LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 13

Search options

  1. Book ; Online: On the Effectiveness of Retrieval, Alignment, and Replay in Manipulation

    Di Palo, Norman / Johns, Edward

    2023  

    Abstract: Imitation learning with visual observations is notoriously inefficient when addressed with end-to-end behavioural cloning methods. In this paper, we explore an alternative paradigm which decomposes reasoning into three phases. First, a retrieval phase, ... ...

    Abstract Imitation learning with visual observations is notoriously inefficient when addressed with end-to-end behavioural cloning methods. In this paper, we explore an alternative paradigm which decomposes reasoning into three phases. First, a retrieval phase, which informs the robot what it can do with an object. Second, an alignment phase, which informs the robot where to interact with the object. And third, a replay phase, which informs the robot how to interact with the object. Through a series of real-world experiments on everyday tasks, such as grasping, pouring, and inserting objects, we show that this decomposition brings unprecedented learning efficiency, and effective inter- and intra-class generalisation. Videos are available at https://www.robot-learning.uk/retrieval-alignment-replay.

    Comment: Published in IEEE Robotics and Automation Letters (RA-L). (Accepted December 2023)
    Keywords Computer Science - Robotics ; Computer Science - Machine Learning
    Subject code 629
    Publishing date 2023-12-19
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Article ; Online: Enhanced optical conductivity and many-body effects in strongly-driven photo-excited semi-metallic graphite.

    Sidiropoulos, T P H / Di Palo, N / Rivas, D E / Summers, A / Severino, S / Reduzzi, M / Biegert, J

    Nature communications

    2023  Volume 14, Issue 1, Page(s) 7407

    Abstract: The excitation of quasi-particles near the extrema of the electronic band structure is a gateway to electronic phase transitions in condensed matter. In a many-body system, quasi-particle dynamics are strongly influenced by the electronic single-particle ...

    Abstract The excitation of quasi-particles near the extrema of the electronic band structure is a gateway to electronic phase transitions in condensed matter. In a many-body system, quasi-particle dynamics are strongly influenced by the electronic single-particle structure and have been extensively studied in the weak optical excitation regime. Yet, under strong optical excitation, where light fields coherently drive carriers, the dynamics of many-body interactions that can lead to new quantum phases remain largely unresolved. Here, we induce such a highly non-equilibrium many-body state through strong optical excitation of charge carriers near the van Hove singularity in graphite. We investigate the system's evolution into a strongly-driven photo-excited state with attosecond soft X-ray core-level spectroscopy. We find an enhancement of the optical conductivity of nearly ten times the quantum conductivity and pinpoint it to carrier excitations in flat bands. This interaction regime is robust against carrier-carrier interaction with coherent optical phonons acting as an attractive force reminiscent of superconductivity. The strongly-driven non-equilibrium state is markedly different from the single-particle structure and macroscopic conductivity and is a consequence of the non-adiabatic many-body state.
    Language English
    Publishing date 2023-11-16
    Publishing country England
    Document type Journal Article
    ZDB-ID 2553671-0
    ISSN 2041-1723 ; 2041-1723
    ISSN (online) 2041-1723
    ISSN 2041-1723
    DOI 10.1038/s41467-023-43191-5
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  3. Book ; Online: Language Models as Zero-Shot Trajectory Generators

    Kwon, Teyun / Di Palo, Norman / Johns, Edward

    2023  

    Abstract: Large Language Models (LLMs) have recently shown promise as high-level planners for robots when given access to a selection of low-level skills. However, it is often assumed that LLMs do not possess sufficient knowledge to be used for the low-level ... ...

    Abstract Large Language Models (LLMs) have recently shown promise as high-level planners for robots when given access to a selection of low-level skills. However, it is often assumed that LLMs do not possess sufficient knowledge to be used for the low-level trajectories themselves. In this work, we address this assumption thoroughly, and investigate if an LLM (GPT-4) can directly predict a dense sequence of end-effector poses for manipulation skills, when given access to only object detection and segmentation vision models. We study how well a single task-agnostic prompt, without any in-context examples, motion primitives, or external trajectory optimisers, can perform across 26 real-world language-based tasks, such as "open the bottle cap" and "wipe the plate with the sponge", and we investigate which design choices in this prompt are the most effective. Our conclusions raise the assumed limit of LLMs for robotics, and we reveal for the first time that LLMs do indeed possess an understanding of low-level robot control sufficient for a range of common tasks, and that they can additionally detect failures and then re-plan trajectories accordingly. Videos, code, and prompts are available at: https://www.robot-learning.uk/language-models-trajectory-generators.

    Comment: 19 pages, 21 figures
    Keywords Computer Science - Robotics ; Computer Science - Artificial Intelligence ; Computer Science - Computation and Language ; Computer Science - Human-Computer Interaction ; Computer Science - Machine Learning
    Subject code 004
    Publishing date 2023-10-17
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Book ; Online: Enhanced optical conductivity and many-body effects in strongly-driven photo-excited semi-metallic graphite

    Sidiropoulos, T. P. H. / Di Palo, N. / Rivas, D. E. / Summers, A. / Severino, S. / Reduzzi, M. / Biegert, J.

