Dissertation defence (Information and Communication Technology): MSc Xianjia Yu
Time
2.10.2024 at 12.00 - 16.00
MSc Xianjia Yu defends the dissertation in Information and Communication Technology titled “Federated Learning Enhanced Multi-modal Sensing and Perception in a Collaborative Multi-robot System” at the University of Turku on 2 October 2024 at 12.00 (University of Turku, Educarium, EDU3, Assistentinkatu 5, Turku).
Opponent: Associate Professor John Folkesson (KTH Royal Institute of Technology, Sweden)
Custos: Professor Tomi Westerlund (University of Turku)
Doctoral Dissertation at UTUPub: https://urn.fi/URN:ISBN:978-951-29-9888-3
***
Summary of the Doctoral Dissertation:
Multi-robot systems are increasingly essential across a wide array of sectors, such as industrial automation, transportation, and search and rescue. The key to these systems lies in the capabilities of agents to collaboratively perceive, comprehend, and reason about their surroundings, thereby attaining advanced situational awareness. Recent advances in artificial intelligence, especially in the field of deep learning (DL), have increased the ability of multi-robot systems to effectively utilize and understand data produced by various sensors.
Despite numerous efforts to integrate multiple sensors, this area remains complex and challenging due to heterogeneous, unstructured, and cluttered deployment environments. Furthermore, these operating scenarios vary considerably across different settings, including hospitals, private residences, ports, and other contexts privacy and security prevail. This dissertation addresses these
challenges by integrating multi-modal sensors to enhance high-level robot perception across multiple agents while ensuring security and privacy through Federated Learning (FL). FL, a privacy-preserving DL method, enabling secure knowledge sharing among robots via model transfers instead of direct data exchanges. Various types of sensors, such as LiDAR, visual sensors, Inertial Measurement Units (IMUs), and Ultra-Wideband (UWB) technology, are employed to enhance environmental perception. FL is utilized in visual obstacle avoidance within autonomous robot navigation as a case to demonstrate its effectiveness
Opponent: Associate Professor John Folkesson (KTH Royal Institute of Technology, Sweden)
Custos: Professor Tomi Westerlund (University of Turku)
Doctoral Dissertation at UTUPub: https://urn.fi/URN:ISBN:978-951-29-9888-3
***
Summary of the Doctoral Dissertation:
Multi-robot systems are increasingly essential across a wide array of sectors, such as industrial automation, transportation, and search and rescue. The key to these systems lies in the capabilities of agents to collaboratively perceive, comprehend, and reason about their surroundings, thereby attaining advanced situational awareness. Recent advances in artificial intelligence, especially in the field of deep learning (DL), have increased the ability of multi-robot systems to effectively utilize and understand data produced by various sensors.
Despite numerous efforts to integrate multiple sensors, this area remains complex and challenging due to heterogeneous, unstructured, and cluttered deployment environments. Furthermore, these operating scenarios vary considerably across different settings, including hospitals, private residences, ports, and other contexts privacy and security prevail. This dissertation addresses these
challenges by integrating multi-modal sensors to enhance high-level robot perception across multiple agents while ensuring security and privacy through Federated Learning (FL). FL, a privacy-preserving DL method, enabling secure knowledge sharing among robots via model transfers instead of direct data exchanges. Various types of sensors, such as LiDAR, visual sensors, Inertial Measurement Units (IMUs), and Ultra-Wideband (UWB) technology, are employed to enhance environmental perception. FL is utilized in visual obstacle avoidance within autonomous robot navigation as a case to demonstrate its effectiveness
University Communications