt! - Dave Coleman
  • The Search-Based Planning Library (SBPL) - Dr. Maxim Likhachev and Andrew Dornbush
  • Updates from the Flexible Collision Checking Library (FCL) - Dr. Dinesh Manocha
  • Delft’s Winning Amazon Picking Challenge Entry - Mukunda Bharatheesha
  • MoveIt! @ Fetch Robotics - Michael Ferguson

Final agenda and details on how to join the AnyMeeting webcast will be sent out closer to the event. If you are interested in presenting your work to the community please contact me by October 21st.

by Paul Hvass on October 18, 2016 10:04 PM

October 14, 2016
Hardware Robot Operating System (H-ROS)

Originally published in Medium:

1--XgoPd36umkXi6lXTGkCng.png

I'm delighted to announce a new game-changing standard for building robot components, H-ROS: the Hardware Robot Operating System. H-ROS provides manufacturers tools for building interoperable robot components that can easily be exchanged or replaced between robots.

H-ROS is about supporting a common environment of robot hardware components, where manufacturers comply with standard interfaces built upon ROS.

Powered by the popular Robot Operating System (ROS) and built with industry and developers in mind, H-ROS classifies robot components in 5 types: sensing?--?used to perceive the world, actuation?--?allow interaction with the environment, communication?--?provide a means of interconnection, cognition?--?the brain of the robot and hybrid?--?components that group together different sub-components under a common interface. This building-block-style parts come as reusable and reconfigurable components allowing developers, to easily upgrade their robots with hardware from different manufacturers and add new features in seconds.

Motivation and origin

Building a robot is accepted as a harsh task thereby it makes sense to reuse previous work to reduce this complexity. Unfortunately, nowadays there are little efforts that reuse hardware in both academy and industry. Robots are generally built by multidisciplinary teams (generally a whole research group or a company division) where different engineers get involved in the mechanical, electrical and logical design. Most of the time is spent dealing with the hardware/software interfaces and little is put into behavior development or real-world scenarios. Existing hardware platforms, although starting to become more common, lack extensibility.

Examples can be seen in several commercial and industrial robots that hit the market recently and already include a common software infrastructure (generally the Robot Operating System(ROS)) but lack of a hardware standard.

With H-ROS, building robots will be about placing H-ROS-compatible hardware components together to build new robot configurations. Constructing robots won't be restricted to a few with high technical skills but it will be extended to a great majority with a general understanding of the sensing and actuation needed in a particular scenario.

H-ROS was initially funded by the US Defense Advanced Research Projects Agency (DARPA) through the Robotics Fast Track program in 2016. It is now available for selected industry partners and will soon be released for the wider robotics community. Additional information can be requested through its official web page at https://h-ros.com/. H-ROS was first unveiled and showcased at ROSCon 2016 (October 8th-9th) in Seoul, South Korea.

by Víctor Mayoral Vilches on October 14, 2016 11:05 PM

October 07, 2016
Better supporting the growing ROS-Industrial software platform

As ROS-Industrial approaches its fifth anniversary, we wanted to share some reflections on how the initiative is evolving and on some adjustments in policy to maintain it on a healthy, sustainable growth path.

The first demo showcasing the advantages of ROS on industrial hardware, a pick-and-place application performed on a Motoman SIA10D, was developed in the fall of 2011 by Shaun Edwards. From this early effort we have come a long way both in terms of Consortia and Community building and of further development of the software platform. With the recent addition of the Asia Pacific region we now have more than 40 organizations supporting the ROS-Industrial Consortia worldwide. On the software side, ROS-Industrial is growing in terms of more supported hardware and of more, and more advanced, capabilities that it offers to industrial users.

In parallel to the effort of expanding the Consortia and to keep the "voice of business" in the loop, the software development community is growing under the technical leadership of Shaun Edwards and Gijs van der Hoorn. We have been hosting online developer meetings since last fall: now held monthly, they provide a venue for contributors to become more involved with the rest of the community and eventually join it on a stable basis. In addition to growing the codebase, we are gradually enforcing best practices in the development process to ensure a better overall software quality. These include an improved review process for PRs; unit and system test coverage; continuous integration tests.

While the expansion of the development community brings on-board very welcome contributors, the commitment required to maintain and support a fast expanding software platform is calling for a more structured approach than we had so far. This in order for us to be able to more effectively and more fairly commit development resources, and for our users to get a better understanding of the support level that they can expect.

A more effective and fair allocation of resources means standing behind the code which supports the activities of Consortia members. These are the organizations making the initiative possible, as they provide financial support and public advocacy for the adoption of open-source software in industrial robotics. A better understanding of support level means helping our users to set their expectations to an appropriate level when evaluating the adoption of specific packages. For instance, a manufacturer actively supporting the driver for its equipment, directly or through its regional ROS-Industrial Consortium, makes for a much different situation than having to rely solely on community support.

