No abstract

No abstract

Mobile autonomous robots have finally emerged from the confined spaces of structured and controlled indoor environments. To fulfill the promises of ubiquitous robotics in unstructured outdoor environments, robust navigation is a key requirement. The research in the simultaneous localization and mapping (SLAM) community has largely focused on optical sensors to solve this problem, and the fact that the robot is a physical entity has largely been ignored. In this paper, a hierarchical SLAM framework is proposed that takes the interaction of the robot with the environment into account. A sequential Monte Carlo filter is used to generate local map segments with a combination of visual and embodied data associations. Constraints between segments are used to generate globally consistent maps with a focus on suitability for navigation tasks. The proposed method is experimentally verified on two different outdoor robots. The results show that the approach is viable and that the rich modeling of the robot with its environment provides a new modality with the potential for improving existing visual methods and extending the availability of SLAM in domains where visual processing alone is not sufficient.

Simulation is an important step of a robotics project. It helps saving time and resources during the project development phase reducing hardware requirements and field tests deployments. Through simulations it is possible to test algorithms in virtually any environment. As complex robots are usually manged by robotics frameworks, a framework-simulator integration is a powerful tool, which allows design and verification of algorithms implemented straight into frameworks. The Gazebo simulator is already integrated with the Robot Operating System (ROS) endorsing its importance to the robotics community. This paper introduces the integration between the Gazebo simulator and the Robot Construction Kit (Rock) framework to allow a real-time simulation. To export simulation resources, framework components are instantiated and synchronized inside a Gazebo system plugin. Each component is a C++ class implemented separately from others classes. Through this approach new components can be easily integrated to extend the simulation capabilities. An Autonomous Underwater Vehicle (AUV) simulation is presented as a use case of the integration. This use case comprises fluid statics and dynamics simulation, thruster models and an underwater environment visualization.

No abstract