查看更多>>摘要：This paper focuses on a newly developed transmission for a milli-scale eight-legged crawling robot called OriSCO.The transmission allows intuitive steering by directly changing the direction of the propulsion force.The transmission is based on the constrained spherical six-bar linkage.The constrained spherical six-bar linkage passes only reciprocating motion out of the motor's rotating motion,allowing the crawling legs to kick the ground and obtain propulsion.Steering is achieved by adjusting the geometric constraints of the spherical six-bar using a servomotor,allowing the direction of propulsion to be changed.As a result,the OriSCO can move along the ground at a speed of 2.15 body lengths/s,and the robot is 60 mm long.
查看更多>>摘要：Fish in nature exhibit a variety of swimming modes such as forward swimming,backward swimming,turning,pitching,etc.,enabling them to swim in complex scenes such as coral reefs.It is still difficult for a robotic fish to swim autonomously in a confined area as a real fish.Here,we develop an untethered robotic manta as an experimental platform,which consists of two flexible pectoral fins and a tail fin,with three infrared sensors installed on the front,left,and right sides of the head to sense the surrounding obstacles.To generate multiple swimming modes of the robotic manta and online switching of dif-ferent modes,we design a closed-loop Central Pattern Generator(CPG)controller based on distance information and use a combination of phase difference and amplitude of the CPG model to achieve stable and rapid adjustment of yaw angle.To verify the autonomous swimming ability of the robotic manta in complex scenes,we design an experimental scenario with a concave obstacle.The experimental results show that the robotic manta can achieve forward swimming,backward swim-ming,in situ turning within the concave obstacle,and finally exit from the area safely while relying on the perception of external obstacles,which can provide insight into the autonomous exploration of complex scenes by the biomimetic robotic fish.Finally,the swimming ability of the robotic manta is verified by field tests.
查看更多>>摘要：This paper is based on a previously developed bio-inspired Flapping Wing Aerial Vehicle(FWAV),RoboFalcon,which can fly with a morphing-coupled flapping pattern.In this paper,a simple flapping stroke control system based on Hall effect sensors is designed and applied,which is capable of assigning different up-and down-stroke speeds for the RoboFalcon platform to achieve an adjustable downstroke ratio.The aerodynamic and power characteristics of the morphing-coupled flapping pattern and the conventional flapping pattern with varying downstroke ratios are measured through a wind tunnel experiment,and the corresponding aerodynamic models are developed and analyzed by the nonlinear least squares method.The relatively low power consumption of the slow-downstroke mode of this vehicle is verified through outdoor flight tests.The results of wind tunnel experiments and flight tests indicate that increased downstroke duration can improve aerodynamic and power performance for the RoboFalcon platform.
查看更多>>摘要：Bioinspired flapping-wing micro-air-vehicles(FWMAVs)have the potential to be useful aerial tools for gathering information in various environments.With recent advancements in manufacturing technologies and better understanding of aerodynamic mechanisms behind of the flapping flight,outdoor flights have become a reality.However,to fully realize the potential of FWMAVs,further improvements are necessary,particularly in terms of stability and robustness under gusty conditions.In this study,the response and control of a tailless two-winged FWMAV under the wind gusts are investigated.Physical experiments are conducted with a one-degree-of-freedom gimbal to focus on effects of wind gusts on the rotational motion of the FWMAV.Proportional-derivative and sliding-mode controls are adopted for the attitude control.Results present that the body angles changed in time and reached approximately 50° at the maximum due to the wing gusts.The sliding-mode controller can more effectively control the rotational angle in the presence of disturbances and both the wing speed and changes in wind speed have an impact on the effectiveness of attitude control.These results contribute to the development of of tailless two-winged,single-motor driven FWMAVs in terms of the design of attitude controller and testing apparatus.
查看更多>>摘要：Lower Limb Exoskeletons(LLEs)are receiving increasing attention for supporting activities of daily living.In such active systems,an intelligent controller may be indispensable.In this paper,we proposed a locomotion intention recognition system based on time series data sets derived from human motion signals.Composed of input data and Deep Learning(DL)algo-rithms,this framework enables the detection and prediction of users'movement patterns.This makes it possible to predict the detection of locomotion modes,allowing the LLEs to provide smooth and seamless assistance.The pre-processed eight subjects were used as input to classify four scenes:Standing/Walking on Level Ground(S/WOLG),Up the Stairs(US),Down the Stairs(DS),and Walking on Grass(WOG).The result showed that the ResNet performed optimally compared to four algorithms(CNN,CNN-LSTM,ResNet,and ResNet-Att)with an approximate evaluation indicator of 100％.It is expected that the proposed locomotion intention system will significantly improve the safety and the effectiveness of LLE due to its high accuracy and predictive performance.
查看更多>>摘要：This paper proposes a new upper-limb exoskeleton to reduce worker physical strain.The proposed design is based on a novel PRRRP(P-Prismatic;R-Revolute)kinematic chain with 5 passive Degrees of Freedom(DoF).Utilizing a magnetic spring,the proposed mechanism includes a specially designed locking mechanism that maintains any desired task posture.The proposed exoskeleton incorporates a balancing mechanism to alleviate discomfort and spinal torsional effects also helping in limb weight relief.This paper reports specific models and simulations to demonstrate the feasibility and effectiveness of the proposed design.An experimental characterization is performed to validate the performance of the mechanism in terms of forces and physical strain during a specific application consisting of ceiling-surface drilling tasks.The obtained results preliminarily validate the engineering feasibility and effectiveness of the proposed exoskeleton in the intended operation task thereby requiring the user to exert significantly less force than when not wearing it.
