RoboHub Eindhoven: Robocup@Work Team Description Paper 2023

Jules van Horen, Remco Kuijpers, Mike van Lieshout, Stefan Clercx, Alec de Jongh, Jeroen Bongers, Mark Geraets, Tim Aarts, Olaf Wijdeven, Ronald Scheer, Sjriek Alers

RoboHub Eindhoven Fontys University of Applied Sciences Department of Engineering De Rondom 1, 5612AP Eindhoven, The Netherlands

http://robohub-eindhoven.nl · https://www.youtube.com/channel/UCQkpwno0b1QEp96Wy66yLPQ · https://github.com/robohubeindhoven · http://youbot-store.com · https://probotics-agv.eu · https://www.universal-robots.com · https://wiki.ros.org/teb_local_planner · https://pjreddie.com/darknet/yolo/ · https://www.smartindustry.nl/english/ · http://ros2.org

Abstract This paper introduces the RoboHub team submission to the RoboCup@Work World Championship 2023. This papers details the current state of our robot and the team behind the robot. We give an overview of the hardware platform, the software framework and technical challenges in navigation, object recognition and manipulation. We outline present and future research interests and discuss relevance to industrial tasks.

Keywords: ROS2 · 3D Vision · lite6 · YOLO V5.

Introduction

RoboHub Eindhoven is a team of motivated students, teachers and professionals that are working together to discover new solutions for robotic systems. RoboHub Eindhoven is part of the Engineering department of the Fontys University of Applied Sciences. We are challenging ourselves to find creative ways to bring robotics to the next step. Together we want to share our knowledge with other motivated people, therefore we work with companies that want to support us and our technology. Within the RoboHub Eindhoven we are participating at the RoboCup@Work league with the RoboHub team that focuses on the industrial use of autonomous robots. We have a multidisciplinary team of students working on the robot, where the core team is complemented with students from our Adaptive Robotics Minor and guided by experienced RoboCup coaches. Furthermore, we created an educational outreach project around our robot. With our educational outreach project we expect to inspire non-technical students to embrace technology and start learning to create and program robots and how to work with robots. The team already started in 2017 and competed multiple times in the RoboCup German Open. At first we participated using a KUKA YouBot, but due to the fact that the YouBot was discontinued we started to investigate the usage of another platform. In 2018 we competed with a prototype of the Probotics Packman platform equipped with a UR3 manipulator. From 2019 onwards, we compete with our custom designed robot platform Sui², which is also equipped with an UR3 manipulator. Since 2022 we started the development of your new competition robot "SLICK". Since 2021 we started the development of the new generation of the Robohub Eindhoven competition robot which will be used in 2023. In the last year we have made "Robohub Eindhoven" an official non-profit foundation registered in the dutch "Kamer Van Koophandel". This will make us able to grow further as an organisation.

Description of the hardware

SLICK is an holonomic mobile platform developed by Robohub Eindhoven. The drivetrain consists of 4 mechanum wheels of which two have a costum-made suspension system. The motors, encoders, gearbox and motor controllers are from Maxon motors. The robot has a 6-dof cobotic manupulator from the company Ufactory called the "Lite-6". For gripping the objects, a parallel 3d printed gripper is developed with an integrated 2d and 3d vision camera. An Asus pc is used for the high level control. The Vision system runs on separate Jetson Xavier. For navigation, two Hukuyo lidar sensors are used. The battery can be easily replaced using a battery slider. The cover of the AGV can be easily detached to quickly replace or test the hardware. The hardware diagram of the robot is shown in Fig. 2.

Description of the software

Our software implementation includes the high-level and low-level controls, sensor and actuator processing and monitoring software.

High-level Control

For the High-level robot control we make use of the Robot Operating System (ROS2). ROS2 provides many useful tools, hardware abstraction and a message passing system between nodes. Nodes are self contained modules that run independently and communicate which each other over so called topics using a one-to-many subscriber model and the TCP/IP protocol.

Localization and Navigation

For localization, SLICK uses two Hokuyo lidars. The raw lidar data is processed within ROS2 to perform robust localization. The Global planner is unchanged, but the local planner is replaced in our system by the Timed Elastic Band planner which locally optimizes the robot's trajectory with respect to trajectory execution time. Furthermore, low level smoothing of the acceleration profiles is implemented to make the robot more controllable.

YOLO V5

For object detection and recognition the robot is equipped with a realsense RGB-D camera. This camera is located on the robot-arm near the end-effector. The images are processed with YOLO V5 (The robot used to use YOLO v3 but we switched to YOLO v5.), a clever neural network for doing object detection in real-time. The model determines what object the camera is seeing in real-time and gives the coordinates of the object, as seen in Figure 3. When using four objects the model needs around two hours of training on our GPU, this approach is fast enough that we are able train for new object the moment we get to the competition.

