Efficient Motion Research Articles

Interactive Path Editing and Simulation System for Motion Planning and Control of a Collaborative Robot

Robots in hazardous environments demand precise and advanced motion control, making extensive simulations crucial for verifying the safety of motion planning. This paper presents a simulation system that enables interactive path editing, allowing for motion planning in a simulated collaborative robot environment and its real-world application. The system includes a simulation host, a control board, and a robot. Unity 3D on a Windows platform provides the simulation environment, while a virtual Linux environment runs ROS2 for execution. Unity sends edited motion paths to ROS2 using the Unity ROS TCP Connector package. The ROS2 MoveIt framework generates trajectories, which are synchronized back to Unity for simulation and real-world validation. To control the six-axis Indy7 collaborative robot, we used the MIO5272 embedded board as an EtherCAT master. Verified trajectories are sent to the target board, synchronizing the robot with the simulation in position and speed. Data are relayed from the host to the MIO5272 using ROS2 and the Data Distribution Service (DDS) to control the robot via EtherCAT communication. The system enables direct simulation and control of various trajectories for robots in hazardous environments. It represents a major advancement by providing safe and optimized trajectories through efficient motion planning and repeated simulations, offering a clear improvement over traditional time-consuming and error-prone teach pendant methods.

Designing highly efficient interlocking interactions in anisotropic active particles

Cluster formation of microscopic swimmers is key to the formation of biofilms and colonies, efficient motion and nutrient uptake, but, in the absence of other interactions, requires high swimmer concentrations to occur. Here we experimentally and numerically show that cluster formation can be dramatically enhanced by an anisotropic swimmer shape. We analyze a class of model microswimmers with a shape that can be continuously tuned from spherical to bent and straight rods. In all cases, clustering can be described by Michaelis-Menten kinetics governed by a single scaling parameter that depends on particle density and shape only. We rationalize these shape-dependent dynamics from the interplay between interlocking probability and cluster stability. The bent rod shape promotes assembly in an interlocking fashion even at vanishingly low particle densities and we identify the most efficient shape to be a semicircle. Our work provides key insights into how shape can be used to rationally design out-of-equilibrium self-organization, key to creating active functional materials and processes that require two-component assembly with high fidelity.

Steady motion of 80-nm-size skyrmions in a 100-nm-wide track

The current-driven movement of magnetic skyrmions along a nanostripe is essential for the advancement and functionality of a new category of spintronic devices resembling racetracks. Despite extensive research into skyrmion dynamics, experimental verification of current-induced motion of ultra-small skyrmions within an ultrathin nanostripe is still pending. Here, we unveil the motion of individual 80 nm-size skyrmions in an FeGe track with an ultrathin width of 100 nm. The skyrmions can move steadily along the track over a broad range of current densities by using controlled pulse durations of as low as 2 ns. The potential landscape, arising from the magnetic edge twists in such a geometrically confined system, introduces skyrmion inertia and ensures efficient motion with a vanishing skyrmion Hall angle. Our results showcase the steady motion of skyrmions in an ultrathin track, offering a practical pathway for implementing skyrmion-based spintronic devices.

A hybrid task-constrained motion planning for collaborative robots in intelligent remanufacturing

Industrial manipulators have extensively collaborated with human operators to execute tasks, e.g., disassembly of end-of-use products, in intelligent remanufacturing. A safety task execution requires real-time path planning for the manipulator’s end-effector to autonomously avoid human operators. This is even more challenging when the end-effector needs to follow a planned path while avoiding the collision between the manipulator body and human operators, which is usually computationally expensive and limits real-time application. This paper proposes an efficient hybrid motion planning algorithm that consists of A∗ algorithm and an online manipulator reconfiguration mechanism (OMRM) to tackle such challenges in task and configuration spaces, respectively. A∗ algorithm is first leveraged to plan the shortest collision-free path of the end-effector in task space. When the manipulator body is risky to the human operator, our OMRM then selects an alternative joint configuration with minimum reconfiguration effort from a database to assist the manipulator to follow the planned path and avoid the human operator simultaneously. The database of manipulator reconfiguration establishes the relationship between the task and configuration space offline using forward kinematics, and is able to provide multiple reconfiguration candidates for a desired end-effector’s position. The proposed new hybrid algorithm plans safe manipulator motion during the whole task execution. Extensive numerical and experimental studies, as well as comparison studies between the proposed one and the state-of-the-art ones, have been conducted to validate the proposed motion planning algorithm.

