This article designs a robotic Chinese character writing system that can resist random human interference. Firstly, an innovative stroke extraction method of Chinese characters was devised. A basic Chinese character stroke extraction method based on cumulative direction vectors is used to extract the components that make up the strokes of Chinese characters. The components are then stitched together into strokes based on the sequential base stroke joining method. To enable the robot to imitate handwriting Chinese character skills, we utilised stroke information as the demonstration and modelled the skills using dynamic movement primitives (DMPs). To suppress random human interference, this article combines improved DMPs and conductance control to adjust robot trajectories based on real-time visual measurements. The experimental results show that the proposed method can accurately extract the strokes of most Chinese characters. The designed trajectory adjustment method offers better smoothness and robustness than direct rotating and translating curves. The robot is able to adjust its posture and trajectory in real time to eliminate the negative impacts of human interference.

Lower limb exoskeletons (LLEs) have demonstrated their potential in delivering quantified repetitive gait training for individuals afflicted with gait impairments. A critical concern in robotic gait training pertains to fostering active patient engagement, and a viable solution entails harnessing the patient’s intrinsic effort to govern the control of LLEs. To address these challenges, this study presents an innovative online gait learning approach with an appropriate control strategy for rehabilitation exoskeletons based on dynamic movement primitives (DMP) and an Assist-As-Needed (AAN) control strategy, denoted as DMP-AAN. Specifically tailored for post-stroke patients, this approach aims to acquire the gait trajectory from the unaffected leg and subsequently generate the reference gait trajectory for the affected leg, leveraging the acquired model and the patient’s personal exertion. Compared to conventional AAN methodologies, the proposed DMP-AAN approach exhibits adaptability to diverse scenarios encompassing varying gait patterns. Experimental validation has been performed using the lower limb rehabilitation exoskeleton HemiGo. The findings highlight the ability to generate suitable control efforts for LLEs with reduced human-robot interactive force, thereby enabling highly patient-controlled gait training sessions to be achieved.

Dynamical movement primitives (DMPs) method is a useful tool for efficient robotic skills learning from human demonstrations. However, the DMPs method should know the specified constraints of tasks in advance. One flexible solution is to introduce the human superior experience as part of input. In this paper, we propose a framework for robot learning based on demonstration and supervision. Superior experience supplied by teleoperation is introduced to deal with unknown environment constrains and correct the demonstration for next execution. DMPs model with integral barrier Lyapunov function is used to deal with the constrains in robot learning. Additionally, a radial basis function neural network based controller is developed for teleoperation and the robot to track the generated motions. Then, we prove convergence of the generated path and controller. Finally, we deploy the novel framework with two touch robots to certify its effectiveness.

In order to assist patients with lower limb disabilities in normal walking, a new trajectory learning scheme of limb exoskeleton robot based on dynamic movement primitives (DMP) combined with reinforcement learning (RL) was proposed. The developed exoskeleton robot has six degrees of freedom (DOFs). The hip and knee of each artificial leg can provide two electric-powered DOFs for flexion/extension. And two passive-installed DOFs of the ankle were used to achieve the motion of inversion/eversion and plantarflexion/dorsiflexion. The five-point segmented gait planning strategy is proposed to generate gait trajectories. The gait Zero Moment Point stability margin is used as a parameter to construct a stability criteria to ensure the stability of human-exoskeleton system. Based on the segmented gait trajectory planning formation strategy, the multiple-DMP sequences were proposed to model the generation trajectories. Meanwhile, in order to eliminate the effect of uncertainties in joint space, the RL was adopted to learn the trajectories. The experiment demonstrated that the proposed scheme can effectively remove interferences and uncertainties.

Dynamic movement primitives (DMP) are motion building blocks suitable for real-world tasks. We suggest a methodology for learning the manifold of task and DMP parameters, which facilitates runtime adaptation to changes in task requirements while ensuring predictable and robust performance. For efficient learning, the parameter space is analyzed using principal component analysis and locally linear embedding. Two manifold learning methods: kernel estimation and deep neural networks, are investigated for a ball throwing task in simulation and in a physical environment. Low runtime estimation errors are obtained for both learning methods, with an advantage to kernel estimation when data sets are small.

The progressive automation framework allows the seamless transition of a robot from kinesthetic guidance to autonomous operation mode during programming by demonstration of discrete motion tasks. This is achieved by the synergetic action of dynamic movement primitives (DMPs), virtual fixtures, and variable impedance control. The proposed DMPs encode the demonstrated trajectory and synchronize with the current demonstration from the user so that the reference generated motion follows the human’s demonstration. The proposed virtual fixtures assist the user in repeating the learned kinematic behavior but allow penetration so that the user can make modifications to the learned trajectory if needed. The tracking error in combination with the interaction forces and torques is used by a variable stiffness strategy to adjust the progressive automation level and transition the leading role between the human and the robot. An energy tank approach is utilized to apply the designed controller and to prove the passivity of the overall control method. An experimental evaluation of the proposed framework is presented for a pick and place task and results show that the transition to autonomous mode is achieved in few demonstrations.

In this paper, we propose and implement an advanced manipulation framework that enables parametric learning of complex action trajectories along with their haptic feedback profiles. Our framework extends Dynamic Movement Primitives (DMPs) method with a new parametric nonlinear shaping function and a novel force-feedback coupling term. The nonlinear trajectories of the action control variables and the haptic feedback trajectories measured during execution are encoded with parametric temporal probabilistic models, namely parametric hidden Markov models (PHMMs). PHMMs enable autonomous segmentation of a taught skill based on the statistical information extracted from multiple demonstrations, and learning the relations between the model parameters and the properties extracted from the environment. Hidden states with high-variances in observation probabilities are interpreted as parts of the skill that could not be reliably learned and autonomously executed due to possibly uncertain or missing information about the environment. In those parts, our proposed force-feedback coupling term, which computes the deviation of the actual force feedback from the one predicted by the force-feedback PHMM, acts as a compliance term, enabling a human to scaffold the ongoing movement trajectory to accomplish the task. Our method is verified in a number of tasks including a real pick and place task that involves obstacles of different heights. Our robot, Baxter, successfully learned to generate the trajectory taking into the heights of the obstacles, move its end effector stiffly (and accurately) along the generated trajectory while passing through apertures, and allow human–robot collaboration in the autonomously detected segments of the motion, for example, when the gripper picks up the object whose position is not provided to the robot.

General-purpose autonomous robots must have the ability to combine the available sensorimotor knowledge in order to solve more complex tasks. Such knowledge is often given in the form of movement primitives. In this paper, we investigate the problem of sequencing of movement primitives. We selected nonlinear dynamic systems as the underlying sensorimotor representation because they provide a powerful machinery for the specification of primitive movements. We propose two new methodologies which both ensure that consecutive movement primitives are joined together in a continuous way (up to second-order derivatives). The first is based on proper initialization of the third-order dynamic motion primitives and the second uses online Gaussian kernel functions modification of the second-order dynamic motion primitives. Both methodologies were validated by simulation and by experimentally using a Mitsubishi PA-10 articulated robot arm. Experiments comprehend pouring, table wiping, and carrying a glass of liquid.