Task Trajectory Research Articles

Trajectory Synthesis and Linkage Design of Single-Degree-of-Freedom Finger Rehabilitation Device

For injured and after-stroke patients who temporarily lose their hand’s grasping abilities, assisting them in regaining their index finger mobility is very important in the rehabilitation process. In this paper, a finger rehabilitation device based on one degree-of-freedom (DOF) linkage mechanism is designed, aiming to lead the index finger through the flexion–extension trajectory during grasping tasks. Two types of one-DOF mechanisms, a four-bar linkage and a Watt-I six-bar linkage, are synthesized for the task trajectory. Various algorithms such as PSO, GA, and GA–BFGS are adopted and compared for the synthesis of these two types of mechanisms, among which the Watt-I six-bar linkage obtained with GA–BFGS shows the optimal performance in accuracy. Clinical biomechanical data are utilized to perform static analyses of the mechanisms, and the feasibility of the Watt-I six-bar linkage models is tested, compared, and demonstrated. Finally, the prototype of the six-bar linkage as well as a wearable exoskeleton finger rehabilitation device are designed to show how they are applied in the finger rehabilitation scenario.

Trajectory Generation Method for Serial Robots in Hybrid Space Operations

The hybrid space of robots is divided into task space and joint space, with task space focused on trajectory-tracking accuracy, while joint space considers dynamic responsiveness and synchronization. Therefore, the robot-motion control systems need to effectively integrate both aspects, ensuring precision in task trajectory while promptly responding to unforeseen environmental events. Hence, this paper proposes an online trajectory-generation method for robots in both joint and task spaces. In task space, a planning approach is presented for high-precision NURBS curves. The global NURBS curve is segmented into several rational Bezier curves, establishing local coordinate systems for control points. This ensures that all local control points meet the chord error constraint, guaranteeing trajectory accuracy. To address the feed rate dynamic planning issue for segmented curves, an improved online S-shape feed-rate scheduling framework is introduced. This framework dynamically adjusts the current execution speed to meet task requirements. In joint space, an offline velocity planning based on a time synchronization scheme and a multi-dimensional synchronization technique based on the principle of spatial-coordinate system projection are proposed. Building upon the offline scheme, it allows for the modification of the target state for any sub-dimension during the motion process, with the remaining dimensions adapting accordingly. Simulation and experimentation demonstrate that the two proposed online trajectory generations for robot motion spaces, while ensuring task trajectory accuracy, effectively handle external unexpected events. They ensure joint synchronization and smoothness, carrying significant practical implications and application value for the stability of robot systems.

Investigation of Multi-Stage Visual Servoing in the context of autonomous assembly

This paper introduces a novel strategy, Multi-Stage Based Visual Servoing (MSBVS), to tackle the significant challenge of planning complex trajectories in robotic systems without hand–eye calibration, particularly in some assembly tasks. The MSBVS strategy decomposes a complete visual servoing process into three distinct phases, each characterized by unique functionalities. By assigning specific image features and control objectives to each phase, the strategy indirectly facilitates the planning and tracking complex trajectories. Furthermore, a novel image feature, the vanishing angle, is introduced, enhancing the precision in representing an object’s spatial position. Subsequently, a robotic vision system is established, and real-time simulations and experiments are performed to verify the efficacy of the MSBVS strategy. The results show that MSBVS efficiently plans and executes complex trajectories in robotic assembly tasks.

Power-Based Safety Constraint for Redundant Robotic Manipulators

A robot making or losing contact with its environment will experience a sudden change in its dynamics. This may cause instability, possibly causing the robot to harm itself and its environment. To prevent this while not placing overly restrictive constraints on the energy generated by the controller, we place a time-varying constraint on the system's power. The power limit varies with a heuristic measure of a desired task trajectory's stability, which is based on the largest Lyapunov exponent. When the trajectory is deemed unstable, the controller is forced to dissipate energy, while it is allowed to generate energy when the trajectory is stable. The constraint is included in a strict task-priority framework, allowing a redundant robotic platform to perform several tasks simultaneously while ensuring that the performance of the higher-priority tasks is not affected by the lower-priority tasks. The presented method is validated by simulation of an articulated intervention autonomous underwater vehicle (AIAUV).