Perception using 3D vision

A new 3D vision is developed by RoboHub Eindhoven to determine the transformation of objects with respect to the robot. The code is written in C++ and python and communicates over ROS2. With the integration of YOLO V5 object recognition, the software is able to detect the competition objects in a 2D image. These objects will then be processed in a 3D point cloud using various algorithms and filters. After processing the 3D data, the transformation of each object is published in ROS2.

Manipulation

A lite6 robotic manipulator is mounted on top of the AGV for the pick and place functionality. Designed with six axes, Lite 6 is perfect for simple, repetitive and monotonous tasks. It provides the speed and precision manufacturers require, meanwhile ensures quality and accuracy. The flexibility of Lite 6 allows manufacturers to optimize workflow, increase productivity, reduce floor space utilization, lower production costs.

Barrier detection

We have also developed barrier tape detection which is able to the detect the line on the ground and transfer the location into the coordinate system of the robot. This will be detected by the main camera attached to the gripper of the robot. This one will point to the ground while driving. Currently the plan is to only detect the lines in the driving direction. Our robot does also sometimes drive backwards so a camera on the back might be needed as well but for now we've constrained this development to one camera. The new development still needs to be integrated into the state machine. We are not able yet to draw the line in the map to actually drive around it.

Focus and Relevance

There are a wide range of industrial applications for autonomous mobile manipulation, we focus our education and research mainly on the manufacturing and logistic domains.

Industry

We contribute to the ambitions of the Dutch smart industry agenda. We collaborate with several companies where we use our platform as a showcase to explain how logistic and manufacturing companies can benefit from mobile robots in their warehouses and factory floors. We are also involved in research project that are funded by the dutch government and are in close collaboration with industry partners. Such a project is the 'Fieldlab Flexible Manufacturing' where mobile manipulating robots contribute to a flexible manufacturing line by delivering parts just on time at the specific (automated) assembly stations, where all these tasks are strongly related to Industry 4.0.

Research

Our current and future research aims at multiple directions, we aim to have adaptive multi-robot systems that are able to autonomously operate in these complex and diverse environments. Think of industrial tasks where multiple robots navigate in a single warehouse and collaboratively transport the required parts in an optimal way, where robots exchange products during transport. We also are focusing on smart/dynamic path-planning, based on the robots experience. Here high and low level traffic rules can not only be pre-programmed, but also should arise on given knowledge of the environment. Furthermore, we work on a set of robot-safety related issues, as on the natural interaction between humans and robots.

First step in automation

Taking the first step in automation is a difficult and often can be a scary step to take if you don't know where to begin. We want to make this first step more accessible with small projects by advising companies and by possibly providing a pre-study, a proof of concept or by executing experiments. This can be done a lot cheaper and a lot more accessible than with a big company. The result of this will be constrained to the 'first step'. After this process we will suggest companies which we have gotten to know over the years who could execute the following steps in automation.

Education

First of all we use this competition to motivate and challenge our engineering students to achieve a higher and more professional level in their engineering education. By performing such a project the students get highly motivated, apply their knowledge and push their boundaries to acquire new knowledge to solve the given problems. In addition to the technical research challenges we as a team also focus on getting younger people involved into robotics. Our goal is to show the impact that technology can have in our daily lives. During the last year we visited several events where we give young children (and their parents) the opportunity to control our robot. Furthermore we visited several (primary) schools to give demonstrations to inspire the children.

Future work

For this years competition we will still have the focus on making the switch from ROS to ROS2. In addition to switching to ROS2, we will also be working on implementing some newly created modules into the robot. The newly developed 3D vision, the newly developed barrier tape collision avoidance, and our new robotic manipulator. We are still working on our new robot SLICK which will be used during the competitions in 2023. Some of the most important improvements we are working on are: new adaptive gripper methods, ROS2, and new low-level and high-level control. We are planning to publish more details on this robot soon, if teams need help with the development of their own platform, we are happy to help! Video's of our platform in action is available at our YouTube Channel. Additional team information can be found at our RoboHub website. Furthermore, all software will be published on the teams GitHub page.

References

1. Alers, Sjriek, et al. "How to win RoboCup@Work? The Swarmlab@Work approach revealed" Robot Soccer World Cup. Springer, Berlin, Heidelberg, 2013.
2. Quigley, Morgan, et al. "ROS: an open-source Robot Operating System." ICRA workshop on open source software. Vol. 3. No. 3.2. 2009.
3. Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
4. Röswmann, Christoph, Frank Hoffmann, and Torsten Bertram. "Planning of multiple robot trajectories in distinctive topologies." Mobile Robots (ECMR), 2015 European Conference on. IEEE, 2015.
5. Najafi, E., T. Laugs, P. Negrete Rubio, and S. Alers. "An implementation of AutomationML for an Industry 4.0 case study: RoboCup@ Work." In 2019 20th International Conference on Research and Education in Mechatronics (REM), pp. 1-6. IEEE, 2019.
6. Grieves, Michael. "Digital twin: manufacturing excellence through virtual factory replication." White paper 1 (2014): 1-7.