Search Results (1,672)

The rapid growth of technology has introduced robots into daily life, necessitating navigation frameworks that enable safe, human-friendly movement while accounting for social aspects. Such methods must also scale to situations with multiple humans and robots moving simultaneously. Recent advances in Deep Reinforcement Learning (DRL) have enabled policies that incorporate these norms into navigation. This work presents a socially aware navigation framework for mobile robots operating in environments shared with humans and other robots. The approach, based on single-agent DRL, models all interaction types between the ego robot, humans, and other robots. Training uses a reward function balancing task completion, collision avoidance, and maintaining comfortable distances from humans. An attention mechanism enables the framework to extract knowledge about the relative importance of surrounding agents, guiding safer and more efficient navigation. Our approach is tested in both dynamic and static obstacle environments. To improve training efficiency and promote socially appropriate behaviors, Imitation Learning is employed. Comparative evaluations with state-of-the-art methods highlight the advantages of our approach, especially in enhancing safety by reducing collisions and preserving comfort distances. Results confirm the effectiveness of our learned policy and its ability to extract socially relevant knowledge in human–robot environments where social compliance is essential for deployment. Full article

Rural dwellings are often self-designed and self-built by their owners, with construction decisions based on experience and imitation of nearby buildings. As existing advanced design methods are often too complex or resource-intensive for rural contexts, balancing cost-efficiency, energy performance, and functional needs remains a challenge. This paper proposes to use the matrix analysis method, which is a relatively simple and easy-to-learn procedure, to identify the optimal design of rural houses. Taking Hebi, located in the Central Plains of China, as an example, field research was carried out, and a baseline model was established. A number of variable models were analysed using the control variable method for building orientation and indoor headroom, and metrics such as energy consumption, uncomfortable hours and construction costs were calculated to screen out effective metrics. Furthermore, by combining matrix analysis with orthogonal tests, the approach enables the development of optimal design solutions more efficiently and with reduced complexity. The results show that the optimised design, generated using the proposed method, significantly improves the indoor thermal environment—reducing energy consumption by 65.26% and uncomfortable hours by 29.22%, with only a 1.3% increase in construction costs. This study contributes to sustainable rural development by proposing a practical framework that guides the design of low-cost and energy-efficient rural housing. Full article

Accurately predicting the long-term behavior of complex dynamical systems is a central challenge for safety-critical applications like autonomous navigation. Mechanistic models are often brittle, relying on difficult-to-measure parameters, while standard deep learning models are black boxes that fail to generalize, producing physically inconsistent predictions. Here, we introduce a physics-informed framework that learns the continuous-time dynamics of an Autonomous Underwater Vehicle (AUV) by discovering its underlying energy landscape. We embed the structure of Port-Hamiltonian mechanics into a neural ordinary differential equation (NODE) architecture, learning not to imitate trajectories but rather to identify the system’s Hamiltonian and its constituent physical matrices from observational data. Geometric consistency is enforced by representing rotational dynamics on the SE(3) manifold, preventing numerical error accumulation. Experimental validation reveals a stark performance divide. While a state-of-the-art black-box model matches our accuracy in simple, interpolative maneuvers, its predictions fail catastrophically under complex controls. Quantitatively, our physics-informed model maintained a mean 10 s position error of a mere 3.3 cm, whereas the black-box model’s error diverged to 5.4 m—an over 160-fold performance gap. This work establishes that the key to robust, generalizable models lies not in bigger data or deeper networks but in the principled integration of physical laws, providing a clear path to overcoming the brittleness of black-box models in critical engineering simulations. Full article

Exploding or concentrating beams, vortex beams, and cylindrical vector beams have a precisely shaped transversal amplitude profile such that they produce a continuously concentrating and intensifying focal spot upon focusing as the lens aperture is opened. This effect is the physical manifestation of the mathematical fact that Fresnel diffraction integral predicts an infinite intensity at the focus when the aperture effects are ignored. Here, using a full electromagnetic, nonparaxial focusing model, we show that the singularity in exploding cylindrical vector beams is an artifact of the paraxial approximation. Nevertheless, the exploding or concentrating effect, alien to any other light beam with finite power, keeps going up to unit numerical aperture, equivalent to infinite aperture radius. This unique feature enables a dynamic control of the focal intensity and spot size down to the sub-wavelength scale using a single light beam, imitating similar control when focusing an ideal plane wave, but requiring a finite amount of power. Full article

