Final Project Video of Factory-in-a-day
Small and medium enterprises in Europe often refrain from using advanced robot technology. The EU-project Factory-in-a-Day aimed at changing this by developing a robotic system that is to set up, operational in 24 hours and is flexible, leasable and cheap. This video summarizes the results of Factory-in-a-day after the project ended this autumn.
Video Deliverable 5.3: Automated Polishing Software
In Factory-in-a-day we developed a software for automating polishing, using software development platforms ROS, VTK and MySQL. In the Automated Polishing Software, the to-be polished work piece’s geometry is loaded and the properties of the workpiece eg. surface finish, hardness, surface curvatures etc. are defined and analyzed. The inference system generates a polishing recipe using the existing polishing recipes in the knowledge base. Afterwards, the polishing path is checked for any collisions and the polishing plan is simulated.
Author: Ceyhun Sözbir / Fraunhofer IPT
Reactive Path Planning and Motion Control (Deliverable 4.4)
This deliverable video focuses on the dynamic obstacle avoidance which is an essential component to ensure safety in the robot environment and get the robots collaborate with fellow human beings thus improving the efficiency of the processes in the factory environment which is one of the goals of the project. In terms of technology, Skin Sensors from TUM, Reactive Path Planner from SIEMENS-PLM, and Reactive Controller from LAAS makes us confident in achieving this task. This deliverable makes an attempt to combine all the components to get a manipulation scenario running to illustrate the dynamical obstacle avoidance capability.
Augmenting awareness by HoloLens: initial exploration
This video is a first exploration on how Augmented Reality can be used in production planning and during deployment & operation. The video is part of Deliverable 4.4.
Author: Jouke Verlinden/TU Delft
Deliverable 5.4 A model based task specification that includes programming by demonstration aspects
The video shows a robotic pick and pack application, where model-based task specification and programming by demonstration are combined in a learnable skill for online and reactive execution.
Trajectories and its variations are extracted from programming by demonstration while allowing incremental learning.
Authors: Cristian Vergara, Erwin Aertbeliën / KU Leuven
Demonstration of the On Robot RG2 gripper URCap
The RG2 gripper is fully integrated with UR robots through the URCaps software platform. Due to the seamless integration between the robot & gripper the setup & programming time is reduced to 5 minutes and the programming requires no coding at all! Enabling your factory in a day! This is part of Deliverable 5.4
Author: Azadeh Sabouri, Robert Wilterdink / Universal Robots A/S
Demonstration of Robotiq’s Path Recording Software with URCapAuthor:
Easy path recording: 5 minute programming time, step-by-step instructions, plug & play without coding. This is part of Deliverable 5.4.
Azadeh Sabouri, Robert Wilterdink / Universal Robots A/S
Use case shaver assembly: The full sequence.
The robot grasp each of 8 parts, move them to the caroussel where they are processed, put them back to the initially empty tray, and finally stacks the empty tray on top of the full tray.
The movie illustrates a robot programming interface to build a sequence of motions in order to perform an industrial task, where shavers are built.
Deliverable 5.3a: Kinesthetic teaching on industrial robots presented at IROS 2015
This video shows our kinesthetic teaching approach using semantic inference to allow TUM’s robot TOMM to segment and recognize the intentions of the human in real-time.
Deliverable 5.3 b: A first concrete learnable skill: an orange picking application
This video shows the kinesthetic teaching of a learnable skill on the robot TOMM in an orange picking application. The kinesthetic teaching uses the multi-modal artificial skin. The learned skill can be combined with target endpoint constraints determined by vision. Other aspects of a task such as collision avoidance can be combined with the learned skill.
Deliverable 4.2 : Path Planning with Proximity Sensing Data
Robot sorting oranges
At IROS 2015 (September 29 – October 1, 2015) the project Factory-in-a-day presented recent results of our work. Partner TUM shows a demonstration of the robot TOMM that is able to sort oranges.
Autonomous motion planning
This video of the project Factory in a day shows how a robot can find a collision-free, accessible path in a work space in order to handle a specific work piece. It demonstrates the work of our partner Siemens AG.
1st Robothon of Factory in a day
How does Factory-in-a-day work in a real world case of one of our partners? This was tested during a 2-day workshop at Fraunhofer IPA in Stuttgart/Germany in July 2014. The goal was to show a full circle of tasks, in which 2 trays were handled(loading and unloading trays with shaver parts as well as handling them). The robot had not only to pick-up parts from a tray and put them in a carrier but also pick-up the trays themselves.
The 2nd workshop
The second Factory-in-a-day workshop for SMEs took place in January 2014. This time the challenge was setting up a robot for the planting of Yucca palms. The team started from scratch, and after two days of work this video was made, showing the prototype at work.
The 1st workshop
In the first Factory-in-a-day workshop on 6 and 7 November 2013, ten people were involved in setting up a robot for a packaging line. They started from scratch, and after two days work this video was made, showing the prototype at work. The workshop is an EU co-funded endavour from the TU Delft Robotics Institute to bring robots into small and medium-sized companies.
In order to give the project members a real taste of the challenge of the Factory-in-a-Day project, they received a task for the kick-off meeting: program a robot to to the same task as can be seen in the video. Therefore the tennis ball box holder and a construction for the ball had to be build all in 3 hours. Quite a challenge as most of the team members worked together for the first time.
You can also visit our YouTube-channel.