Motion Primitives Research Articles

A Synthesis-based Tool Path Planning Approach for Machining Operations

The planning of machining operations for components using CAM requires careful consideration by highly trained personnel, with rising complexity in part requirements. This work proposes a novel domain-specific planning technique using Combinatory Logic Synthesis to generate a multitude of tool paths. By analyzing current state CNC path planning algorithms, motion primitives are identified and implemented in a modular representation using software components. Thus, a large variety of path planning strategies can be generated, while maintaining a multitude of different boundary constraints and productivity metrics. These solutions are subjected to geometric physically-based simulations in order to validate their ranking and compliance.

Origami Folding by Multifingered Hands with Motion Primitives.

Origami, a traditional Japanese art, is an example of superior handwork produced by human hands. Achieving such extreme dexterity is one of the goals of robotic technology. In the work described in this paper, we developed a new general-purpose robot system with sufficient capabilities for performing Origami. We decomposed the complex folding motions into simple primitives and generated the overall motion as a combination of these primitives. Also, to measure the paper deformation in real-time, we built an estimator using a physical simulator and a depth camera. As a result, our experimental system achieved consecutive valley folds and a squash fold.

Motion Pattern of Human Arm Reaching Point Movements Based on the Movement Primitives

Motion Pattern of Human Arm Reaching Point Movements Based on the Movement Primitives

A Skill Programming Method Based on Assembly Motion Primitive for Modular Assembly System

To improve the programming efficiency of automatic assembly system, a novel skill programming framework based on task learning is proposed for modular assembly system in this paper. In this framework, the motion sequence of assembly skills can be modeled by demonstration data. And the assembly task is represented hierarchically. A complete assembly process of a part is divided into several skills, and each skill is divided into several sequential assembly motion primitives (AMP) of multiple modules. Then, a learning method of assembly motion sequence based on Hidden Markov Model is proposed, and the maximum probability method is used to generate the optimal sequential AMP. Each AMP is input to the assembly system in the form of instruction to complete the assembly. Aiming at the problem of accurate positioning and trajectory planning, visual guidance and direct teaching method are used to settle this problem. To evaluate the viability of the proposed framework, a customized modular assembly system is used to acquire the demonstration data, and a graphical user interface (GUI) software is designed. Five assembly skills are learned. Experimental are conducted to validate the effectiveness of the proposed method.

Assistive Positioning via Integrating User Input and Dynamic Movement Primitives in Shared Teleoperation

Assistive Positioning via Integrating User Input and Dynamic Movement Primitives in Shared Teleoperation

Adaptive Multi-Task Human-Robot Interaction Based on Human Behavioral Intention

Learning from demonstrations with Probabilistic Movement Primitives (ProMPs) has been widely used in robot skill learning, especially in human-robot collaboration. Although ProMP has been extended to multi-task situations inspired by the Gaussian mixture model, it still treats each task independently. ProMP ignores the common scenario that robots conduct adaptive switching of the collaborative tasks in order to align with the instantaneous change of human intention. To solve this problem, we proposed an alternate learning-based parameter estimation method and an empirical minimum variation-based decomposition strategy with projection points, combining with linear interpolation strategy for weights, based on a Gaussian mixture model framework. Alternate learning of weights and parameters in multi-task ProMP (MTProMP) allows the robot to obtain a smooth composite trajectory planning which crosses expected via points. Decomposition strategy reflects how the desired via point state is projected onto the individual ProMP component, rendering the minimum total sum of deviations between each projection point with the respective prior. Linear interpolation is used to adjust the weights among sequential via points automatically. The proposed method and strategy are successfully extended to multi-task interaction ProMPs (MTiProMP). With MTProMP and MTiProMP, the robot can be applied to multiple tasks in industrial factories and collaborate with the worker to switch from one task to another according to changing intentions of the human. Classical via points trajectory planning experiments and human-robot collaboration experiments are performed on the Sawyer robot. The results of experiments show that MTProMP and MTiProMP with the proposed method and strategy perform better.