Learning from Demonstration (LfD) enables robots to acquire manipulation skills by observing human actions. However, existing methods often face challenges such as high computational cost, limited generalizability, and a loss of key interaction details. This study presents a compact representation for interaction recognition in LfD that encodes human–object interactions using 2D wrist trajectories and 3D object poses. A lightweight extraction pipeline combines MediaPipe-based wrist tracking with FoundationPose-based 6-DoF object estimation to obtain these trajectories directly from RGB-D video without specialized sensors or heavy preprocessing. Experiments on the GRAB and FPHA datasets show that the representation effectively captures task-relevant interactions, achieving 94.6% accuracy on GRAB and 96.0% on FPHA with well-calibrated probability predictions. Both Bidirectional Long Short-Term Memory (Bi-LSTM) with attention and Transformer architectures deliver consistent performance, confirming robustness and generalizability. The method achieves sub-second inference, a memory footprint under 1 GB, and reliable operation on both GPU and CPU platforms, enabling deployment on edge devices such as NVIDIA Jetson. By bridging pose-based and object-centric paradigms, this approach offers a compact and efficient foundation for scalable robot learning while preserving essential spatiotemporal dynamics. Full article

The present work is focused on the implementation of a robot system that mimics cat whiskers to differentiate between different objects. The robotic system imitates the motion from whiskers in the same way a cat uses them to collide with objects. The states from the system are estimated with the use of an Extended State Observer to measure the perturbation applied over the motors responsible for the whisker collision. The estimated perturbation is analyzed on the frequency domain with the use of the Fast Fourier Transform to determine the fundamental frequencies. A pair of classifiers are used to determine the object that collided with the whiskers based on the frequencies of the estimated perturbation. Full article

In reinforcement learning (RL), reward function design is critical to the learning efficiency and final performance of agents. However, in complex tasks such as humanoid motion tracking, traditional static weighted reward functions struggle to adapt to shifting learning priorities across training stages, and designing a suitable shaping reward is problematic. To address these challenges, this paper proposes a two-layered reward reinforcement learning framework. The framework decomposes the reward into two layers: an upper-level goal reward that measures task completion, and a lower-level optimizing reward that includes auxiliary objectives such as stability, energy consumption, and motion smoothness. The key innovation lies in the online optimization of the lower-level reward weights via an online meta-heuristic optimization algorithm. This online adaptivity enables goal-conditioned reward shaping, allowing the reward structure to evolve autonomously without requiring expert demonstrations, thereby improving learning robustness and interpretability. The framework is tested on a gymnastic motion tracking problem for the Unitree G1 humanoid robot in the Isaac Gym simulation environment. The experimental results show that, compared to a static reward baseline, the proposed framework achieves 7.58% and 10.30% improvements in upper-body and lower-body link tracking accuracy, respectively. The resulting motions also exhibit better synchronization and reduced latency. The simulation results demonstrate the effectiveness of the framework in promoting efficient exploration, accelerating convergence, and enhancing motion imitation quality. Full article

This paper presents our first results obtained in the direction of using a humanoid robot to perform a robot dance at a level comparable to that of a human dancer. The scope of this first approach is limited to performing an offline analysis of the movements of the arms of the dancer and to replicating these movements with the arms of the robot. To this end, the movements of a dancer performing a static robot dance (without moving the hips or feet) were recorded. These movements were analyzed offline using the MediaPipe BlazePose framework, adapted to the mechanical configuration of the arms of the humanoid robot, and finally reproduced by the robot. Results showed that MediaPipe has some inaccuracies when detecting sudden movements of the dancer’s arms that appeared blurred in the images. In general, the humanoid robot was capable of replicating the movement of the dancer’s arms but was unable to follow the original rhythm of the robotic dance due to acceleration limitations of its actuators. Full article

