Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 66 for “"embodied agents"”.

  1. Collaborative embodied agents

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms

    uiuc Repository record for Collaborative embodied agents (opens in a new tab)

  2. Persuasive Embodied Agents: Using Embodied Agents to Change People's Behavior, Beliefs, and Assessments

    Embodied Conversational Agents (i.e., avatars; ECAs) are appearing in increasingly many everyday contexts, such as e-commerce, occupational training, and airport security. Also common to a typical person's daily life is persuasion. Whether being persuaded or persuading, the ability to change …

    arizona-thes Repository record for Persuasive Embodied Agents: Using Embodied Agents to Change People's Behavior, Beliefs, and Assessments (opens in a new tab)

  3. Coalition Formation And Teamwork In Embodied Agents

    Embodied agents are agents acting in the physical world, such as persons, robots, unmanned air or ground vehicles and so on. These types of agents are subject to spatio-temporal constraints, which do not exist for agents acting in a virtual environment. The movement of embodied agents is limited by …

    ucf Repository record for Coalition Formation And Teamwork In Embodied Agents (opens in a new tab)

  4. Towards Generalist Embodied Agents via Representation Learning

    In our dynamic and ever-evolving world, embodied agents for sequential decision-making (SDM) lie at the heart of intelligent behavior in machine learning systems. Just as foundation models in vision and language have revolutionized natural language processing and computer vision through large-scale …

    maryland Repository record for Towards Generalist Embodied Agents via Representation Learning (opens in a new tab)

  5. From Multimodal LLMs to Generalist Embodied Agents

    … large language models (MLLMs) with large-scale embodied experience unlocks their ability to act as generalist embodied agents. While MLLMs provide reasoning abilities and broad world knowledge, finetuning aligns these capabilities with the demands of embodied agents, unlocking their potential to …

    gatech Repository record for From Multimodal LLMs to Generalist Embodied Agents (opens in a new tab)

  6. Recognizing Teamwork Activity In Observations Of Embodied Agents

    … to recognize the likely roles played by agents in teams even before the team action was recognized. Through experimental studies we show that the feature functions and role recognition module significantly increase the recognition accuracy, while allowing arbitrary shuffled inputs and …

    ucf Repository record for Recognizing Teamwork Activity In Observations Of Embodied Agents (opens in a new tab)

  7. Spatial reasoning and planning for deep embodied agents

    … and forecasting outcomes of actions. For embodied agents (e.g. robots) to achieve similar capabilities, they must gain knowledge of the environment transferable to novel scenarios with a limited budget of additional trial and error. Learning-based approaches, such as deep reinforcement …

    oxford Repository record for Spatial reasoning and planning for deep embodied agents (opens in a new tab)

  8. Speech-Driven Gesture Generation of Social Robot and Embodied Agents

    … field of human-computer interaction, embedded agents in virtual agents or social robots are rapidly becoming more widespread. In human-to-human interactions, humans use nonverbal behaviors to express their atti- tudes, emotions, and intentions. Consequently, embedded agents also need this …

    unsw Repository record for Speech-Driven Gesture Generation of Social Robot and Embodied Agents (opens in a new tab)

  9. Emergence of Intelligent Navigation Behavior in Embodied Agents from Massive-Scale Simulation

    … GPUs and machines. We use DD-PPO to train agents for PointGoal navigation (e.g. ‘Go 5 meters north and 10 meters east relative to start’) for the equivalent of 80 years of human experience. This massive-scale training results in near-perfect autonomous navigation in an unseen environment …

    gatech Repository record for Emergence of Intelligent Navigation Behavior in Embodied Agents from Massive-Scale Simulation (opens in a new tab)

  10. Vision and Language Learning: From Image Captioning and Visual Question Answering towards Embodied Agents

    … and language methods to problems involving embodied agents, we present the Matterport3D Simulator, a large-scale interactive reinforcement learning environment constructed from densely-sampled panoramic RGB-D images of 90 real buildings. Using this simulator, which can in future support a …

    anu Repository record for Vision and Language Learning: From Image Captioning and Visual Question Answering towards Embodied Agents (opens in a new tab)

