Curriculum-based humanoid robot identification using large-scale human motion database [PDF]
Frontiers in Robotics and AI, 2023 Identifying an accurate dynamics model remains challenging for humanoid robots. The difficulty is mainly due to the following two points. First, a good initial model is required to evaluate the feasibility of motions for data acquisition.
Sunhwi Kang +4 more
doaj +2 more sources
Multi-Humanoid Robot Arm Motion Imitation and Collaboration Based on Improved Retargeting [PDF]
BiomimeticsHuman–robot interaction (HRI) is a key technology in the field of humanoid robotics, and motion imitation is one of the most direct ways to achieve efficient HRI.
Xisheng Jiang +7 more
doaj +2 more sources
Skeleton-aware networks for deep motion retargeting [PDF]
ACM Transactions on Graphics, 2020 We introduce a novel deep learning framework for data-driven motion retargeting between skeletons, which may have different structure, yet corresponding to homeomorphic graphs. Importantly, our approach learns how to retarget without requiring any explicit pairing between the motions in the training set. We leverage the fact that
Daniel Cohen-Or +2 more
exaly +3 more sources
Learning character-agnostic motion for motion retargeting in 2D [PDF]
ACM Transactions on Graphics, 2019 Analyzing human motion is a challenging task with a wide variety of applications in computer vision and in graphics. One such application, of particular importance in computer animation, is the retargeting of motion from one performer to another.
Daniel Cohen-Or, Dani Lischinski
exaly +3 more sources
Environment-sensitive motion modelling in healthcare with synthetic retargeting [PDF]
Digital HealthObjective To address the critical data scarcity and privacy constraints that limit video-based motor behaviour assessment in clinical settings through a synthetic data generation framework, enabling robust human detection with high fidelity across ...
Xiaodong Guan +5 more
doaj +2 more sources
Motion Strategy Generation Based on Multimodal Motion Primitives and Reinforcement Learning Imitation for Quadruped Robots [PDF]
BiomimeticsWith the advancement of task-oriented reinforcement learning (RL), the capability of quadruped robots for motion generation and complex task completion has significantly improved. However, current control strategies require extensive domain expertise and
Qin Zhang +5 more
doaj +2 more sources
Design and Control of Bio-Inspired Joints for Legged Robots Driven by Shape Memory Alloy Wires [PDF]
BiomimeticsBio-inspired joints play a pivotal role in legged robots, directly determining their motion capabilities and overall system performance. While shape memory alloy (SMA) actuators present superior power density and silent operation compared to conventional
Xiaojie Niu, Xiang Yao, Erbao Dong
doaj +2 more sources
DT-Loong: A Digital Twin Simulation Framework for Scalable Data Collection and Training of Humanoid Robots [PDF]
BiomimeticsRecent advances in bionic intelligence are reshaping humanoid-robot design, demonstrating unprecedented agility, dexterity and task versatility. These breakthroughs drive an increasing need for large scale and high-quality data.
Yufei Liu +4 more
doaj +2 more sources
DNN-based Skeleton Independent Motion Retargeting
Procedia Computer Science, 2023 Agnieszka Szczęsna +1 more
exaly +2 more sources
A Facial Motion Retargeting Pipeline for Appearance Agnostic 3D Characters [PDF]
Computer Animation and Virtual WorldsChangan Zhu
exaly +2 more sources