Legged robots have great potential in complex environments, but achieving robust and natural locomotion remains difficult due to challenges in generating smooth gaits and resisting disturbances. This article presents a novel reinforcement learning framework that integrates a skeleton-aware graph neural network (GNN), a single-stage teacher–student architecture, a system-response model, and a Wasserstein Adversarial Motion Priors (wAMP) module. The skeleton-aware GNN enriches observations by encoding key node information and link properties, providing structured body information and better spatial awareness on irregular terrains. Unlike conventional two-stage approaches, this method jointly trains teacher and student policies to accelerate learning and improve sim-to-real transfer using hybrid advantage estimation (HAE). The system-response model further enhances robustness by predicting future observations from historical states via contrastive learning, enabling the policy to anticipate terrain variations and external disturbances. Finally, wAMP provides a more stable adversarial imitation method for fitting expert datasets of both flat ground and stair locomotion. Experiments on quadruped robots demonstrate that the proposed approach achieves more natural gaits and stronger robustness than existing baselines. Full article

This article investigates liuli qinglou (琉璃青樓, blue–green glazed pavilions) of medieval China as architectural manifestations of the trans-Eurasian jeweled paradise ideal. Tracing developments from the Northern and Southern Dynasties (420–589 CE) through the Tang dynasty (618–907 CE), it outlines an evolutionary trajectory in representing sacred space: from the use of genuine gemstones in West Asian traditions, through their imitation in glass and glazed ceramics, with applications before the Tang remaining selective and elite, to the ultimate abstraction into symbolic blue–green palettes in the cave murals of Kucha and Dunhuang, where chromatic choices may at times reflect pictorial convention. Integrating textual, archeological, and visual evidence, the study shows how Chinese rulers appropriated imported glazing technologies, together with painted or coated blue–green finishes that simulated liuli effects, not merely for ornamentation but to materially embody Buddhist cosmology and to legitimize imperial authority by creating a terrestrial Buddha land. The pervasive use of qing (青, blue–green) in religious art thus reflects a profound sensory-theological translation, illustrating how Eurasian flows of materials, techniques, and ideas were adapted to shape localized visions of paradise through innovative processes of material and visual transformation. Full article

Background: This paper concerns the study of forces acting on the upper ankle joint of a human in static and quasi-dynamic positions. This paper aimed to determine the pressure forces on the axis of the upper ankle joint in the position of the body tilting forward and backward, as well as in a neutral position. Methods: A model with designated centres of gravity (including and excluding the weight of the platform imitating the foot) and the point of gravity imitating the proximal insertion of the triceps surae and tibialis anterior muscles was developed for this study. The forces and the weight of the tilted object were measured using dynamometers. A method for determining the arms of gravitational forces and the angle of inclination of an object is presented. The function describing the distribution of gravitational loading along its tilting part was described. Next, all measurements and calculations were referred to the human body. Results: Measurements of muscle force, body gravity, the arms of these forces, and the angles of the object’s inclination on the axis of rotation are presented. A methodology for determining the pressure force on the human upper ankle joint axis is presented. The distribution of the value of the pressure force and its components from the maximal forward, through the vertical body position, up to the maximal backward position of the body tilt, is provided. Conclusions: The ankle joint pressure force is the vector sum of the force of gravity and the force of the muscle counteracting the body tilt. This force is the smallest in the vertical body position and increases with the body tilt. It reaches 5.23 times the weight of the tilting part of the body when the body is tilted to its maximum forward position, and 3.57 times the weight when the body tilts backward. Regardless of the direction of the body tilt, the joint pressure vector always runs through the axis of the upper ankle joint. Full article