산업용 협동 로봇의 직접교시를 위한 DMP 제어의 교시 정밀도 개선 알고리즘

An industrial manipulator with a high degree of freedom is useful in many tasks. However, to control such a manipulator, one requires an understanding of structures, such as kinematics and robot control, and knowledge of various programming techniques. To operate and control the manipulator conveniently, a control method based on direct teaching is widely used to transmit the intention of a person to the manipulator and operate it. In this paper, we propose a strategy to increase the reference trajectory tracking accuracy of DMP (Dynamic Movement Primitives) based on a reference angular acceleration as a Direct Teaching strategy. A simulation is conducted using two trajectories that are unexpected to expect accurate tracking performance by using DMP, and the feasibility of the proposed strategy is verified by comparing the errors.

Sequential Motion Primitives Recognition of Robotic Arm Task via Human Demonstration Using Hierarchical BiLSTM Classifier

Learning from demonstration (LfD) is an intuitive teaching technology without extensive programming for an operator. In recent LfD research, machine vision is usually used to capture the human-robot interaction. However, it's not reliable during the machining process. In this letter, a novel intuitive high-level kinesthetic teaching technology is proposed by reconstructing the motion information recorded from human-guided demonstrations. A hierarchical BiLSTM-based machine learning algorithm is proposed in this letter to recognize and segment motion primitives according to the therblig definition. A hybrid sensing interface is used to record and extract the motion features, consisting of the velocity profile, force/torque, and gripper information. The motion features are then used to classify into the target motion primitive by the proposed classifier. The experimental results and comparisons with the state-of-the-art algorithm show that the proposed method can correctly and efficiently synthesize the recorded motion features into a motion primitive sequence. Finally, the recognition results of real-world tasks show that the proposed algorithm can be used to reconstruct the human-guided task and further used to command a KUKA robot. The experimental results of the reconstructed trajectory show that a real-world task can represent and maintain the accuracy in 2.37 mm using the proposed algorithm.

Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters

SUMMARYDynamic 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.

Evaluation of Motor Primitive-Based Adaptive Control for Lower Limb Exoskeletons.

In order to assist after-stroke individuals to rehabilitate their movements, research centers have developed lower limbs exoskeletons and control strategies for them. Robot-assisted therapy can help not only by providing support, accuracy, and precision while performing exercises, but also by being able to adapt to different patient needs, according to their impairments. As a consequence, different control strategies have been employed and evaluated, although with limited effectiveness. This work presents a bio-inspired controller, based on the concept of motor primitives. The proposed approach was evaluated on a lower limbs exoskeleton, in which the knee joint was driven by a series elastic actuator. First, to extract the motor primitives, the user torques were estimated by means of a generalized momentum-based disturbance observer combined with an extended Kalman filter. These data were provided to the control algorithm, which, at every swing phase, assisted the subject to perform the desired movement, based on the analysis of his previous step. Tests are performed in order to evaluate the controller performance for a subject walking actively, passively, and at a combination of these two conditions. Results suggest that the robot assistance is capable of compensating the motor primitive weight deficiency when the subject exerts less torque than expected. Furthermore, though only the knee joint was actuated, the motor primitive weights with respect to the hip joint were influenced by the robot torque applied at the knee. The robot also generated torque to compensate for eventual asynchronous movements of the subject, and adapted to a change in the gait characteristics within three to four steps.

Slope Gradient Adaptive Gait Planning for Walking Assistance Lower Limb Exoskeletons

In recent years, lower limb exoskeletons have gained considerable interest in applications of walking assistance for paraplegic patients. In daily lives, the exoskeleton should have the ability to help the patients to walk over different terrains. For sloped terrains, how to plan the stepping locations on slopes with different gradients and generate stable human-like gaits for patients is a critical issue. In this article, we proposed a slope gradient estimator (SGE) based on the sensor data fusion of the exoskeleton and combined SGE with the capture point theory and dynamic movement primitives (DMP) to construct an adaptive gait planning approach for slopes. After learning from demonstrated gaits sampled from healthy subjects, adaptive gait trajectories can be reproduced online to adapt to slopes with different gradients. The efficiency of the proposed approach was demonstrated on an exoskeleton system named AIDER. Experimental results indicate that the proposed approach can endow exoskeletons with the ability to generate appropriate gaits for different slopes. Note to Practitioners —For lower limb exoskeletons, it is a vital problem to plan the gait for sloped terrains. Considering different gradients among slopes, fixed predefined gait planning cannot cover all cases; thus, a slope gradient adaptive gait planning approach is necessary. The slope gradient estimator proposed in this article provides a possible slope gradient estimation method for exoskeletons or humanoid bipedal robots; it is easy to estimate the slope gradient only based on the local sensor data of the robot. The proposed dynamic gait generator provides lower limb exoskeletons and humanoid bipedal robots a possible adaptive gait planning framework and some flexibility for different slopes. The proposed approach may inspire more extended gait planning strategies for other terrains, such as stairs.