Task-unit based trajectory generation for excavators utilizing expert operator skills

Effective trajectory generation methods are crucial for the development of intelligent excavators. However, current methods face challenges in adapting to dynamic work environments and fulfilling task-specific requirements. This study proposes a trajectory generation method based on task-units. The trenching task is divided into five task-units by interviewing the expert operators, the data collected from the expert operators is further used for task-unit modeling. After that, the infrastructure of the task-units and the connectivity between the individual task-units are established. The advantages of Dynamical Movement Primitives (DMP) and Gaussian mixture models (GMM) are fused to model the trajectory generation of the task-unit. The trajectory reproduction capability of the model is further enhanced by the optimization of the Genetic Algorithm (GA). This method has the capability to generate various task trajectories by generalizing and combining task-units, making it highly applicable.

Peg-in-hole assembly skill imitation learning method based on ProMPs under task geometric representation.

Behavioral Cloning (BC) is a common imitation learning method which utilizes neural networks to approximate the demonstration action samples for task manipulation skill learning. However, in the real world, the demonstration trajectories from human are often sparse and imperfect, which makes it challenging to comprehensively learn directly from the demonstration action samples. Therefore, in this paper, we proposes a streamlined imitation learning method under the terse geometric representation to take good advantage of the demonstration data, and then realize the manipulation skill learning of assembly tasks. We map the demonstration trajectories into the geometric feature space. Then we align the demonstration trajectories by Dynamic Time Warping (DTW) method to get the unified data sequence so we can segment them into several time stages. The Probability Movement Primitives (ProMPs) of the demonstration trajectories are then extracted, so we can generate a lot of task trajectories to be the global strategy action samples for training the neural networks. Notalby, we regard the current state of the assembly task as the via point of the ProMPs model to get the generated trajectories, while the time point of the via point is calculated according to the probability model of the different time stages. And we get the action of the current state according to the target position of the next time state. Finally, we train the neural network to obtain the global assembly strategy by Behavioral Cloning. We applied the proposed method to the peg-in-hole assembly task in the simulation environment based on Pybullet + Gym to test its task skill learning performance. And the learned assembly strategy was also executed on a real robotic platform to verify the feasibility of the method further. According to the result of the experiment, the proposed method achieves higher success rates compared to traditional imitation learning methods while exhibiting reasonable generalization capabilities. It shows that the ProMPs under geometric representation can help the BC method make better use of the demonstration trajectory and thus better learn the task skills.

A rehabilitation robot control framework with adaptation of training tasks and robotic assistance.

Robot-assisted rehabilitation has exhibited great potential to enhance the motor function of physically and neurologically impaired patients. State-of-the-art control strategies usually allow the rehabilitation robot to track the training task trajectory along with the impaired limb, and the robotic motion can be regulated through physical human-robot interaction for comfortable support and appropriate assistance level. However, it is hardly possible, especially for patients with severe motor disabilities, to continuously exert force to guide the robot to complete the prescribed training task. Conversely, reduced task difficulty cannot facilitate stimulating patients' potential movement capabilities. Moreover, challenging more difficult tasks with minimal robotic assistance is usually ignored when subjects show improved performance. In this paper, a control framework is proposed to simultaneously adjust both the training task and robotic assistance according to the subjects' performance, which can be estimated from the users' electromyography signals. Concretely, a trajectory deformation algorithm is developed to generate smooth and compliant task motion while responding to pHRI. An assist-as-needed (ANN) controller along with a feedback gain modification algorithm is designed to promote patients' active participation according to individual performance variance on completing the training task. The proposed control framework is validated using a lower extremity rehabilitation robot through experiments. The experimental results demonstrate that the control scheme can optimize the robotic assistance to complete the subject-adaptation training task with high efficiency.

Cascaded ESO based multi-task priority tracking and null-space compliance control for redundant robots

This paper investigates multi-task priority trajectory tracking and null-space compliance control of redundant robots without joint velocity and joint torque sensors. A novel multi-task priority controller is proposed to improve the dynamic performance and robustness of all level tasks. First, a cascaded extended state observer (ESO) is put forward to estimate joint velocity, lumped disturbances and the interference from high-priority tasks to low-priority tasks simultaneously. Then, a tracking controller for higher priority tasks and a null space compliance controller for the lowest priority task are designed. The stability of the closed loop system under the proposed cascaded ESO and task trajectory tracking controller is analyzed, as well as the passivity of the lowest priority task. The parameter tunning procedure of the cascaded ESO is given. Comparative simulation and experiment results verify the effectiveness of the proposed method.

