Task and data allocation in autonomous mobile robots

Abstract

The increasing need for AMR in service industries, particularly those requiring precision and efficiency, such as coffee preparation, emphasizes the importance of advanced task and data allocation methods that improve system performance and adaptability. Service-oriented AMRs have to navigate environments that demand not only operational efficiency but also the capacity to interact dynamically with complex, ever-changing environments and customer needs.

This research project focuses on simulating a barista robot's operational capabilities, using the ROS to painstakingly organize the robot's operations in a simulated coffee shop setting. The simulation uses both the RViz and Gazebo platforms to provide a thorough visualization of the robot's operational movements, providing insights into its motion planning, environmental interaction, and task execution capabilities.

The integration of these two simulation environments reinforces the project's primary goal, which is to improve understanding and use of AMRs in service-based tasks using advanced simulation approaches. This method not only helps to identify possible operational issues and areas for algorithmic improvement, but it also paves the way for future research on adaptive and autonomous robot systems that can learn from and adapt to their operational contexts.