Motion Capture Data Analysis in the Instantaneous Frequency-Domain Using Hilbert-Huang Transform.

Motion capture data are widely used in different research fields such as medical, entertainment, and industry. However, most motion researches using motion capture data are carried out in the time-domain. To understand human motion complexities, it is necessary to analyze motion data in the frequency-domain. In this paper, to analyze human motions, we present a framework to transform motions into the instantaneous frequency-domain using the Hilbert-Huang transform (HHT). The empirical mode decomposition (EMD) that is a part of HHT decomposes nonstationary and nonlinear signals captured from the real-world experiments into pseudo monochromatic signals, so-called intrinsic mode function (IMF). Our research reveals that the multivariate EMD can decompose complicated human motions into a finite number of nonlinear modes (IMFs) corresponding to distinct motion primitives. Analyzing these decomposed motions in Hilbert spectrum, motion characteristics can be extracted and visualized in instantaneous frequency-domain. For example, we apply our framework to (1) a jump motion, (2) a foot-injured gait, and (3) a golf swing motion.

Multiparty motion coordination: from choreographies to robotics programs

We present a programming model and typing discipline for complex multi-robot coordination programming. Our model encompasses both synchronisation through message passing and continuous-time dynamic motion primitives in physical space. We specify continuous-time motion primitives in an assume-guarantee logic that ensures compatibility of motion primitives as well as collision freedom. We specify global behaviour of programs in a choreographic type system that extends multiparty session types with jointly executed motion primitives, predicated refinements, as well as a separating conjunction that allows reasoning about subsets of interacting robots. We describe a notion of well-formedness for global types that ensures motion and communication can be correctly synchronised and provide algorithms for checking well-formedness, projecting a type, and local type checking. A well-typed program is communication safe , motion compatible , and collision free . Our type system provides a compositional approach to ensuring these properties. We have implemented our model on top of the ROS framework. This allows us to program multi-robot coordination scenarios on top of commercial and custom robotics hardware platforms. We show through case studies that we can model and statically verify quite complex manoeuvres involving multiple manipulators and mobile robots---such examples are beyond the scope of previous approaches.

Phase-Synchronized Learning of Periodic Compliant Movement Primitives (P-CMPs)

Autonomous trajectory and torque profile synthesis through modulation and generalization require a database of motion with accompanying dynamics, which is typically difficult and time-consuming to obtain. Inspired by adaptive control strategies, this paper presents a novel method for learning and synthesizing Periodic Compliant Movement Primitives (P-CMPs). P-CMPs combine periodic trajectories encoded as Periodic Dynamic Movement Primitives (P-DMPs) with accompanying task-specific Periodic Torque Primitives (P-TPs). The state-of-the-art approach requires to learn TPs for each variation of the task, e.g., modulation of frequency. Comparatively, in this paper, we propose a novel P-TPs framework, which is both frequency and phase-dependent. Thereby, the executed P-CMPs can be easily modulated, and consequently, the learning rate can be improved. Moreover, both the kinematic and the dynamic profiles are parameterized, thus enabling the representation of skills using corresponding parameters. The proposed framework was evaluated on two robot systems, i.e., Kuka LWR-4 and Franka Emika Panda. The evaluation of the proposed approach on a Kuka LWR-4 robot performing a swinging motion and on Franka Emika Panda performing an exercise for elbow rehabilitation shows fast P-CTPs acquisition and accurate and compliant motion in real-world scenarios.