This paper presents TVAE-SSL, a novel semi-supervised learning (SSL) paradigm that involves Tabular Variational Autoencoder (TVAE)-sampled synthetic data injection into the training process to enhance model performance under low-label data conditions in Educational Data Mining tasks. The algorithm begins with training a TVAE on the given labeled data to generate imitative synthetic samples of the underlying data distribution. These synthesized samples are treated as additional unlabeled data and combined with the original unlabeled ones in order to form an augmented training pool. A standard SSL algorithm (e.g., Self-Training) is trained using a base classifier (e.g., Random Forest) on the combined dataset. By expanding the pool of unlabeled samples with realistic synthetic data, TVAE-SSL improves training sample quantity and diversity without introducing label noise. Large-scale experiments on a variety of datasets demonstrate that TVAE-SSL can outperform baseline supervised models in the full labeled dataset in terms of accuracy, F1-score and fairness metrics. Our results demonstrate the capacity of generative augmentation to enhance the effectiveness of semi-supervised learning for tabular data. Full article

This paper presents a methodological framework for selectively optimizing computer vision models for safety-critical applications. Through systematic processes of hyperparameter tuning alongside multitask learning, we attempt to create a highly interpretable system to better assess the dangers of models intended for safety operations and intentionally select their trade-offs. Using thermographic images of a specific imitation explosive, we create a case study for the viability of humanitarian demining operations. We hope to demonstrate how this approach provides a developmental framework for creating humanitarian AI systems that optimize safety verification in real-world scenarios. By employing a comprehensive grid search across 64 model configurations to evaluate how loss function weights impact detection reliability, with particular focus on minimizing false negative rates due to their operational impact. The optimized configuration achieves a 37.5% reduction in false negatives while improving precision by 2.8%, resulting in 90% detection accuracy with 92% precision. However, to expand the generalizability of this model, we hope to call institutions to openly share their data to increase the breadth of imitation landmines and terrain data to train models from. Full article

Based on the problem of incomplete mining of Additive Manufacturing (AM) potential caused by the limitations of current Design for Additive Manufacturing (DFAM) methods, this paper proposes to integrate Additive Manufacturing and axiomatic design to obtain the global conceptual design method of products to be manufactured with AM. In response to the lower process dependence of AM technology compared to traditional processes, two integration measures of “influence region division” and “process domain forward” are proposed, and finally, the axiomatic design process for AM is obtained. Taking the assembly-free integrated design of mechanical fingers imitating dexterous hands as an example, the conceptual design method studied was validated. The application of innovative features such as flexible finger joints and lattice-filled finger joints shows that the design method proposed in this paper can deeply tap into the manufacturing potential of AM, achieve lightweight and integrated molding of products, which provides useful references for designers. Full article

Background: Evolutionary game theory (EGT), originating from Darwinian competition studies, offers a powerful framework for understanding complex healthcare interactions where multiple stakeholders with conflicting interests evolve strategies over time. Unlike traditional game theory, EGT accounts for bounded rationality and strategic evolution through imitation and selection. Aims and objectives: In our study, we use Synthetic Knowledge Synthesis (SKS) that integrates descriptive bibliometrics and bibliometric mapping to systematically analyze the application of EGT in healthcare. The SKS aimed to identify prolific research topics, suitable publishing venues, and productive institutions/countries for collaboration and funding. Data was harvested from the Scopus bibliographic database, encompassing 539 publications from 2000 to June 2025, Results: Production dynamics is revealing an exponential growth in scholarly output since 2019, with peak productivity in 2024. Descriptive bibliometrics showed China as the most prolific country (376 publications), followed by the United States and the United Kingdom. Key institutions are predominantly Chinese, and top journals include PLoS One and Frontiers in Public Health. Funding is primarily from Chinese entities like the National Natural Science Foundation of China. Bibliometric mapping identified five key research themes: game theory in cancer research, evolution game-based simulation of supply management, evolutionary game theory in epidemics, evolutionary games in trustworthy connected public health, and evolutionary games in collaborative governance. Conclusions: Despite EGT’s utility, significant research gaps exist in methodological robustness, data availability, contextual modelling, and interdisciplinary translation. Future research should focus on integrating machine learning, longitudinal data, and explicit ethical frameworks to enhance EGT’s practical application in adaptive, patient-centred healthcare systems. Full article