Effective utilization of attentional resources in postural control in athletes of skill-oriented sports: an event-related potential study.

Postural control plays a key role in skill-oriented sports. Athletes of skill-oriented sports (hereinafter referred to as "skilled athletes") usually showed better control ability compared with non-athletes. However, research focused on the single postural task, rarely considering the actual situation in skill-oriented sports in which other processes, such as cognitive control, frequently accompany postural control. This study aims to explore how skilled athletes control their posture under the dual-task situation and use limited attentional resources. A total of 26 skilled athletes and 26 non-athletes were required to perform the postural control and N-back tasks simultaneously. Center of pressure (COP) trajectory, reaction times (RTs), and discriminability (d') of N-back tasks were recorded and evaluated, along with event-related potentials, including N1 (Oz, PO7, and PO8), P2 (Fz, FCz, Cz, and Pz) components, and the spectral power of alpha band. Skilled athletes demonstrated more postural control stability and a higher d' than non-athletes in all dual tasks. Besides, they showed enhanced N1, P2 amplitudes and reduced alpha band power during dual-tasking. Notably, in skilled athletes, a significant negative correlation between N1 amplitude and d' was observed, while significant positive correlations between alpha band power and postural control performance were also identified. This study investigates the potential advantages of skilled athletes in postural control from the view of neuroscience. Compared to non-athletes, skilled athletes could decrease the consumption of attentional resources in postural control and recruit more attentional resources in stimulus discrimination and evaluation in cognitive tasks. Since the allocation of attentional resources plays a crucial part in postural control in skilled athletes, optimizing the postural control training program and the selection of skilled athletes from a dual-task perspective is important.

Vision-Based Virtual Impedance Control for Robotic System Without Prespecified Task Trajectory

This article proposes a vision-based virtual impedance control (VBVIC) scheme for the robotic system without pre-specified task trajectory, where a neural network (NN) is used to compensate for the unmodeled dynamics and parameter uncertainties. In the proposed scheme, a novel control framework combined virtual potential field (VPF) with the impedance control is proposed to achieve non-contact impedance control, where the task trajectory does not need to be pre-specified but is generated by integrating the bio-inspired Tau-J into the virtual impedance model. Moreover, the virtual force generated by VPF is utilized to achieve the shaping and tracking of the task trajectory in the virtual impedance control scheme, and the information of target and obstacle is obtained by the visual sensing. The proposed VPF-based VBVIC scheme is analyzed by the Lyapunov stability theory and validated by a carrying task in simulations and experiments, respectively.

Stiffness Modeling and Dynamics Co-Modeling for Space Cable-Driven Linkage Continuous Manipulators

The space cable-driven continuous manipulator (SCCM) has a slender structure, ultra-high degrees of freedom, and a low mass, which make it suitable for equipment inspection and maintenance operations in an unstructured and limited space environment. In this paper, the SCCM including the cable network and plenty of joint links was deeply modeled. Firstly, the mapping relationship between the cable-driving space, joint space, and task space of the SCCM was studied, and the complete kinematic relationship of the SCCM was established. Secondly, the stiffness components of the SCCM are discussed, and the stiffness modeling method of each part is given. Finally, the Cartesian space equivalent stiffness model of the end was established. Then, a dynamic co-modeling method of Matlab + Adams is proposed, which greatly improved the modeling efficiency while ensuring the modeling accuracy. Finally, based on the stiffness model, the end stiffness characteristics of a specific configuration were analyzed, and the influence of the cable tension on the stiffness and frequency of the manipulator was analyzed. Based on the dynamic co-modeling, the task trajectory dynamics’ simulation analysis and space slit crossing experiment were carried out, which verified that the designed SCCM can meet the needs of slit crossing.

Gaussian-process-based robot learning from demonstration

AbstractLearning from demonstration allows to encode task constraints from observing the motion executed by a human teacher. We present a Gaussian-process-based learning from demonstration (LfD) approach that allows robots to learn manipulation skills from demonstrations of a human teacher. By exploiting the potential that Gaussian process (GP) models offer, we unify in a single, entirely GP-based framework, the main features required for a state-of-the-art LfD approach. We address how GP can be used to effectively learn a policy from trajectories in task space. To achieve an effective generalization across demonstrations, we propose the novel Task Completion Index (TCI) for temporal alignment of task trajectories. Also, our probabilistic GP-based representation allows encoding variability throughout the different phases of the task. Finally, we present a method to efficiently adapt the policy to fulfill new requirements and modulate the robot behavior as a function of task variability. This approach has been successfully tested in a real-world application, namely teaching a TIAGo robot to open different types of doors.

