Dynamic motion primitives (DMPs) have been widely used in robotics and automation systems because of their rapid deployment capability. Previous research has concentrated on extending coupled dynamic movement primitives (CDMPs) to manipulate rigid objects using a dual-arm robot. However, manipulating deformable objects may fail due to issues with the workspace, manipulability caused by the robot’s layout, and the uncertain dynamics of deformable objects. This research proposes a unique system that combines Learning from Demonstration (LfD) to optimise robot layouts based on human experience and robot manipulability. It also employs a modified CDMPs (MCDMPs) method to manipulate deformable objects. The MCDMPs include a new term to ensure that the deformed object can change its configuration during manipulation. Furthermore, another term is introduced to track the desired trajectory of the deformed object, which is crucial for transporting tasks. We conducted simulations using a mass-spring-damper system for cooperative manipulation to validate the proposed approach. We also employed a dual-arm robot platform to transport a deformed ball with disturbance. The simulation and experimental findings indicate that our method performs well in trajectory tracking and configuration change. Note to Practitioners—This research paper addresses the need for faster deployment of dual-arm robots in various applications, such as industrial and services. We must consider the robot’s installation layout and task programming for rapid deployment. To optimise layouts for tasks quickly, we introduce an optimisation framework which considers the comprehensive performance of dual arms and uses demonstration sampling and learning generalisation. To address the manipulation of deformable objects by dual-arm robots, we use an MCDMPs method that employs the barrier Lyapunov function (BLF) to track changed configurations. Additionally, we introduce a term for reference trajectory tracking component for the manipulated object.

Teleoperation and Learning from Demonstration (LfD) are complementary paradigms for robotic control, yet their synergistic potential remains underexplored. This work proposes a unified framework that dynamically adjusts teleoperation precision using task-specific priors from LfD while optimizing demonstration learning through teleoperation scaling. By analyzing human operator signals (e.g., muscle activity), our method autonomously scales robot movements to balance the precision requirements and execution efficiency during teleoperation. Conversely, teleoperation data informs the adaptive arrangement of motion primitives in LfD, improving trajectory accuracy in critical task phases. Experiments show that the proposed method can improve the efficiency of teleoperation tasks and the accuracy of task learning. This bidirectional synergy offers a practical pathway to enhance both human-robot interaction and skill learning, particularly in applications demanding variable precision, such as assembly and surgical robotics.

Due to changes in the environment and errors that occurred during skill initialization, the robot's operational skills should be modified to adapt to new tasks. As such, skills learned by the methods with fixed features, such as the classical Dynamical Movement Primitive (DMP), are difficult to use when the using cases are significantly different from the demonstrations. In this work, we propose an incremental robot skill learning and generalization framework including an incremental DMP (IDMP) for robot trajectory learning and an adaptive neural network (NN) control method, which are incrementally updated to enable robots to adapt to new cases. IDMP uses multi-mapping feature vectors to rebuild the forcing function of DMP, which are extended based on the original feature vector. In order to maintain the original skills and represent skill changes in a new task, the new feature vector consists of three parts with different usages. Therefore, the trajectories are gradually changed by expanding the feature and weight vectors, and all transition states are also easily recovered. Then, an adaptive NN controller with performance constraints is proposed to compensate dynamics errors and changed trajectories after using the IDMP. The new controller is also incrementally updated and can accumulate and reuse the learned knowledge to improve the learning efficiency. Compared with other methods, the proposed framework achieves higher tracking accuracy, realizes incremental skill learning and modification, achieves multiple stylistic skills, and is used for obstacle avoidance with different heights, which are verified in three comparative experiments.

The moving platform of an RPR-equivalent parallel mechanism (PM) can undergo a 3-degree-of-freedom (DOF) motion that is the product of a rotation followed by a translation and another rotation. A 5-DOF hybrid parallel manipulator can be developed by adding an x-y gantry or an RR serial mechanism to an RPR-equivalent PM, which is suitable for manipulations requiring high rigidity and accuracy with good dexterity along surfaces of the 3-D space. This paper investigates the type synthesis of the RPR-equivalent PM. First, the RPR motion is briefly discussed. Then, the kinematic bonds of limb chains and their mechanical generators are presented. Structural conditions for constructing an RPR-equivalent PM are presented. Furthermore, the RPR-equivalent PMs are classified into several categories, depending on the DOF of its limb chains. Numerous new architectures of the RPR-equivalent PMs are synthesized.

Parasitic motion is a major drawback of the general 1T2R parallel mechanism (PM), where T denotes a translation degree of freedom (DOF) and R a rotational DOF. This paper investigates the type synthesis of the 1T2R PM without parasitic motion. First, a brief review on the planar–spherical bond and its mechanical generators is presented. Then, the difference between the general and special$a$T$b$R motion is discussed. Relations between the parasitic motion and the general and special$a$T$b$R motion are revealed. An infinitesimal 1T2R PM with rotation bifurcation is presented as a special case. Further, the definition of the 1T2R PM without parasitic motion is presented, and the limb bond {${\bf G}$(${\bf u}$)}{${\bf S}$($N$)} is identified. Geometrical conditions to construct an 1T2R PM without parasitic motion are presented, and nonoverconstrained 1T2R PMs without parasitic motion are synthesized. Idle pairs in the nonoverconstrained 1T2R PMs without parasitic motion are detected. Finally, overconstrained 1T2R PMs without parasitic motion are obtained by removing the idle pairs in the nonoverconstrained 1T2R PMs.

