ETEleftherios Triantafyllidis

Eleftherios Triantafyllidis

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Eleftherios Triantafyllidis has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Computational methods for circular design with non-standard materials: Systematic review and future directions

    by Beril Önalan, Ioanna Mitropoulou, Eleftherios Triantafyllidis, Jens Hunhevicz, Catherine De Wolf

    Computational design and optimization methods play a crucial role in early stage design by allowing the incorporation of reclaimed components, fostering resource reuse, and minimizing waste. However, to advance the field of computer-aided material reuse and support its integration into circular construction practices, there is a pressing need for a comprehensive overview of the available methods and their applications. We address this gap by conducting a systematic review of the literature on the role of computational design in facilitating the reuse of building elements, followed by analyzing the interrelationships between optimization methods, materials, and geometric dimensions of reclaimed materials. We then synthesize the identified approaches, offering guidelines that assist stakeholders in selecting suitable computational methodologies for integrating non-standard materials into design processes. Our findings highlight current knowledge gaps in algorithm scalability, performance integration, and the advancement of hybrid computational methods needed to unlock the full potential of computational design for a circular built environment.


  • Open Access

    Hybrid hierarchical learning for solving complex sequential tasks using the robotic manipulation network ROMAN

    by Eleftherios Triantafyllidis, Fernando Acero, Zhaocheng Liu, Zhibin Li

    Solving long sequential tasks remains a non-trivial challenge in the field of embodied artificial intelligence. Enabling a robotic system to perform diverse sequential tasks with a broad range of manipulation skills is a notable open problem and continues to be an active area of research. In this work, we present a hybrid hierarchical learning framework, the robotic manipulation network ROMAN, to address the challenge of solving multiple complex tasks over long time horizons in robotic manipulation. By integrating behavioural cloning, imitation learning and reinforcement learning, ROMAN achieves task versatility and robust failure recovery. It consists of a central manipulation network that coordinates an ensemble of various neural networks, each specializing in different recombinable subtasks to generate their correct in-sequence actions, to solve complex long-horizon manipulation tasks. Our experiments show that, by orchestrating and activating these specialized manipulation experts, ROMAN generates correct sequential activations accomplishing long sequences of sophisticated manipulation tasks and achieving adaptive behaviours beyond demonstrations, while exhibiting robustness to various sensory noises. These results highlight the significance and versatility of ROMAN’s dynamic adaptability featuring autonomous failure recovery capabilities, and underline its potential for various autonomous manipulation tasks that require adaptive motor skills.


  • Open Access

    Identifying important sensory feedback for learning locomotion skills

    by Wanming Yu, Chuanyu Yang, Christopher McGreavy, Eleftherios Triantafyllidis, Guillaume Bellegarda, Milad Shafiee, Auke Jan Ijspeert, Zhibin Li

    Robot motor skills can be acquired by deep reinforcement learning as neural networks to reflect state–action mapping. The selection of states has been demonstrated to be crucial for successful robot motor learning. However, because of the complexity of neural networks, human insights and engineering efforts are often required to select appropriate states through qualitative approaches, such as ablation studies, without a quantitative analysis of the state importance. Here we present a systematic saliency analysis that quantitatively evaluates the relative importance of different feedback states for motor skills learned through deep reinforcement learning. Our approach provides a guideline to identify the most essential feedback states for robot motor learning. By using only the important states including joint positions, gravity vector and base linear and angular velocities, we demonstrate that a simulated quadruped robot can learn various robust locomotion skills. We find that locomotion skills learned only with important states can achieve task performance comparable to the performance of those with more states. This work provides quantitative insights into the impacts of state observations on specific types of motor skills, enabling the learning of a wide range of motor skills with minimal sensing dependencies.


  • Metrics for 3D Object Pointing and Manipulation in Virtual Reality: The Introduction and Validation of a Novel Approach in Measuring Human Performance

    by Eleftherios Triantafyllidis, Wenbin Hu, Christopher McGreavy, Zhibin Li

    Assessing the performance of human movements during teleoperation and virtual reality (VR) is a challenging problem, particularly in 3D space, due to complex settings. Despite the presence of a multitude of measurements, a compelling standardized 3D metric is yet missing, aggravating interstudy comparability. Hence, evaluating human performance in virtual environments (VEs) is a long-standing research goal, and a performance metric that combines two or more measurements under one formulation remains largely unexplored, particularly in higher dimensions. The absence of such a metric is primarily attributed to the discrepancies between pointing and manipulation, the complex spatial variables in 3D, and the combination of translational and rotational movements.


  • Open Access

    Study of Multimodal Interfaces and the Improvements on Teleoperation

    by Eleftherios Triantafyllidis, Christopher Mcgreavy, Jiacheng Gu, Zhibin Li

    Research in multimodal interfaces aims to provide immersive solutions and to increase overall human performance. A promising direction is to combine auditory, visual and haptic interaction between the user and the simulated environment. However, no extensive comparison exists to show how combining audiovisuohaptic interfaces would affect human perception and by extent reflected on task performance. Our paper explores this idea and presents a thorough, full-factorial comparison of how all combinations of audio, visual and haptic interfaces affect performance during manipulation. We evaluated how each combination affects the performance in a study (N=25) consisting of manipulation tasks with various difficulties. The overall performance was assessed using both subjective, by assessing cognitive workload and system usability, and objective measurements, by incorporating time and spatial accuracy-based metrics. The results showed that regardless of task complexity, the combination of stereoscopic-vision with the virtual reality headset increased performance across all measurements by 40%, compared to monocular-vision from a generic display monitor. Besides, using haptic feedback improved outcomes by 10% and auditory feedback accounted for approximately 5% improvement.


  • Open Access

    Multimodal Interfaces for Effective Teleoperation

    by Eleftherios Triantafyllidis, Christopher McGreavy, Jiacheng Gu, Zhibin Li

    Research in multi-modal interfaces aims to provide solutions to immersion and increase overall human performance. A promising direction is combining auditory, visual and haptic interaction between the user and the simulated environment. However, no extensive comparisons exist to show how combining audiovisuohaptic interfaces affects human perception reflected on task performance. Our paper explores this idea. We present a thorough, full-factorial comparison of how all combinations of audio, visual and haptic interfaces affect performance during manipulation. We evaluate how each interface combination affects performance in a study (N=25) consisting of manipulating tasks of varying difficulty. Performance is assessed using both subjective, assessing cognitive workload and system usability, and objective measurements, incorporating time and spatial accuracy-based metrics. Results show that regardless of task complexity, using stereoscopic-vision with the VRHMD increased performance across all measurements by 40% compared to monocular-vision from the display monitor. Using haptic feedback improved outcomes by 10% and auditory feedback accounted for approximately 5% improvement.