Touch Semantics for Intuitive Physical Manipulation of Humanoids

Rather than systematically programming joint or task trajectories, having a human physically manipulate the robot for direct adjustments is more intuitive, saves time, and increases usability, especially for nonexperts. Interactive motion generation or repositioning of humanoid robots through direct human-touch manipulation is not an easy task, especially for high-level multijoint maneuvers. We propose a set of design rules for generating intuitive touch semantics called the “two-touch kinematic chain paradigm.” Our method interprets user touch intentions to allow motions ranging from low-level single joint control to high-level whole-body task control with posture generation, stepping, and walking. The goal is to provide the user with an intuitive protocol for physical humanoid manipulation that can serve the purpose of any application. The generated set of touch semantics is embodied in a finite state machine-based framework using a task-space quadratic programming controller to interpret human touch using capacitive sensors embedded in the humanoid shell, and force-torque sensors located at the ankles and wrists. A position-controlled humanoid robot is used to assess the utility and function of our proposed touch semantics for physical manipulation. Furthermore, a user study with nonexperts examines how our approach is perceived in practice.

Robot Task Learning With Motor Babbling Using Pseudo Rehearsal

The paradigm of deep robot learning from demonstrations allows robots to solve complex manipulation tasks by capturing motor skills from given demonstrations; however, collecting demonstrations can be costly. As an alternative, robots can acquire embodiment and motor skills by randomly moving their bodies, which is referred to as motor babbling. Motor babbling data provide relatively inexpensive demonstrations and can be used to enhance the generalizability of robot motions, but they are often used for pre-training or joint training with target task demonstrations. This study focused on the concept of pseudo-rehearsal and retaining the embodiment information acquired from motor babbling data for effective task learning. Pseudo-rehearsal has beneficial features that allow robot models to be retrained and distributed without access to the motor babbling dataset. In this paper, we propose a pseudo-rehearsal framework that can be jointly trained with task trajectories and rehearsed motor babbling trajectories. Using our proposed method, robots can retain motor skills from motor babbling and exhibit improved performance in task execution.

An enhanced approach for joint configuration of a robot performing in a repetitive task

Human-Centric Manufacturing considers the integration of the industrial automation systems with human capabilities. It combines the strength, speed, repeatability and precision of automation with the intelligence, flexibility and skill of human operators. This advanced manufacturing concept strongly emphasis on human-assisted robotic operation. Recently, the interest in the human-robot cooperative industrial robot which can work together with human through physical interaction in the same space has increased. The direct teaching technology for human-robot cooperation enables an operator who is not used to robot programming to control the robot easily by teaching the task trajectory directly. However, because of the industrial robot inverse kinematics characteristics, there are multiple different inverse kinematics solutions in configure space. The planned trajectory based on the track points selected by the operator may be not efficient enough for the task. Hence, optimizing the joint configurations of a robot in a repetitive task becomes one of the increasingly important issues. In this paper, a mathematical model of the robotic joint configurations based on graph theory is developed, which takes into account repeat task constraints. An enhanced approach for the joint configuration of a robot in a repetitive task is proposed. It leads to the reduction of computational complexity and computing time. A numerical experiment and a case study of the optimization of time consumption in an industrial repetitive task are reported to show the effectiveness of the proposed approach.

Interplay of coordination, co-creation and community building: examining interprofessional collaboration in workplace development efforts in health care

PurposeInterprofessional collaboration (IPC) is increasingly important in work and workplace learning. The purpose of this paper is to investigate the characteristics of IPC that are relevant for learning and developing at work.Design/methodology/approachWe examine IPC in the discussion data of health care professionals when designing, implementing and evaluating developmental tasks. Qualitative content analysis is carried out on temporally sequential task trajectories, considering IPC from the perspective of the objects and goals of IPC task activity in developmental efforts.FindingsThe developmentally relevant characteristics of IPC are crystallized in the concepts of coordination, co-creation and community building, which play different, interdependent roles in development efforts. We show their interplay and how they complement each other in practice.Research limitations/implicationsOur findings regarding IPC characteristics are to be interpreted as working hypotheses and resources for further research.Practical implicationsUnderstanding the dynamics of IPC is useful for renewing work practices. Attention to the interplay and complementarity of IPC characteristics may help in the design and implementation of effective and sustained development efforts.Originality/valueThe dynamics of IPC in developmental settings have not been sufficiently studied. This paper proposes three developmentally relevant and intertwined characteristics of IPC for scholars of workplace learning.