Soft-Grasping With an Anthropomorphic Robotic Hand Using Spiking Neurons

Evolution gave humans advanced grasping capabilities combining an adaptive hand with efficient control. Grasping motions can quickly be adapted if the object moves or deforms. Soft-grasping with an anthropomorphic hand is a great capability for robots interacting with objects shaped for humans. Nevertheless, most robotic applications use vacuum, 2-finger or custom made grippers. We present a biologically inspired spiking neural network (SNN) for soft-grasping to control a robotic hand. Two control loops are combined, one from motor primitives and one from a compliant controller activated by a reflex. The finger primitives represent synergies between joints and hand primitives represent different affordances. Contact is detected with a mechanism based on inter-neuron circuits in the spinal cord to trigger reflexes. A Schunk SVH 5-finger hand was used to grasp objects with different shapes, stiffness and sizes. The SNN adapted the grasping motions without knowing the exact properties of the objects. The compliant controller with online learning proved to be sensitive, allowing even the grasping of balloons. In contrast to deep learning approaches, our SNN requires one example of each grasping motion to train the primitives. Computation of the inverse kinematics or complex contact point planning is not required. This approach simplifies the control and can be used on different robots providing similar adaptive features as a human hand. A physical imitation of a biological system implemented completely with SNN and a robotic hand can provide new insights into grasping mechanisms.

Passive Exercise Adaptation for Ankle Rehabilitation Based on Learning Control Framework.

Ankle injuries are among the most common injuries in sport and daily life. However, for their recovery, it is important for patients to perform rehabilitation exercises. These exercises are usually done with a therapist’s guidance to help strengthen the patient’s ankle joint and restore its range of motion. However, in order to share the load with therapists so that they can offer assistance to more patients, and to provide an efficient and safe way for patients to perform ankle rehabilitation exercises, we propose a framework that integrates learning techniques with a 3-PRS parallel robot, acting together as an ankle rehabilitation device. In this paper, we propose to use passive rehabilitation exercises for dorsiflexion/plantar flexion and inversion/eversion ankle movements. The therapist is needed in the first stage to design the exercise with the patient by teaching the robot intuitively through learning from demonstration. We then propose a learning control scheme based on dynamic movement primitives and iterative learning control, which takes the designed exercise trajectory as a demonstration (an input) together with the recorded forces in order to reproduce the exercise with the patient for a number of repetitions defined by the therapist. During the execution, our approach monitors the sensed forces and adapts the trajectory by adding the necessary offsets to the original trajectory to reduce its range without modifying the original trajectory and subsequently reducing the measured forces. After a predefined number of repetitions, the algorithm restores the range gradually, until the patient is able to perform the originally designed exercise. We validate the proposed framework with both real experiments and simulation using a Simulink model of the rehabilitation parallel robot that has been developed in our lab.

Motion Planning of Upper-Limb Exoskeleton Robots: A Review

(1) Background: Motion planning is an important part of exoskeleton control that improves the wearer’s safety and comfort. However, its usage introduces the problem of trajectory planning. The objective of trajectory planning is to generate the reference input for the motion-control system. This review explores the methods of trajectory planning for exoskeleton control. In order to reduce the number of surveyed papers, this review focuses on the upper limbs, which require refined three-dimensional motion planning. (2) Methods: A systematic search covering the last 20 years was conducted in Ei Compendex, Inspect-IET, Web of Science, PubMed, ProQuest, and Science-Direct. The search strategy was to use and combine terms “trajectory planning”, “upper limb”, and ”exoskeleton” as high-level keywords. “Trajectory planning” and “motion planning” were also combined with the following keywords: “rehabilitation”, “humanlike motion“, “upper extremity“, “inverse kinematic“, and “learning machine “. (3) Results: A total of 67 relevant papers were discovered. Results were then classified into two main categories of methods to plan trajectory: (i) Approaches based on Cartesian motion planning, and inverse kinematics using polynomial-interpolation or optimization-based methods such as minimum-jerk, minimum-torque-change, and inertia-like models; and (ii) approaches based on “learning by demonstration” using machine-learning techniques such as supervised learning based on neural networks, and learning methods based on hidden Markov models, Gaussian mixture models, and dynamic motion primitives. (4) Conclusions: Various methods have been proposed to plan the trajectories for upper-limb exoskeleton robots, but most of them plan the trajectory offline. The review approach is general and could be extended to lower limbs. Trajectory planning has the advantage of extending the applicability of therapy robots to home usage (assistive exoskeletons); it also makes it possible to mitigate the shortages of medical caregivers and therapists, and therapy costs. In this paper, we also discuss challenges associated with trajectory planning: kinematic redundancy and incompatibility, and the trajectory-optimization problem. Commonly, methods based on the computation of swivel angles and other methods rely on the relationship (e.g., coordinated or synergistic) between the degrees of freedom used to resolve kinematic redundancy for exoskeletons. Moreover, two general solutions, namely, the self-tracing configuration of the joint axis and the alignment-free configuration of the joint axis, which add the appropriate number of extra degrees of freedom to the mechanism, were employed to improve the kinematic incompatibility between human and exoskeleton. Future work will focus on online trajectory planning and optimal control. This will be done because very few online methods were found in the scope of this study.