As a first step towards this direction, we announce the following levels of support for packages in the ros-industrial github organization:

  • consortium / vendor: for packages supporting the activities of a Consortium member, which ideally also contributes with in-house technical support (e.g., robot drivers); for core ROS-I packages developed and maintained by the technical leads;
  • vendor: for packages directly supported by the vendor's technical staff;
  • community: support is community-based, and as such it is best-effort and based upon the work of volunteers.
support badges for ROS-I packages

support badges for ROS-I packages

We are currently rolling out this scheme by gradually assigning "badges" corresponding to the appropriate support level to the various ROS-Industrial packages. We also want to provide soon users with means to "ping the OEM" behind a specific piece of hardware which is currently at community-level support, and we are currently looking for the most effective means to do so.

by Mirko Bordignon on October 07, 2016 03:48 PM

October 05, 2016
Introducing Cartographer

From Damon Kohler, Wolfgang Hess, and Holger Rapp, Google Engineering

We are happy to announce the open source release of Cartographer, a real-time SLAM library in 2D and 3D with ROS support.

Cartographer builds globally consistent maps in real-time across a broad range of sensor configurations common in academia and industry. The following video is a demonstration Cartographer's real-time loop closure:


A detailed description of Cartographer's 2D algorithms can be found in our ICRA 2016 paper.

Thanks to ROS integration and support from external contributors, Cartographer is ready to use on several robot platforms with ROS support:

At Google, Cartographer has enabled a range of applications from mapping museums and transit hubs to enabling new visualizations of famous buildings.

We recognize the value of high quality datasets to the research community. That's why, thanks to cooperation with the Deutsches Museum (the largest tech museum in the world), we are also releasing three years of LIDAR and IMU data collected using our 2D and 3D mapping backpack platforms during the development and testing of Cartographer.


Our focus is on advancing and democratizing SLAM as a technology. Currently, Cartographer is heavily focused on LIDAR SLAM. Through continued development and community contributions, we hope to add both support for more sensors and platforms as well as new features, such as lifelong mapping and localizing in a pre-existing map.

by Tully Foote on October 05, 2016 07:26 PM

October 04, 2016
TALOS: the next step in humanoid robots from PAL Robotics

PAL Robotics is launching a new humanoid robot: TALOS, a collaborative robot for industrial complex tasks. TALOS will be an advanced electrical high-performance humanoid robot due to the cutting-edge technology integrated. Stay tuned, TALOS will be released soon!

This humanoid robot is conceived for industrial Human-Robot collaboration. TALOS’ goal is to assist workers in factory assembly lines with physically demanding tasks that need high accuracy, and which are performed in hostile or uncomfortable industrial settings.

TALOS Robot by PAL Robotics.

TALOS Robot by PAL Robotics.

This new humanoid robot was born from a tender granted by the French research lab LAAS-CNRS. The first platform will be delivered to the LAAS-CNRS’ Gepetto team, under the direction of Philippe Souères, PhD. The humanoid will be released in November. The Gepetto team will name it PYRENE.

Want to know a bit about TALOS?

  • TALOS is a fully electrical human-sized robot
  • It has sensored torque control in all joints
  • The platform uses EtherCAT communicationsTALOS robot from PAL Robotics

The robot can walk dynamically at a maximum speed of 3Km/h, and is able to navigate through uneven ground. Each arm has a 6Kg payload when fully extended, and it has dexterous and flexible manipulation skills. Therefore it can nimbly handle heavy industrial tools with its customized 3-fingered grippers.

TALOS is 100% ROS capable as all of PAL Robotics’ platforms. PAL Robotics has made a huge effort to integrate the best hardware components and sensors on this humanoid robot.

The tendency of collaborative robots in Industry 4.0

Collaborative robots like TALOS are conceived to take part in industrial activities that are manual, arduous, and require accuracy or strength. TALOS’ mission is to assist in those tasks that are susceptible to damage the worker’s health.

With TALOS, PAL Robotics makes available a flexible and accessible platform to go beyond the limits of Industry 4.0.

The post TALOS: the next step in humanoid robots from PAL Robotics appeared first on PAL Robotics Blog.

by Judith Viladomat on October 04, 2016 08:53 AM

September 26, 2016
ROS-Industrial Training and Conference 2016: schedule now online
fraunhofer izs - Institute center stuttgart

fraunhofer izs - Institute center stuttgart

Check out the exciting schedule for the upcoming ROS-Industrial Training and Conference 2016, to be held Nov 2-4 at Fraunhofer IPA in Stuttgart, Germany. For this year's edition of the Conference we have the pleasure to host two keynote speakers. During the first day Brian Gerkey, CEO and founder of the Open Source Robotics Foundation, will recap the history of ROS and share with the audience how advanced robotics is performed during "the era of open-source software". During the second day Prof. Michael Beetz from the University of Bremen will illustrate how knowledge-based services such as openEASE can improve interoperability in robotics and lower the barriers for robot programming. The training session has been updated as well, with our colleagues at FH Aachen delivering a full day of hands-on ROS training, and ROS-Industrial Consortium Europe members PPM AS and IT+Robotics srl providing FlexGui and cROS training during the second day. Please note that there is a significant discount if you register (registration now closed) for both events, and a further reduction for ROS-Industrial Consortium members. See you in Stuttgart on November 2-4!

by Mirko Bordignon on September 26, 2016 05:40 PM

September 23, 2016
catkin-tools tip pt.2
From TORK blog

Following our previous post about a nice hidden tip for catkin-tools, here’s another one.

