A Reverse Path Planning Approach for Enhanced Performance of Multi-Degree-of-Freedom Industrial Manipulators

In the domain of autonomous industrial manipulators,precise positioning and appropriate posture selection in path planning are pivotal for tasks involving obstacle avoidance,such as handling,heat sealing,and stacking.While Multi-Degree-of-Freedom(MDOF)manipulators offer kinematic redundancy,aiding in the derivation of optimal inverse kinematic solutions to meet position and posture requisites,their path planning entails intricate multiobjective optimization,encompassing path,posture,and joint motion optimization.Achieving satisfactory results in practical scenarios remains challenging.In response,this study introduces a novel Reverse Path Planning(RPP)methodology tailored for industrial manipulators.The approach commences by conceptualizing the manipulator’s end-effector as an agent within a reinforcement learning(RL)framework,wherein the state space,action set,and reward function are precisely defined to expedite the search for an initial collision-free path.To enhance convergence speed,the Q-learning algorithm in RL is augmented with Dyna-Q.Additionally,we formulate the cylindrical bounding box of the manipulator based on its Denavit-Hartenberg(DH)parameters and propose a swift collision detection technique.Furthermore,the motion performance of the end-effector is refined through a bidirectional search,and joint weighting coefficients are introduced to mitigate motion in high-power joints.The efficacy of the proposed RPP methodology is rigorously examined through extensive simulations conducted on a six-degree-of-freedom(6-DOF)manipulator encountering two distinct obstacle configurations and target positions.Experimental results substantiate that the RPP method adeptly orchestrates the computation of the shortest collision-free path while adhering to specific posture constraints at the target point.Moreover,itminimizes both posture angle deviations and joint motion,showcasing its prowess in enhancing the operational performance of MDOF industrial manipulators.

B-Spline-Based Curve Fitting to Cam Pitch Curve Using Reinforcement Learning

Directly applying the B-spline interpolation function to process plate cams in a computer numerical control(CNC)system may produce verbose tool-path codes and unsmooth trajectories.This paper is devoted to addressing the problem of B-splinefitting for cam pitch curves.Considering that the B-spline curve needs to meet the motion law of the follower to approximate the pitch curve,we use the radial error to quantify the effects of thefitting B-spline curve and the pitch curve.The problem thus boils down to solving a difficult global optimization problem tofind the numbers and positions of the control points or data points of the B-spline curve such that the cumulative radial error between thefitting curve and the original curve is minimized,and this problem is attempted in this paper with a double deep Q-network(DDQN)reinforcement learning(RL)algorithm with data points traceability.Specifically,the RL envir-onment,actions set and current states set are designed to facilitate the search of the data points,along with the design of the reward function and the initialization of the neural network.The experimental results show that when the angle division value of the actions set isfixed,the proposed algorithm can maximize the number of data points of the B-spline curve,and accurately place these data points to the right positions,with the minimum average of radial errors.Our work establishes the theoretical foundation for studying splinefitting using the RL method.

握力对前臂肌肉活动水平的影响

目的:评价不同强度的握力与前臂肌肉活动水平的相关性。方法:8名健康被试者参加实验,分别完成了最大自主收缩力80%MVC,60%MVC,40%MVC及20%MVC,实验记录了指浅屈肌和腕长伸肌的表面肌电信号,采用均方根的方法分析并提取表面肌电信号的幅度特征参数;运用统计分析方法比较握力水平与指浅屈肌、腕长伸肌的表面肌电的相关性,并且使用线性回归分析握力水平与相对特征值之间是否存在线性关系。结果表明指浅屈肌和腕长伸肌的表面肌电信号幅度随握力强度的增加而增加。握力水平与前臂肌肉表面肌电信号幅值存在正相关性,屈肌和伸肌对握力都有贡献,这种特征对于肌电假肢及其他应用的研究有一定帮助。

Wind Power Forecasting Methods Based on Deep Learning:A Survey

Accurate wind power forecasting in wind farm can effectively reduce the enormous impact on grid operation safety when high permeability intermittent power supply is connected to the power grid.Aiming to provide reference strategies for relevant researchers as well as practical applications,this paper attempts to provide the literature investigation and methods analysis of deep learning,enforcement learning and transfer learning in wind speed and wind power forecasting modeling.Usually,wind speed and wind power forecasting around a wind farm requires the calculation of the next moment of the definite state,which is usually achieved based on the state of the atmosphere that encompasses nearby atmospheric pressure,temperature,roughness,and obstacles.As an effective method of high-dimensional feature extraction,deep neural network can theoretically deal with arbitrary nonlinear transformation through proper structural design,such as adding noise to outputs,evolutionary learning used to optimize hidden layer weights,optimize the objective function so as to save information that can improve the output accuracy while filter out the irrelevant or less affected information for forecasting.The establishment of high-precision wind speed and wind power forecasting models is always a challenge due to the randomness,instantaneity and seasonal characteristics.

