5+ day, 22+ hour ago   (532+ words) Reliable localization and mapping are critical for intelligent robotic systems operating in dynamic indoor environments, where pedestrians and other moving objects can lead to erroneous feature associations, map contamination, and accumulated trajectory drift. To address these challenges, this study proposes…...

1+ week, 1+ day ago   (467+ words) Generalization under deployment shifts remains a major challenge for visuomotor robot manipulation, especially when changes in camera placement and control behavior are unknown to the policy. This paper introduces the System-Context-Conditioned Diffusion Policy (SCE-DP), a history-conditioned manipulation policy designed to…...

1+ week, 4+ day ago   (389+ words) As a result of population ageing, rehabilitation assistive products for older adults increasingly need to meet long-term user requirements in terms of usability, comfort, and interactive experience. Although existing hand rehabilitation robots (HRRs) are capable of supporting hand training tasks,…...

2+ week, 2+ day ago   (432+ words) Robotic bin-picking of disordered, randomly stacked workpieces remains challenging because reliable grasping depends on an accurate estimate of object pose, yet many established solutions require high-precision 3D sensing, detailed object models, or large annotated datasets that raise the cost and effort…...

3+ week, 2+ day ago   (481+ words) Assessments based solely on gesture execution may not reproduce the sensory and biomechanical demands of actual tool use. This study compared upper-limb muscle activation during gesture execution (GE) and actual tool use (AU) in 52 healthy adults in their twenties performing…...

3+ week, 1+ day ago   (410+ words) Improving sample efficiency and achieving balanced multi-task performance across different tasks remain important research challenges in reinforcement learning. Yie Ar Kung-Fu is formulated as a multi-task reinforcement learning environment. A task-specific neural network architecture, simplified state and action encoding schemes,…...

1+ week, 4+ day ago   (486+ words) Skeleton-based action recognition via graph convolutional networks (GCNs) has achieved remarkable progress, yet two persistent bottlenecks limit practical deployment: (1) systematic confusion among fine-grained actions that differ primarily in hand or finger movements, which the standard 25-joint skeleton cannot disambiguate; and…...

1+ week, 6+ day ago   (435+ words) Manual material handling tasks are a major source of physical workload and work-related musculoskeletal disorders in industrial environments. This study evaluated the effects of a passive back-support exoskeleton (BSE) on muscle activity and perceived discomfort during lifting and lowering tasks…...