BEGIN:VCALENDAR PRODID:-//eluceo/ical//2.0/EN VERSION:2.0 CALSCALE:GREGORIAN BEGIN:VEVENT UID:18d5ae8edc9198d277b3d829d63933ba DTSTAMP:20260915T211847Z SUMMARY:Ayesha Jena's Licentiate Seminar DESCRIPTION:Contact: ayesha.jena@cs.lth.se\n\nThesis title: \;Towards P roactive Support for Human-Robot CollaborationAuthor: \;Ayesha Jena\, Department of Computer Science\, Lund UniversityFaculty opponent: Prof. Te resa Zielińska\, Warsaw University of TechnologyExaminer: \;Senior Le cturer Emelie Engström\, LTHSupervisor: Senior Lecturer Elin Anna Topp\, LTHCo-supervisor: \;Prof. Jacek Malec\, LTH &\; Senior Lecturer Bj örn Olofsson\, LTHDate and time: Tuesday 23 September at 13:15Location:&n bsp\;E:C\, E-huset\, LTH\, Klas Anshelms väg 10/Ole Römers väg 3\, Lund Link to the thesis at LU Research Portal \;AbstractAs robots increasin gly integrate into our social environments\, from factories to social spac es\, there is a growing need to find ways to effectively collaborate in th ese dynamic environments. However\, current robotics research is mostly ai med towards task and environment specific programming. Even the state-of-t he-art collaborative robotics technologies lack or have a very rudimentary understanding of the multimodal methods used by human teammates to commun icate in real-time. This leads to an increased workload for human operator s and becomes a critical problem that limits robots to operate in dynamic environments. We focus on one such dynamic setting of search and rescue (S AR) scenarios. In order to achieve effective collaboration between humans and robots in this scenario\, there is a need for robots to naturally unde rstand human intentions through the interpretation of multimodal communica tion cues such as gaze\, gesture\, and contextual signals in real-time. Th is research aims towards achieving mixed-initiative interaction by address ing the gap of robots proactively collaborating with humans through a two step process. The first part of the thesis\, following a Design Science ap proach\, explores the use and integration of non-verbal communication cues to conduct collaborative tasks in a SAR environment. Through designing th e human-in-the-loop collaboration system CueSense and testing different co llaboration strategies\, we investigate when and how humans and robots can dynamically share control during missions. This modular system is capable of tracking gaze to predict task focus and gesture inputs for nuanced int ent interpretation. This is validated through user studies where participa nts work alongside the system in different collaborative settings for a si mulated search-and-rescue scenario. The results show that the system succe ssfully assists users in the task and improves task efficiency\, performan ce\, and reduces mental workload. The second part of the thesis focuses on intention recognition as a foundation of proactive support and mixed-init iative interaction in human robot collaboration. We present an extensive r eview of the literature on intention recognition and identify gaps and cha llenges in implementing robust intention recognition systems in robotics. In summary\, we focus our research on communication modalities\, interface s\, and intention recognition for mixed-initiative interaction to allow ef ficient and seamless human robot collaboration in dynamic high-stakes scen arios. \;\n\nMore information about the event: https://www.cs.lth.se/e n/calendar/ayesha-jenas-licentiate-seminar-0 DTSTART;TZID=GMT:20250923T111500 DTEND;TZID=GMT:20250923T111500 LOCATION:E:C\, E-huset\, LTH\, Ole Römers väg 3\, Lund END:VEVENT END:VCALENDAR