Transcranial magnetic stimulation-induced finger force changes under various finger coordination patterns and target finger force phases

BACKGROUND： The detection of motor evoked potential is utilized to explore neuromuscular finger coordination. The influence of transcranial magnetic stimulation on finger force has been investigated mainly on a single finger, and only time-dependent increased target finger force has been detected in the finger force task. OBJECTIVE： To explore the neural mechanism of finger force coordination in the motor cortex by observing the influence of various finger coordination patterns and patterns of transcranial magnetic stimulation （TMS）-induced finger force changes. DESIGN, TIME AND SETTING： Neurophysiological and behavioral study was performed at the Biomedical Engineering Laboratory of Chongqing University from April to June 2008. PARTICIPANTS： A total of 10 healthy, university students, comprising 5 males and 5 females, aged 21-23 years, voluntarily participated in this study. All participants were right-handed, with normal or corrected vision. Individuals with upper limb complaints or other musculoskeletal disorders were excluded. METHODS： A target force-tracking task was conducted on the index finger, the index and middle fingers, and four fingers （index, middle, ring, and little）, respectively. Target force trace in a single trial consisted of a 6-second ramp phase, a 20-second constant phase, and a 6-second drop phase. During experimentation, an unpredictable single-pulse TMS （120% motor threshold） was applied to the primary motor cortex （M1） in each phase. MAIN OUTCOME MEASURES： Changes in peak force induced by TMS were obtained for each finger pattern during each force-tracking phase. Differences in force changes were tested between different finger pattems with regard to ramp, constant, and drop phases of target force. RESULTS： Under ramp, constant, and drop phases of target force, the increase in magnetic stimulation-induced finger forces changes positively correlated with the number of fingers involved in the force tracking task. The magnetic stimulation-induced force changes from the index finger were less than the combination of the index and middle fingers or all four fingers under the corresponding target force, and the force changes from the combination of the index and middle fingers were less than all four fingers, Le., index finger 〈 index and middle fingers 〈 four fingers. CONCLUSION： Different neuromuscular mechanisms could be involved in finger force production for different finger combination patterns. Results from the present study suggested that independent motor neurons regulated individual finger force production.

Correlation between primary motor cortex neural activity and fingertip force following transcranial magnetic stimulation

A better understanding of the neural mechanisms of finger-force regulation can help to explain the relationship between the central nervous system and nerve-muscle force, as well as assist in motor functional rehabilitation and the development robot hand designs. In the present study, 11 healthy volunteers performed a different target force-tracking task, which involved the index finger alone, index and middle finger together, and the combination of four fingers （i.e., index, middle, ring, and little）. The target force trace corresponded to 3 levels of 20% maximal voluntary changes （MVC）, 30% MVC, and 40% MVC in 20 seconds. In the test, an unexpected single 120% motor threshold transcranial magnetic stimulation was applied to the primary motor cortex （M1） during force tracking. Results revealed that peak force changes increased with increasing background force and the number of involved task fingers. These results demonstrate that M1 neural activities correlate with finger-force production, and M1 plays a role in finger-force control. Moreover, different neuronal networks were required for different finger patterns; a complicated task required multi-finger combinations and a complicated neuronal network comprised a large number of neurons.

Bifurcation-Based Stability Analysis of Electrostatically Actuated Micromirror as a Two Degrees of Freedom System

Torsional micromirror devices have been widely used in micro displays,RF switches,optical communications,and optical coherence tomography systems.In order to study the stability of electrostatically driven torsional micromirror system with double bottom plates and two voltage sources,a dimensionless,two degrees of freedom(2-DoF)dynamic model was constructed.Governed by the dimensionless phase space model equation,the pull-in and bifurcation phenomena were analyzed using the Hamiltonian method and numerical simulation.In particular,the influence of the damping coefficient and the torsion-bending coupling effect on the phase trajectory was investigated.Furthermore,the conditions that can lead to pull-in were numerically determined for saddle-node,pitchfork and Hopf bifurcations in the framework of 2-DoF system.Result showed that the dynamic pull-in voltage as predicted by the proposed 2-DoF system model is considerably lower than that by the one degree of freedom(1-DoF)system model.It was also confirmed that the pull-in voltage varies with the damping coefficient and/or the ratio of the two voltages applied to the bottom plates of the micromirror.The modelling method and stability analysis presented in this paper shall provide valuable insight to the design and control of electrostatically actuated micromirror systems.

