Situational awareness for a reliable collaborative multi-robot system

University of Turku

Mobile robots are set to take on a key role in improving many services, both in the civilian and industrial domains. In particular, UAVs and USVs are already important for environmental monitoring and sensing in both urban, rural and remote environments. In this project, research investigates the underlying technologies in robotics and AI. The development of a robust and resilient collaborative robotic framework holds the potential to establish a paradigm for multi-sensor integration and a more efficient monitoring system. This aims to empower mobile robots to undertake autonomous missions in complex and remote environments. Specifically, the focus is on using them for water monitoring and data collection to aid the development of Digital Twins for integrated water resource management.

This project aims to investigate collaborative situational awareness within a complex environment through the integration of diverse sensor modalities to enhance the reliability of a multi-robot system comprising UAVs, USVs and quadruped robots. We will look at deep learning methodologies for the extraction of keypoints, as well as for the detection and segmentation tasks. Deep learning methodologies are expected to provide a comprehensive understanding of the environmental context, which is essential for the local decision-making processes and navigation capabilities of mobile robots. The essence of the collaboration between UAVs and USVs necessitates the design, development, and deployment of the network or methodology is inherently distributed and secure. This requirement underscores the importance of designing a framework that not only supports the intricate dynamics of multi-robot systems but also ensures the integrity and confidentiality of the data and interactions within the system, thereby safeguarding against potential vulnerabilities and threats in the operational environment. We will carry out missions in the Aura and Teno river environments.

We are looking for a doctoral researcher with a blend of independence and collaboration skills, motivated to work in a multinational and interdisciplinary team on projects involving multi-robot systems and embedded AI. An outstanding master’s degree in computer science, robotics, embedded students, mechatronics, or related fields, including master’s students who will complete their master’s degree in 2024 by the date set by the involved doctoral programme at UTU. Essential skills include proficiency in Python and C++ programming. Experience with machine learning technologies and practical experience with robots is seen as an advantage. Additionally, we value: – Experience with robotics sensors such as LiDARs, Cameras, and IMUs. – Knowledge in LiDAR odometry, Obstacle avoidance, and other related. – Machine learning/Deep learning in a distributed agent system – Familiarity with ROS for robotics programming. -Hands on practice of multi-modal sensor calibration. Candidates should be prepared to engage in interdisciplinary research, demonstrating the ability to integrate methods and insights across different fields, and leverage collaboration opportunities.

TBA

Department of Computing, Faculty of Technology

Prof. Tomi Westerlund, UTU

Assoc. Prof. Wallace Moreira Bessa, UTU

TBA

TBA