In this work, we introduce a control framework that combines model-based footstep planning with Reinforcement Learning (RL), leveraging desired footstep patterns derived from the Linear Inverted Pendulum (LIP) dynamic...
详细信息
The realization of natural and authentic facial expressions in humanoid robots poses a challenging and prominent research domain,encompassing interdisciplinary facets including mechanical design,sensing and actuation ...
详细信息
The realization of natural and authentic facial expressions in humanoid robots poses a challenging and prominent research domain,encompassing interdisciplinary facets including mechanical design,sensing and actuation control,psychology,cognitive science,flexible electronics,artificial intelligence(AI),*** have traced the recent developments of humanoid robot heads for facial expressions,discussed major challenges in embodied AI and flexible electronics for facial expression recognition and generation,and highlighted future trends in this *** humanoid robot heads with natural and authentic facial expressions demands collaboration in interdisciplinary fields such as multi-modal sensing,emotional computing,and human-robot interactions(HRIs)to advance the emotional anthropomorphism of humanoid robots,bridging the gap between humanoid robots and human beings and enabling seamless HRIs.
In this paper, we present a novel cascade control structure with formal guarantees of uniform almost global asymptotic stability for the state tracking error dynamics of a quadcopter. The proposed approach features a ...
详细信息
Hand Gesture Recognition (HGR) is a form of perceptual computing with applications in human-machine interaction, virtual/augmented reality, and human behavior analysis. Within the HGR domain, several frameworks have b...
Hand Gesture Recognition (HGR) is a form of perceptual computing with applications in human-machine interaction, virtual/augmented reality, and human behavior analysis. Within the HGR domain, several frameworks have been developed with different combinations of input modalities and network architectures with varying levels of efficacy. Such frameworks maximized performance at the expense of increased hardware and computational requirements. These drawbacks can be tackled by transforming the relatively complex dynamic hand gesture recognition task into a simpler image classification task. This paper presents a skeleton-based HGR framework that implements data-level fusion for encoding spatiotemporal information from dynamic gestures into static representational images. Said static images are subsequently processed by a custom, end-to-end trainable multi-stream CNN architecture for gesture classification. Our framework reduces the hardware and computational requirements of the HGR task while remaining competitive with the state-of-the-art on the CNR, FPHA, LMDHG, SHREC2017, and DHG142S benchmark datasets. We demonstrated the practical utility of our framework by creating a lightweight real-time application that makes use of skeleton data extracted from RGB video streams captured by a standard inbuilt PC webcam. The application operates successfully with minimal CPU and RAM footprint while achieving 93.46% classification accuracy with approximately 2s latency at 15 frames per second.
This paper proposes a multiscale topology optimization method for the design of functionally graded lattice structures for energy absorption, considering material nonlinearity. The proposed multiscale topology optimiz...
This paper proposes a multiscale topology optimization method for the design of functionally graded lattice structures for energy absorption, considering material nonlinearity. The proposed multiscale topology optimization procedure consists of pre-processing, main processing, and post-processing. In the pre-processing step, the Representative Volume Element (RVE) method is used to compute the effective material properties. To consider material nonlinearity in the effective material property calculation process, the bilinear hardening model is applied. In the main processing step, multiscale topology optimization is performed using the computed effective material properties to maximize energy absorption performance until fracture occurs. Finally, in the post-processing step, the optimized design variables are reconstructed into a functionally graded lattice structure. Through a design example, the effectiveness of the proposed method is verified, and the topology optimization results are converted into a CAD format and fabricated using 3D printing to confirm manufacturability.
Active locomotion of capsule endoscopes has become a prominent progress in minimally invasive diagnostic procedures. Utilizing external magnetic fields for this purpose enables contactless actuation and enhanced maneu...
