ROS2 has adopted DDS/RTPS as its middleware, increasing the performance and feature set over ROS1. DDS exposes many QoS parameters to adapt the middleware to very different scenarios, allowing easy configuration using XML files. This presentation will show how to set up ROS2 for several interesting scenarios.

RoboWare is a development kit specifically designed for ROS. It provides an integrated development environment, which has general purpose IDE functions： code editing, building and debugging; It fully supports ROS, including the creation and management of workspace, packages, libraries, nodes, msg/srv/action/launch/yaml/urdf files, etc. RoboWare supports “POD (Product Oriented Design)” development, it has a graphical designer for robot hardware architecture, the design diagram can be automatically exported as a ROS workspace for further development. It also provides a GUI development framework, which has plenty of robot-related controls and is cross-platform

Daimler (Mercedes-Benz) has a long history on research and development on ADAS systems and autonomous driving. Today’s increasing complex requirements on sensors, algorithms and fusion put high demands on the underlying software framework. In this talk, the group Pattern Recognition and Cameras of Daimler Research and Development showcase their latest research vehicle. Additionally, a detailed look on an implemented multi-sensor synchronization system is given. Findings and lessons learned as well as tool modifications and added functionality will be discussed as well. The audience will get insights on data handling in the context of high data throughput.

As AMZ Racing Driverless, we’re competing in the first Formula Student Driverless competition with «flüela», an electric 4WD car with high wheel torque and a lightweight design (0-100km/h in 1.9s), developed by our team in 2015. To race autonomously, the car has been extended with a LiDAR, a self-developed stereo visual-inertial system, an IMU, a GPS and a velocity sensor. We chose to use ROS Indigo on our Master Slave computing system, as it provided a robust, flexible framework to interface the different components of our Autonomous System. Furthermore we made extensive use of its logging capabilities and powerful visualization and simulation tools.

In this session we will share our experience and describe our approach to learning-based control. We do this for underwater (marine) environments where we want to approximate some of the hydrodynamic factors in 6 degrees of freedom. Our work addresses “learning to swim” via the automatic synthesis of swimming controllers for the AQUA platform: a six legged autonomous underwater vehicle. First, we will describe our approaches for simulating the underwater dynamics of the AQUA robot. This description includes our modelling choices and the integration into the Gazebo simulator. Second, we will describe the software interfaces we developed, based on the ROS framework, for testing learning algorithms in the simulation environment. Finally, we will show how ROS facilitated the use of our software on physical robots, and discuss the current research that our software has enabled.

We introduce ROS.NET, a series of C# projects that allow a managed .NET application to communicate with traditional ROS nodes, we then present a wrapper for it that allows Unity applications to integrate with ROS. Unity is a game design tool which can be used as a 3d rendering engine and a physics engine. We present two applications of combining ROS and Unity, one in the form of a ROS Virtual Reality engine, usable for robot visualization and control, and another in the form of a Project Tango device driver, which can also be used for visualization and control, and which we plan to augment for 3d scanning and reconstruction.

This proposal covers the development of a framework for the automated generation of efficient tool path plans from 3D geometry for industrial processes such as painting or sanding. The work is organized into three main software modules. The first module analyzes 3D data to extract features salient to the desired process. The second module works on these features to generate tool paths that optimally perform the process on individual features. The final module, sequence planning, determines the optimal ordering for processing the entire part.

At PAL Robotics, we use the ROS framework to design software that is modular, configurable and testable. All of our robots, from small mobile bases to human-sized bipeds, are the result of a process of continual review, adaption and improvement. In this presentation, we will reveal some of the lessons we’ve learned when developing our software and how to design modular components for our robots. The control software architecture, based on OROCOS and ros_control, will be presented together with the ros_controllers we’re currently using. We will focus, in particular, on Whole Body Control as an efficient redundancy resolution controller that allows operators to generate real-time motions on anthropomorphic robots.