    2023  

    Abstract: The excitation of quasi-particles near the extrema of the electronic band structure is a gateway to electronic phase transitions in condensed matter. In a many-body system, quasi-particle dynamics are strongly influenced by the electronic single-particle ...

    Abstract The excitation of quasi-particles near the extrema of the electronic band structure is a gateway to electronic phase transitions in condensed matter. In a many-body system, quasi-particle dynamics are strongly influenced by the electronic single-particle structure and have been extensively studied in the weak optical excitation regime. Yet, under strong optical excitation, where light fields coherently drive carriers, the dynamics of many-body interactions that can lead to new quantum phases remain largely unresolved. Here, we induce such a highly non-equilibrium many-body state through strong optical excitation of charge carriers near the van Hove singularity in graphite. We investigate the system's evolution into a strongly-driven photo-excited state with attosecond soft X-ray core-level spectroscopy. Surprisingly, we find an enhancement of the optical conductivity of nearly ten times the quantum conductivity and pinpoint it to carrier excitations in flat bands. This interaction regime is robust against carrier-carrier interaction with coherent optical phonons acting as an attractive force reminiscent of superconductivity. The strongly-driven non-equilibrium state is markedly different from the single-particle structure and macroscopic conductivity and is a consequence of the non-adiabatic many-body state.
    Keywords Condensed Matter - Materials Science
    Subject code 535
    Publishing date 2023-08-11
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  5. Book ; Online: SAFARI

    Di Palo, Norman / Johns, Edward

    Safe and Active Robot Imitation Learning with Imagination

    2020  

    Abstract: One of the main issues in Imitation Learning is the erroneous behavior of an agent when facing out-of-distribution situations, not covered by the set of demonstrations given by the expert. In this work, we tackle this problem by introducing a novel ... ...

    Abstract One of the main issues in Imitation Learning is the erroneous behavior of an agent when facing out-of-distribution situations, not covered by the set of demonstrations given by the expert. In this work, we tackle this problem by introducing a novel active learning and control algorithm, SAFARI. During training, it allows an agent to request further human demonstrations when these out-of-distribution situations are met. At deployment, it combines model-free acting using behavioural cloning with model-based planning to reduce state-distribution shift, using future state reconstruction as a test for state familiarity. We empirically demonstrate how this method increases the performance on a set of manipulation tasks with respect to passive Imitation Learning, by gathering more informative demonstrations and by minimizing state-distribution shift at test time. We also show how this method enables the agent to autonomously predict failure rapidly and safely.
    Keywords Computer Science - Robotics ; Computer Science - Machine Learning
    Subject code 006
    Publishing date 2020-11-18
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Book ; Online: Demonstrate Once, Imitate Immediately (DOME)

    Valassakis, Eugene / Papagiannis, Georgios / Di Palo, Norman / Johns, Edward

    Learning Visual Servoing for One-Shot Imitation Learning

    2022  

    Abstract: We present DOME, a novel method for one-shot imitation learning, where a task can be learned from just a single demonstration and then be deployed immediately, without any further data collection or training. DOME does not require prior task or object ... ...

    Abstract We present DOME, a novel method for one-shot imitation learning, where a task can be learned from just a single demonstration and then be deployed immediately, without any further data collection or training. DOME does not require prior task or object knowledge, and can perform the task in novel object configurations and with distractors. At its core, DOME uses an image-conditioned object segmentation network followed by a learned visual servoing network, to move the robot's end-effector to the same relative pose to the object as during the demonstration, after which the task can be completed by replaying the demonstration's end-effector velocities. We show that DOME achieves near 100% success rate on 7 real-world everyday tasks, and we perform several studies to thoroughly understand each individual component of DOME. Videos and supplementary material are available at: https://www.robot-learning.uk/dome .

    Comment: To be published at IROS 2022. 7 figures, 8 pages. Videos and supplementary material are available at: https://www.robot-learning.uk/dome
    Keywords Computer Science - Robotics ; Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition
    Subject code 004 ; 629
    Publishing date 2022-04-06
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  7. Book ; Online: Coarse-to-Fine for Sim-to-Real

    Valassakis, Eugene / Di Palo, Norman / Johns, Edward

    Sub-Millimetre Precision Across Wide Task Spaces

    2021  

    Abstract: In this paper, we study the problem of zero-shot sim-to-real when the task requires both highly precise control with sub-millimetre error tolerance, and wide task space generalisation. Our framework involves a coarse-to-fine controller, where ... ...

    Abstract In this paper, we study the problem of zero-shot sim-to-real when the task requires both highly precise control with sub-millimetre error tolerance, and wide task space generalisation. Our framework involves a coarse-to-fine controller, where trajectories begin with classical motion planning using ICP-based pose estimation, and transition to a learned end-to-end controller which maps images to actions and is trained in simulation with domain randomisation. In this way, we achieve precise control whilst also generalising the controller across wide task spaces, and keeping the robustness of vision-based, end-to-end control. Real-world experiments on a range of different tasks show that, by exploiting the best of both worlds, our framework significantly outperforms purely motion planning methods, and purely learning-based methods. Furthermore, we answer a range of questions on best practices for precise sim-to-real transfer, such as how different image sensor modalities and image feature representations perform.