详细信息
ISBN:
(数字)9798331529734
ISBN:
(纸本)9798331529741
Active locomotion of capsule endoscopes has become a prominent progress in minimally invasive diagnostic procedures. Utilizing external magnetic fields for this purpose enables contactless actuation and enhanced maneuverability. This study presents an optimal control technique for magnetically actuated capsule endoscopes (MACE) within the small intestine, using a modified OCTAMAG setup. The objective is to minimize input currents while ensuring accurate path tracking, thereby preventing coil overheating and avoiding actuation inaccuracies. A correction force is also incorporated into the controller to stabilize it against external disturbances. The proposed method is evaluated using a path inspired by the small intestine and compared to conventional PID control. Results show that the optimal controller achieves superior path tracking while maintaining input currents within safe limits. Additionally, the disturbance rejection capabilities of the optimal controller are comparable to those of the PID.
There is a need for the remediation of space debris, but many objects must be detumbled before they can be safely serviced. In this paper, we describe an empirical study that is the first to evaluate the detumbling pe...
详细信息
ISBN:
(数字)9798350367232
ISBN:
(纸本)9798350367249
There is a need for the remediation of space debris, but many objects must be detumbled before they can be safely serviced. In this paper, we describe an empirical study that is the first to evaluate the detumbling performance of a rotating magnetic dipole (MD) field. We develop a new rotatingpermanent-magnet robotic end-effector capable of generating a strong MD field that can be rotated at high speeds. We construct a low-friction experimental apparatus to simulate a tumbling object. We conduct detumbling experiments using a rotating MD field with a variety of angular velocities, as well as the same field held static in two canonical orientations. We provide an estimate of the expected performance of each method in the microgravity environment of space by correcting our data for the friction in our experimental apparatus. We find that a rotating MD field detumbles an object in finite time, whereas a static field only detumbles an object asympotically to zero angular velocity. We find that the rotating MD field substantially outperforms a static MD field in reaching approximately zero angular velocity, provided the angular velocity of the rotating MD exceeds a modest minimum value. Finally, we observe a diminishing return in performance as we continue to increase the angular velocity of the rotating MD field.
Enabling aerial robots to handle dynamic contacts happening at non-vanishing speeds can enlarge the range of their applications. In this work, we propose an impactaware strategy to allow aerial multirotor robots to re...
Anterior ground reaction force (AGRF) is a common measurement of propulsion mechanics. It is typically measured using multi-axis force-plates which are not always found in robotic research labs. Here we present a comp...
详细信息
ISBN:
(数字)9798350386523
ISBN:
(纸本)9798350386530
Anterior ground reaction force (AGRF) is a common measurement of propulsion mechanics. It is typically measured using multi-axis force-plates which are not always found in robotic research labs. Here we present a comparison of models using kinematic and kinetic metrics of propulsion to estimate AGRF. Nine models using measurements of maximum vertical ground reaction force (maxVGRF), vertical ground reaction force at peak AGRF (aVGRF), maximum trailing limb angle (maxTLA), trailing limb angle at peak AGRF (aTLA) and stride length (SL) were used to predict different metrics of propulsion kinetics, including maximum AGRF (maxAGRF), propulsive impulse (PI), maximum AGRF normalized by body-weight (maxAGRFnorm), and normalized PI (PInorm) from participants walking at speeds [0.6 1.4] m/s. R2 and AICc scores were recorded for each model, and the individual participant R
2
values for the best single and two-factor models for each outcome were examined. Of the single-factor models, kinematic measurements were the best predictors of the outcome measurements. More specifically, maxAGRF/norm were best predicted by SL (R
2
= 0.91, 0.82, respectively), and PI/norm were best predicted by maxTLA (R
2
= 0.84, 0.43, respectively). For the two-factor models, maxAGRFnorm and PInorm were both best predicted by SL and aVGRFnorm, and maxVGRF yielded the best predictions for maxAGRF and PI. Models predicting maxAGRF /norm better fit individual participants than those predicting PI/norm. These results indicate that maxAGRF can be estimated with reasonable accuracy (R
2
= 0.92, RMSE of residuals: 1.5% bodyweight, equivalent to a 0.09 m/s increase in velocity) in the absence of a direct measurement of AGRF using both kinematic and kinetic measurements of propulsion.
暂无评论