  11. Identity, Form, and Function: Designing Multi-Embodied Agents for Human-Robot Teaming in Virtual Reality

    … multi-embodiment interfaces where artificial agents can take on different forms across physical and virtual environments. While embodiment facilitates communication through non-verbal cues such as appearance, gaze, and gesture, limited research has examined how to design these interfaces for …

    anu Repository record for Identity, Form, and Function: Designing Multi-Embodied Agents for Human-Robot Teaming in Virtual Reality (opens in a new tab)

  12. The Social and Behavioral Influences of Interactions with Virtual Dogs as Embodied Agents in Augmented and Virtual Reality

    Intelligent virtual agents (IVAs) have been researched for years and recently many of these IVAs have become commercialized and widely used by many individuals as intelligent personal assistants. The majority of these IVAs are anthropomorphic, and many are developed to resemble real humans …

    ucf Repository record for The Social and Behavioral Influences of Interactions with Virtual Dogs as Embodied Agents in Augmented and Virtual Reality (opens in a new tab)

  13. Towards a Planning-Based Neural-Symbolic Framework for Egocentric Agent Design

    … the last decade, deep neural networks have given embodied agents many tools that can extract information from environmental data. However, tasks such as reasoning and long-term planning cannot be done effectively using deep neural networks. Symbolic methods, such as automated planning, are still …

    queens Repository record for Towards a Planning-Based Neural-Symbolic Framework for Egocentric Agent Design (opens in a new tab)

  14. Improvisational artificial intelligence for embodied co-creativity

    This dissertation explores embodied agents that can improvise with people in an object-based gestural proto-narrative domain. I study the improvisational action selection problem (the challenge of performing action selection in an open-ended, ill-defined problem space in near real-time based on the …

    gatech Repository record for Improvisational artificial intelligence for embodied co-creativity (opens in a new tab)

  15. Scaling Online Reinforcement Learning In Embodied AI To 64K Steps

    Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in an unfamiliar house initially wouldn't know the locations of objects needed for tasks and might perform inefficiently. However, as it gathers …

    gatech Repository record for Scaling Online Reinforcement Learning In Embodied AI To 64K Steps (opens in a new tab)

  16. Intelligence Through the Lens of Interaction

    … understanding: (1) visual perception and (2) embodied intelligence. To address the first question, I designed experiments to learn visual representations by observing animals and humans interact with the visual world. Further, I investigated the idea of learning perception from hands-on …

    washington Repository record for Intelligence Through the Lens of Interaction (opens in a new tab)

  17. Tailored Computing: Cross-Layer System, Architecture, and Silicon Co-Design for Physical Intelligence

    Physical intelligence -- where embodied agents perceive, reason, plan, and act in the physical world -- is emerging as the next transformative computing platform, offering significant potential impact across robotics, healthcare, manufacturing, and scientific automation. Yet today’s physical …

    gatech Repository record for Tailored Computing: Cross-Layer System, Architecture, and Silicon Co-Design for Physical Intelligence (opens in a new tab)

  18. Advances in embodied control: from Bayesian exploration to interactive full-body motion imitation

    … However, the physical capabilities of embodied agents, such as robots and virtual entities, still lag behind the agility of natural beings. This thesis explores the potential of learning-based methods and control theory to enhance the physical capabilities of artificial agents.</p> …

    oxford Repository record for Advances in embodied control: from Bayesian exploration to interactive full-body motion imitation (opens in a new tab)

  19. Internet-Scale Pretraining Enables Bootstrapping Skill-Specific Supervision for Training Multi-Modal Agents

    … supervision for training multi-modal agents, enabling distillation of novel skills without human labelled data. First, we show how vision–language models can enable converting unlabelled web images into labelled data to teach embodied agents spatial and semantic common-sense reasoning …

    gatech Repository record for Internet-Scale Pretraining Enables Bootstrapping Skill-Specific Supervision for Training Multi-Modal Agents (opens in a new tab)

Page 1 of 4