A Novel Human-Like Control Framework for Mobile Medical Service Robot

Recently, as a highly infectious disease of novel coronavirus (COVID-19) has swept the globe, more and more patients need to be isolated in the rooms of the hospitals, so how to deliver the meals or drugs to these infectious patients is the urgent work. It is a reliable and effective method to transport medical supplies or meals to patients using robots, but how to teach the robot to the destination and to enter the door like a human is an exciting task. In this paper, a novel human-like control framework for the mobile medical service robot is considered, where a Kinect sensor is used to manage human activity recognition to generate a designed teaching trajectory. Meanwhile, the learning technique of dynamic movement primitives (DMP) with the Gaussian mixture model (GMM) is applied to transfer the skill from humans to robots. A neural-based model predictive tracking controller is implemented to follow the teaching trajectory. Finally, some demonstrations are carried out in a hospital room to illustrate the superiority and effectiveness of the developed framework.

Muscle Activation Patterns Are More Constrained and Regular in Treadmill Than in Overground Human Locomotion.

The use of motorized treadmills as convenient tools for the study of locomotion has been in vogue for many decades. However, despite the widespread presence of these devices in many scientific and clinical environments, a full consensus on their validity to faithfully substitute free overground locomotion is still missing. Specifically, little information is available on whether and how the neural control of movement is affected when humans walk and run on a treadmill as compared to overground. Here, we made use of linear and non-linear analysis tools to extract information from electromyographic recordings during walking and running overground, and on an instrumented treadmill. We extracted synergistic activation patterns from the muscles of the lower limb via non-negative matrix factorization. We then investigated how the motor modules (or time-invariant muscle weightings) were used in the two locomotion environments. Subsequently, we examined the timing of motor primitives (or time-dependent coefficients of muscle synergies) by calculating their duration, the time of main activation, and their Hurst exponent, a non-linear metric derived from fractal analysis. We found that motor modules were not influenced by the locomotion environment, while motor primitives were overall more regular in treadmill than in overground locomotion, with the main activity of the primitive for propulsion shifted earlier in time. Our results suggest that the spatial and sensory constraints imposed by the treadmill environment might have forced the central nervous system to adopt a different neural control strategy than that used for free overground locomotion, a data-driven indication that treadmills could induce perturbations to the neural control of locomotion.

Learning quadrupedal locomotion over challenging terrain.

Legged locomotion can extend the operational domain of robots to some of the most challenging environments on Earth. However, conventional controllers for legged locomotion are based on elaborate state machines that explicitly trigger the execution of motion primitives and reflexes. These designs have increased in complexity but fallen short of the generality and robustness of animal locomotion. Here, we present a robust controller for blind quadrupedal locomotion in challenging natural environments. Our approach incorporates proprioceptive feedback in locomotion control and demonstrates zero-shot generalization from simulation to natural environments. The controller is trained by reinforcement learning in simulation. The controller is driven by a neural network policy that acts on a stream of proprioceptive signals. The controller retains its robustness under conditions that were never encountered during training: deformable terrains such as mud and snow, dynamic footholds such as rubble, and overground impediments such as thick vegetation and gushing water. The presented work indicates that robust locomotion in natural environments can be achieved by training in simple domains.