Single Swept Volume Reconstruction by Signed Distance Function Learning: A feasibility study based on implicit geometric regularization

In automated production using collaborative robots in a manufacturing cell, a crucial aspect to ensure the safety of workers and robots in human-robot interaction is to avoid collisions or detect unsafe situations. When detecting collisions, one approach is the use of swept volume to identify safe protective space for the operation or maintenance. To reduce the cost of collision checking due to the complexity of swept volume geometries, we propose to use Implicit Geometric Regularization (IGR) to train the signed distance function of the precomputed swept volume as a continuous collision detector during task trajectory execution. We validate the accuracy of the reconstruction given by Hausdorff distance and memory budgets over three trajectory instances followed by planar 2-link and PUMA-like fixed-base robot arms with polyhedral links and rotary joints. The simulation results and the error analysis of test scenarios suggest that it is feasible to model the signed distance function of a precomputed swept volume by IGR.

Finite-Time Task-Space Coordinated Tracking of Networked Robotic Manipulators With Uncertain Dynamics and Disturbances

This article investigates task-space coordinated tracking in a finite time for networked robotic manipulators under uncertain dynamics and external disturbances. In contrast to the existing works by Liu and Chopra, Wang, Wang, Liang et al., and Zhang et al. that provide asymptotic convergence and require all the robots to have full access to the desired global task reference and communicate via either undirected or strongly connected graphs, the goal of this article is to propose an estimation and control framework so that task-space coordinated tracking can be achieved in a finite-time and robust manner over a directed graph with a spanning tree. Specifically, a supertwisting-based distributed estimator is developed first for each robot to estimate the desired global task trajectory in the finite time. By incorporating this estimated information, finite-time distributed adaptive control laws are designed to achieve task-space coordinated tracking irrespective of uncertain robot dynamics and disturbances. To demonstrate the effectiveness of the proposed approach, numerical simulations are presented.

Hybrid Imitation Learning Framework for Robotic Manipulation Tasks.

This study proposes a novel hybrid imitation learning (HIL) framework in which behavior cloning (BC) and state cloning (SC) methods are combined in a mutually complementary manner to enhance the efficiency of robotic manipulation task learning. The proposed HIL framework efficiently combines BC and SC losses using an adaptive loss mixing method. It uses pretrained dynamics networks to enhance SC efficiency and performs stochastic state recovery to ensure stable learning of policy networks by transforming the learner’s task state into a demo state on the demo task trajectory during SC. The training efficiency and policy flexibility of the proposed HIL framework are demonstrated in a series of experiments conducted to perform major robotic manipulation tasks (pick-up, pick-and-place, and stack tasks). In the experiments, the HIL framework showed about a 2.6 times higher performance improvement than the pure BC and about a four times faster training time than the pure SC imitation learning method. In addition, the HIL framework also showed about a 1.6 times higher performance improvement and about a 2.2 times faster training time than the other hybrid learning method combining BC and reinforcement learning (BC + RL) in the experiments.

Iterative learning-based path control for robot-assisted upper-limb rehabilitation

AbstractIn robot-assisted rehabilitation, the performance of robotic assistance is dependent on the human user’s dynamics, which are subject to uncertainties. In order to enhance the rehabilitation performance and in particular to provide a constant level of assistance, we separate the task space into two subspaces where a combined scheme of adaptive impedance control and trajectory learning is developed. Human movement speed can vary from person to person and it cannot be predefined for the robot. Therefore, in the direction of human movement, an iterative trajectory learning approach is developed to update the robot reference according to human movement and to achieve the desired interaction force between the robot and the human user. In the direction normal to the task trajectory, human’s unintentional force may deteriorate the trajectory tracking performance. Therefore, an impedance adaptation method is utilized to compensate for unknown human force and prevent the human user drifting away from the updated robot reference trajectory. The proposed scheme was tested in experiments that emulated three upper-limb rehabilitation modes: zero interaction force, assistive and resistive. Experimental results showed that the desired assistance level could be achieved, despite uncertain human dynamics.