查看更多>>摘要：Lower limb motion recognition techniques commonly employ Surface Electromyographic Signal(sEMG)as input and apply a machine learning classifier or Back Propagation Neural Network(BPNN)for classification.However,this artificial feature engineering technique is not generalizable to similar tasks and is heavily reliant on the researcher's subject expertise.In contrast,neural networks such as Convolutional Neural Network(CNN)and Long Short-term Memory Neural Network(LSTM)can automatically extract features,providing a more generalized and adaptable approach to lower limb motion recognition.Although this approach overcomes the limitations of human feature engineering,it may ignore the potential correlation among the sEMG channels.This paper proposes a spatial-temporal graph neural network model,STGNN-LMR,designed to address the problem of recognizing lower limb motion from multi-channel sEMG.STGNN-LMR transforms multi-channel sEMG into a graph structure and uses graph learning to model spatial-temporal features.An 8-channel sEMG dataset is constructed for the experimental stage,and the results show that the STGNN-LMR model achieves a recognition accuracy of 99.71％.Moreover,this paper simulates two unexpected scenarios,including sEMG sensors affected by sweat noise and sudden failure,and evaluates the testing results using hypothesis testing.According to the experimental results,the STGNN-LMR model exhibits a significant advantage over the control models in noise scenarios and failure scenarios.These experimental results confirm the effectiveness of the STGNN-LMR model for addressing the challenges associated with sEMG-based lower limb motion recognition in practical scenarios.
Ali NasrSydney BellRachel L.WhittakerClark R.Dickerson...
270-287页
查看更多>>摘要：A machine learning model for regression of interrupted Surface Electromyography(sEMG)signals to future control-oriented signals(e.g.,robot's joint angle and assistive torque)of an active biomechatronic device for high-level myoelectric-based hierarchical control is proposed.A Recurrent Neural Network(RNN)was trained using output data,initially obtained from offline optimization of the biomechatronic(human-robot)device and shifted by the prediction horizon.The input of the RNN consisted of interrupted sEMG signals(to mimic signal disconnections)and previous kinematic signals of the assistive system.The RNN with a 0.1-s prediction horizon could predict the control-oriented joint angle and assistive torque with 92％and 86.5％regression accuracy,respectively,for the test dataset.This proposed approach permits a fast,predictive,and direct estimation of control-oriented signals instead of an iterative process that optimizes assistive torque in the inverse dynamic simulation of a multibody human-robot system.Training with these interrupted input signals significantly improves the regression accuracy in the case of sEMG signal disconnection.This Robust Predictive Control-oriented Machine Learning(Robust-MuscleNET)model can support volitional high-level myoelectric-based control of biomechatronic devices,such as exoskeletons,prostheses,and assistive/resistive robots.Future work should study the application to prosthesis control as well as the repeatability of the high-level controller with electrode shift.The low-level hierarchical controller that manages the human-robot interaction,the assistance/resistance strategy,and the actuator coordination should also be studied.
查看更多>>摘要：Artificial intelligence is currently achieving impressive success in all fields.However,autonomous navigation remains a major challenge for AI.Reinforcement learning is used for target navigation to simulate the interaction between the brain and the environment at the behavioral level,but the Artificial Neural Network trained by reinforcement learning cannot match the autonomous mobility of humans and animals.The hippocampus-striatum circuits are considered as key circuits for target navigation planning and decision-making.This paper aims to construct a bionic navigation model of reinforcement learning corresponding to the nervous system to improve the autonomous navigation performance of the robot.The ventral striatum is considered to be the behavioral evaluation region,and the hippocampal-striatum circuit constitutes the position-reward association.In this paper,a set of episode cognition and reinforcement learning system simulating the mechanism of hip-pocampus and ventral striatum is constructed,which is used to provide target guidance for the robot to perform autonomous tasks.Compared with traditional methods,this system reflects the high efficiency of learning and better Environmental Adaptability.Our research is an exploration of the intersection and fusion of artificial intelligence and neuroscience,which is conducive to the development of artificial intelligence and the understanding of the nervous system.
查看更多>>摘要：In this study,different conditions of sandblasting on dental implant fixtures were investigated to achieve the best sandblasting conditions.18 different sandblasting conditions(Using 152 implant fixture samples)were examined,including parameters such as particle size,particle blasting pressure,and particle blasting angle.The surface treatment of the samples was per-formed using the SLA+Anodizing method.AFM testing was performed for each of the 18 different states,and the average surface roughness of each of these was compared with each other.Then,a bone layer was placed on the sample with the closest average surface roughness to the standard and the least amount of aluminum oxide on its surface among the 18 dif-ferent states,to confirm the accuracy and quality of the desired surface roughness by examining the bone formation process and speed.The results showed that state No.4(sandblast particle size:75 pm,spraying pressure of sandblast particles:4 bar,sandblast particle spraying angle:30 degrees),which was prepared using the SLA+Anodizing method and had a surface roughness of 1.989 pm(The percentage of Al2O3 on the surface=6％),had the best sandblasting conditions and showed 95％cell viability and accelerated the treatment and bone formation process for about a week.The simulation results,using Abaqus software,indicated that the stress distribution on the surface of the implant fixture in contact with the bone surface has increased by approximately 4.3％for state No.4.This will help prevent loosening of the dental implant fixture over time.
NETL
NSTL
万方数据