Welcome to the upgraded MacSphere! We're putting the finishing touches on it; if you notice anything amiss, email macsphere@mcmaster.ca

About MacSphere

MacSphere is McMaster University's Institutional Repository. MacSphere brings together the institution's scholarly works under one umbrella to preserve and provide ongoing open access to them. MacSphere works have been selected and deposited by members of the McMaster community as part of our collective committment to sharing our knowledge with the world.

MacSphere is supported and hosted by the McMaster University Libraries.

To contribute, sign on to MacSphere with your McMaster Account. If you have any questions, refer to the user guide or contact the MacSphere Support Team for assistance.

Students wishing to deposit their PhD or Masters thesis, please follow the instructions outlined by the School of Graduate Studies.

Discover

Communities in MacSphere

Select a community to browse its collections.

Recent Submissions

  • Thumbnail Image
    Item type: Item ,
    RISE brief 13: Communities of practice
    (2019-08) Waddell, K; Lavis, JN
    Key insights to support Ontario Health Teams in their work related to communities of practice.
  • Thumbnail Image
    Item type: Item ,
  • Thumbnail Image
    Item type: Item ,
  • Thumbnail Image
    Item type: Item ,
    Learning Social Robot Navigation From Real-World Demonstrations With a Multi-Model Evaluation of Social Compliance
    (2026) Taherifard, Fatemeh; Geiskkovitch, Denise; Stoyanov, Todor; Computing and Software
    Autonomous mobile robot navigation in human-populated environments requires more than simple obstacle avoidance; it demands adherence to uid social norms. This thesis investigates the e cacy of Learning from Demonstration (LfD) for developing socially compliant navigation policies. Utilizing a Turtlebot4 platform, a real-world dataset was collected on the McMaster University campus to train three distinct imitation learning architectures: Behavioral Cloning (BC), Generative Adversarial Imitation Learning (GAIL), and Di usion Policies. The models were evaluated using a multi-modal approach involving simulation metrics, video-based behavioral analysis, and human-robot interaction (HRI) surveys. Quantitative results indicated that while BC achieved high positional accuracy, it lacked robustness under distribution shifts. The Augmented Di usion Policy emerged as the superior architecture, maintaining a 91.7% success rate while achieving the lowest "Social Work" score, signifying minimal disruption to human tra c. However, HRI survey data revealed a "safety-perception paradox," where the robot's prioritization of social distance led to increased wall collisions, negatively impacting user perception of path consistency. This research concludes that social compliance is a multifaceted optimization problem requiring a balance between human-awareness, spatial safety, and mechanical predictability.
  • Thumbnail Image
    Item type: Item ,