One important category of parallel mechanisms is the translational parallel mechanism (TPM). This paper focuses on the structural shakiness of the non overconstrained TPM. Such a structural shakiness is due to the unavoidable lack of rigidity of the real bodies, which leads to uncheckable orientation changes of the moving platform of a TPM. Using algebraic properties of displacement subsets and, especially, displacement Lie subgroup theory, we show that the structural shakiness of the non overconstrained TPM is inherently determined by the structural type of its limb chains. A structural shakiness index (SSI) for a non overconstrained TPM is introduced. When the set of feasible displacements of the end body of a 5-degree-of-freedom (DOFs) limb chain contains two infinities of parallel axes of rotation, we have SSI = 2; when the displacement set of the end body of a 5-DOF limb chain contains only one infinity of parallel axes of rotation, we have SSI = 1. It is proven that non over con stained TPMs constructed with limb chains with SSI = 1 are much less prone to orientation changes than those constructed with limb chains with SSI = 2. Based on the SSI, we enumerate limb kinematic chains and construct 21 non overconstrained TPMs with less shakiness.

Type synthesis of lower mobility parallel mechanisms (PMs) has attracted extensive attention in research community of robotics over the last seven years. One important trend in this area is to synthesize PMs with prespecified motion properties. This paper focuses on the type synthesis of a special family of PMs whose moving platform can undergo a bifurcation of Schoenflies motion. First, bifurcation of Schoenflies motion in PMs is interpreted in terms of displacement group theory and the basic limb bond {X(y)}{R(N,x)} is identified. Further, the geometric condition for constructing a PM with bifurcation of Schoenflies motion is presented. The kinematic equivalence between {X(y)}{R(N,x)} and {X(y)}{X(x)} is proven. Four subcategories of irreducible representation of the product {X(y)}{X(x)} are proposed and the limb chains that produce the desired limb bond are synthesized. Finally, the partitioned mobility of PMs with bifurcation of Schoenflies motion and its effect on actuation selection are discussed.

The use of lower mobility parallel manipulators with less than six degrees of freedom (DOFs) has drawn a lot of interest in the area of parallel robots. In this paper, the type synthesis of 3R2T 5-DOF parallel mechanisms (PMs) is performed systematically using the Lie group of displacements, where R denotes a rotational DOF, and T denotes a translational DOF. First, some necessary theoretical fundamentals about the displacement group are recalled. Then, a general approach is proposed for the type synthesis of 3R2T 5-DOF PMs. The limb kinematic chains, which produce the desired displacement manifolds, are synthesized and enumerated. Structural conditions, which guarantee that the intersection of the displacement manifolds generated by the limb is the desired 5-DOF manifold, are presented. An exhaustive enumeration of 3R2T 5-DOF symmetrical PMs is obtained. Finally, an input selection method is proposed.

The number of 4-DOF (degrees of freedom) parallel manipulators with full-cycle mobility has been small for a long time. In this paper, the type synthesis of 4-DOF parallel manipulators is performed systematically by the constraint-synthesis method. Novel 4-DOF symmetrical and asymmetrical parallel manipulators with full-cycle mobility are identified and enumerated. Moreover, structural characteristics of the 4-DOF parallel manipulators are revealed.

Mobility analysis of lower-mobility parallel manipulators is of great importance in the context of analysis and design. A method is proposed for the mobility analysis of lower-mobility parallel manipulators based on screw theory. The limb structural constraint acting on the moving platform is first analyzed. Then the combined effect of all limb structural constraints is obtained by investigating the geometrical conditions of the linear dependency of them. Moreover, identification of the instantaneous mechanism is performed. The method is testified through examples including 4- and 5-DOF parallel mechanisms.

The number of 5-DOF parallel manipulators is fairly small and it has been believed for a long time that there are no symmetrical 5-DOF parallel manipulators with full-cycle mobility. In this paper, the type synthesis of 5-DOF parallel manipulators is performed systematically by the constraint-synthesis method. Novel 5-DOF symmetrical and asymmetrical parallel manipulators with full-cycle mobility are enumerated. Moreover, structural characteristics of the 5-DOF parallel manipulators are revealed.

Mobility analysis of a 3-5R parallel mechanism family whose limb consists of a 2R and a 3R parallel subchains is performed by the aid of screw theory. A mobility criterion applicable to such 3-leg parallel mechanisms in which each kinemaic chain contains five kinematic pairs is proposed. It is shown that under different structural conditions, the 3-5R parallel mechanism can have 3, 4, or 5 DOF (degrees of freedom). The structural conditions which guarantee the full-cycle mobility are analyzed. The analysis and the method presented in this paper will be helpful in using such a 3-5R parallel mechanism family and introduce new insights into the mobility analysis of parallel mechanisms.