When finishes compilation, `catkin build` shows a pop-up window at the top-right on your screen (if you’re on Ubuntu Linux), which indicates `Build Finished` or `Build Failed`. This is nice in that you can work on another windows without payting attention to catkin’s progress. Caveat is, though, that “Finished” and “Failed” aren’t that obviously differentiating whatsoever.
With the newer version of catkin-tools, 0.4.3 or higher, the window pops up with a distinguishable colors; Green for success and red for failure.

This little but significantly effective change is done by our TORK associates again. The change was made swiftly and neatly as it has always been in the opensource software community.

by Isaac Saito (noreply@blogger.com) on September 23, 2016 08:57 PM

More than 30,000 Questions on ROS Answers

We've reached another milestone for ROS Answers, 30,000 questions asked!

answers.ros.org_30000.png

The 30,000th question was asked Friday by @Mani who regularly helps answer others questions as well.

To see the many contributors to the site please view the list of users

Congratulations to the answers.ros.org community for making the site the thriving resource that it is today. Keep up the fantastic work, and keep the questions--and answers--coming.

With the awareness on the site. If you've asked a question and not marked it answered. Please consider revising it with more details or to add clarity. And likewise consider trying to answer one question each time you're on the site.

by Tully Foote on September 23, 2016 01:32 AM

September 21, 2016
Grid Map Library

From Péter Fankhauser via ros-users@:

We'd like to announce our new Grid Map package, developed to manage two-dimensional grid maps with multiple data layers and designed for mobile robotic mapping in rough terrain navigation.

The package is available for ROS Indigo, Jade, and Kinetic and can be installed from the ROS PPA. After multiple development cycles and use in many projects, the library is well tested and stable.

Features:

  • Multi-layered: Developed for universal 2.5-dimensional grid mapping with support for any number of layers.

  • Efficient map re-positioning: Data storage is implemented as two-dimensional circular buffer. This allows for non-destructive shifting of the map's position (e.g. to follow the robot) without copying data in memory.

  • Based on Eigen: Grid map data is stored as Eigen data types. Users can apply available Eigen algorithms directly to the mapdata for versatile and efficient data manipulation.

  • Convenience functions: Several helper methods allow for convenient and memory safe cell data access. For example, iterator functions for rectangular, circular, polygonal regions and lines are implemented.

  • ROS interface: Grid maps can be directly converted to and from ROS message types such as PointCloud2, OccupancyGrid, GridCells, and our custom GridMap message.

  • OpenCV interface: Grid maps can be seamlessly converted from and to OpenCV image types to make use of the tools provided by OpenCV.

  • Visualizations: The grid_map_rviz_plugin renders grid maps as 3d surface plots (height maps) in RViz. Additionally, the grid_map_visualization package helps to visualize grid maps as point clouds, occupancy grids, grid cells etc.

Source code, documentation, and tutorials available at https://github.com/ethz-asl/grid_map

by Víctor Mayoral Vilches on September 21, 2016 08:37 AM

September 20, 2016
ROS Interface for Impedance/Force Control

Originally published at the ROS Industrial blog:


This summer, Risto Kojcev, sponsored by the Google Summer of Code (GSOC) and directed by the Open Source Robotics Foundation (OSRF) and the ROS-Industrial (ROS-I) Consortium developed a user friendly ROS Interface to control and change a manipulator into Cartesian Impedance control mode. The external forces that the robot applies to the environment can also be set with the developed interface.

Risto shares:

Our first goal was to create a set of common messages containing the necessary parameters for setting Impedance and Force control. This allows interaction between the ROS ecosystem and the ROS driver of the robot. The messages are created based on the commonly used parameters for Impedance/Force control and discussion with the ROS community. The relevant current set of ROS messages are available in the majorana repository. I would also like to encourage the Robotics community to contribute to this project by sharing their suggestions. I believe that this set of messages could still be more generalized and improved based on community input.

The second goal was to develop a user interface which allows the user to set the necessary parameters for Cartesian Impedance/Force Control and interactively switch between control modes. In this case I have expanded previous GSoC 2014 Project: Cartesian Path Planner Plug-In for MoveIt!. The updated plugin now contains the relevant UI fields for setting Cartesian Impedance and Force Control. Depending on the implementation and the properties of the robot controller, this plugin also allows interactively switching between control modes during runtime.

by Víctor Mayoral Vilches on September 20, 2016 06:40 PM


Powered by the awesome: Planet