A Graph-Based Reinforcement Learning Method with Converged State Exploration and Exploitation

In any classical value-based reinforcement learning method,an agent,despite of its continuous interactions with the environment,is yet unable to quickly generate a complete and independent description of the entire environment,leaving the learning method to struggle with a difficult dilemma of choosing between the two tasks,namely exploration and exploitation.This problem becomes more pronounced when the agent has to deal with a dynamic environment,of which the configuration and/or parameters are constantly changing.In this paper,this problem is approached by first mapping a reinforcement learning scheme to a directed graph,and the set that contains all the states already explored shall continue to be exploited in the context of such a graph.We have proved that the two tasks of exploration and exploitation eventually converge in the decision-making process,and thus,there is no need to face the exploration vs.exploitation tradeoff as all the existing reinforcement learning methods do.Rather this observation indicates that a reinforcement learning scheme is essentially the same as searching for the shortest path in a dynamic environment,which is readily tackled by a modified Floyd-Warshall algorithm as proposed in the paper.The experimental results have confirmed that the proposed graph-based reinforcement learning algorithm has significantly higher performance than both standard Q-learning algorithm and improved Q-learning algorithm in solving mazes,rendering it an algorithm of choice in applications involving dynamic environments.

Effect of visual stimulus locations on pattern-reversal visual evoked potential An epidural electrocorticogram study

To explore the effect of the location of a visual stimulus on neural responses in the primary visual cortex （V1）, a micro-electromechanical system-based microelectrode array with nine channels was implanted on the cerebral dura mater of V1 in adult cats. 2 Hz pattern reversal checkerboard stimul were used to stimulate the four visual quadrants （i.e., upper left, upper right, lower left, and lower right fields）. The results showed that there was a N75 component of the visual evoked potential around 50-80 ms after the onset of a checkerboard stimulus, and the onset of these N75 peaks varied with different stimulus locations. The checkerboard stimuli Jnduced shorter latencJes in the contralateral V1 than in the ipsilateral V1, while the checkerboard stimulus in the upper half visual field induced shorter latencies for N75. These results suggested that the pattern-reversal stimuli induced neural activities in V1 that can be recorded with multichannel microelectrodes, and more detailed temporal and spatial properties can be measured.

Nanoparticle monolayer-based flexible strain gauge with ultrafast dynamic response for acoustic vibration detection

The relatively poor dynamic response of current flexible strain gauges has prevented their wide adoption in portable electronics. In this work, we present a greatly improved flexible strain gauge, where one strip of Au nanoparticle （NP） monolayer assembled on a polyethylene terephthalate film is utilized as the active unit. The proposed flexible gauge is capable of responding to applied stimuli without detectable hysteresis via electron tunneling between adjacent nanoparticles within the Au NP monolayer. Based on experimental quantification of the time and frequency domain dependence of the electrical resistance of the proposed strain gauge, acoustic vibrations in the frequency range of 1 to 20,000 Hz could be reliably detected. In addition to being used to measure musical tone, audible speech, and creature vocalization, as demonstrated in this study, the ultrafast dynamic response of this flexible strain gauge can be used in a wide range of applications, including miniaturized vibratory sensors, safe entrance guard management systems, and ultrasensitive pressure sensors.

Ultrasensitive strain gauge with tunable temperature coefficient of resistivity

We demonstrate an ultrasensitive strain gauge based on a discontinuous metal film with a record detection limit as low as 8.3 × 10^-6. Constructed by well-tunable crevices on the nanometer scale within the film, this gauge exhibits an ultrafast dynamic response to vibrations with a frequency range of 1 Hz to 10 kHz. More importantly, the temperature coefficient of resistivity （TCR） of the metal film is tunable owing to the cancellation effect caused by the possibility of tunneling across the nanoscale crevices （showing a negative temperature dependence） and the electron conduction within the metal islands （showing a positive temperature dependence）. Consequently, a nullified TCR is achievable when the crevice size can be precisely controlled. Thus, a fabrication strategy to precisely control the nanoscale crevices was developed in this study through the real-time tracking of the electrical conductivity during thermal evaporation. The ultrasensitive strain gauge with a tunable thermal drift introduces numerous opportunities for precision devices and wearable electronics with superior reliability.