    Comment: To be published at IROS 2021. 8 pages, 6 figures
    Keywords Computer Science - Robotics ; Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Machine Learning
    Subject code 006
    Publishing date 2021-05-24
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  8. Book ; Online: Towards A Unified Agent with Foundation Models

    Di Palo, Norman / Byravan, Arunkumar / Hasenclever, Leonard / Wulfmeier, Markus / Heess, Nicolas / Riedmiller, Martin

    2023  

    Abstract: Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like behaviour, in text form, among many others. In this work, we ... ...

    Abstract Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like behaviour, in text form, among many others. In this work, we investigate how to embed and leverage such abilities in Reinforcement Learning (RL) agents. We design a framework that uses language as the core reasoning tool, exploring how this enables an agent to tackle a series of fundamental RL challenges, such as efficient exploration, reusing experience data, scheduling skills, and learning from observations, which traditionally require separate, vertically designed algorithms. We test our method on a sparse-reward simulated robotic manipulation environment, where a robot needs to stack a set of objects. We demonstrate substantial performance improvements over baselines in exploration efficiency and ability to reuse data from offline datasets, and illustrate how to reuse learned skills to solve novel tasks or imitate videos of human experts.
    Keywords Computer Science - Robotics ; Computer Science - Artificial Intelligence ; Computer Science - Machine Learning
    Subject code 004 ; 006
    Publishing date 2023-07-18
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  9. Article ; Online: Reconstruction of ultrafast exciton dynamics with a phase-retrieval algorithm.

    Dolso, Gian Luca / Moio, Bruno / Inzani, Giacomo / Di Palo, Nicola / Sato, Shunsuke A / Borrego-Varillas, Rocío / Nisoli, Mauro / Lucchini, Matteo

    Optics express

    2022  Volume 30, Issue 8, Page(s) 12248–12267

    Abstract: The first step to gain optical control over the ultrafast processes initiated by light in solids is a correct identification of the physical mechanisms at play. Among them, exciton formation has been identified as a crucial phenomenon which deeply ... ...

    Abstract The first step to gain optical control over the ultrafast processes initiated by light in solids is a correct identification of the physical mechanisms at play. Among them, exciton formation has been identified as a crucial phenomenon which deeply affects the electro-optical properties of most semiconductors and insulators of technological interest. While recent experiments based on attosecond spectroscopy techniques have demonstrated the possibility to observe the early-stage exciton dynamics, the description of the underlying exciton properties remains non-trivial. In this work we propose a new method called extended Ptychographic Iterative engine for eXcitons (ePIX), capable of reconstructing the main physical properties which determine the evolution of the quasi-particle with no prior knowledge of the exact relaxation dynamics or the pump temporal characteristics. By demonstrating its accuracy even when the exciton dynamics is comparable to the pump pulse duration, ePIX is established as a powerful approach to widen our knowledge of solid-state physics.
    Language English
    Publishing date 2022-04-26
    Publishing country United States
    Document type Journal Article
    ZDB-ID 1491859-6
    ISSN 1094-4087 ; 1094-4087
    ISSN (online) 1094-4087
    ISSN 1094-4087
    DOI 10.1364/OE.451759
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  10. Book ; Online: Probing the energy conversion pathways between light, carriers and lattice in real time with attosecond core-level spectroscopy

    Sidiropoulos, T. P. H. / Di Palo, N. / Rivas, D. E. / Severino, S. / Reduzzi, M. / Nandy, B. / Bauerhenne, B. / Krylow, S. / Vasileiadis, T. / Danz, T. / Elliott, P. / Sharma, S. / Dewhurst, K. / Ropers, C. / Joly, Y. / Garcia, K. M. E. / Wolf, M. / Ernstorfer, R. / Biegert, J.

    2021  

    Abstract: Detection of the energy conversion pathways, between photons, charge carriers, and the lattice is of fundamental importance to understand fundamental physics and to advance materials and devices. Yet, such insight remains incomplete due to experimental ... ...

    Abstract Detection of the energy conversion pathways, between photons, charge carriers, and the lattice is of fundamental importance to understand fundamental physics and to advance materials and devices. Yet, such insight remains incomplete due to experimental challenges in disentangling the various signatures on overlapping time scales. Here, we show that attosecond core-level X-ray spectroscopy can identify these interactions with attosecond precision and across a picosecond range. We demonstrate this methodology on graphite since its investigation is complicated by a variety of mechanisms occurring across a wide range of temporal scales. Our methodology reveals, through the simultaneous real-time detection of electrons and holes, the different dephasing mechanisms for each carrier type dependent on excitation with few-cycle-duration light fields. These results demonstrate the general ability of our methodology to detect and distinguish the various dynamic contributions to the flow of energy inside materials on their native time scales.
    Keywords Condensed Matter - Materials Science ; Physics - Applied Physics ; Physics - Instrumentation and Detectors ; Physics - Optics
    Publishing date 2021-10-13
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top