An efficient motion visual learning method for video action recognition

Currently, efficient spatio-temporal information modeling is one of the key research components to solve the action recognition problem. Previous approaches focus on enhancing the backbone features individually using hierarchical structures, and unfortunately, most of them fail to achieve a better balance between the interactional adequacy of features within the structure. In this work, we propose an effective Multi-dimensional Adaptive Fusion Network (MDAF-Net), which can be embedded into the mainstream action recognition backbone in a plug-and-play manner to fully activate the transfer and representation of action features in the deep network. Specifically, our MDAF-Net contains two main components: the Adaptive Temporal Capture Module (ATCM) and the Extended Spatial and Channel Module (ESCM). The ATCM effectively suppresses the over-expression of similar features in adjacent frames and activates the expression of motion flow information. The ESCM further improves temporal modeling efficiency by extending the spatial feature perceptual field and enhancing channel attention. Extensive experiments on several challenging action recognition benchmarks, such as Something-Something V1&V2 and Kinetics-400, demonstrate that the proposed MDAF can achieve state-of-the-art and competitive performance.

Free-breathing 3D whole-heart joint T1/T2 mapping and water/fat imaging at 0.55 T.

To develop and validate a highly efficient motion compensated free-breathing isotropic resolution 3D whole-heart joint T1/T2 mapping sequence with anatomical water/fat imaging at 0.55 T. The proposed sequence takes advantage of shorter T1 at 0.55 T to acquire three interleaved water/fat volumes with inversion-recovery preparation, no preparation, and T2 preparation, respectively. Image navigators were used to facilitate nonrigid motion-compensated image reconstruction. T1 and T2 maps were jointly calculated by a dictionary matching method. Validations were performed with simulation, phantom, and in vivo experiments on 10 healthy volunteers and 1 patient. The performance of the proposed sequence was compared with conventional 2D mapping sequences including modified Look-Locker inversion recovery and T2-prepared balanced steady-SSFP sequence. The proposed sequence has a good T1 and T2 encoding sensitivity in simulation, and excellent agreement with spin-echo reference T1 and T2 values was observed in a standardized T1/T2 phantom (R2 = 0.99). In vivo experiments provided good-quality co-registered 3D whole-heart T1 and T2 maps with 2-mm isotropic resolution in a short scan time of about 7 min. For healthy volunteers, left-ventricle T1 mean and SD measured by the proposed sequence were both comparable with those of modified Look-Locker inversion recovery (640 ± 35 vs. 630 ± 25 ms [p = 0.44] and 49.9 ± 9.3 vs. 54.4 ± 20.5 ms [p = 0.42]), whereas left-ventricle T2 mean and SD measured by the proposed sequence were both slightly lower than those of T2-prepared balanced SSFP (53.8 ± 5.5 vs. 58.6 ± 3.3 ms [p < 0.01] and 5.2 ± 0.9 vs. 6.1 ± 0.8 ms [p = 0.03]). Myocardial T1 and T2 in the patient measured by the proposed sequence were in good agreement with conventional 2D sequences and late gadolinium enhancement. The proposed sequence simultaneously acquires 3D whole-heart T1 and T2 mapping with anatomical water/fat imaging at 0.55 T in a fast and efficient 7-min scan. Further investigation in patients with cardiovascular disease is now warranted.

Efficient Motion Primitives-Based Trajectory Planning for UAVs in the Presence of Obstacles

The achievement of full autonomy in Unmanned Aerial Vehicles (UAVs) is significantly dependent on effective motion planning. Specifically, it is crucial to plan collision-free trajectories for smooth transitions from initial to final configurations. However, finding a solution executable by the actual system adds complexity: the planned motion must be dynamically feasible. This involves meeting rigorous criteria, including vehicle dynamics, input constraints, and state constraints. This work addresses optimal kinodynamic motion planning for UAVs in the presence of obstacles by employing a hybrid technique instead of conventional search-based or direct trajectory optimization approaches. This technique involves precomputing a library of motion primitives by solving several Two-Point-Boundary-Value Problems (TPBVP) offline. This library is then repeatedly used online within a graph-search framework. Moreover, to make the method computationally tractable, continuity between consecutive motion primitives is enforced only on a subset of the state variables. This approach is compared with a state-of-the-art quadrotor-tailored search-based approach, which generates motion primitives online through control input discretization and forward propagation of the dynamic equations of a simplified model. The effectiveness of both methods is assessed through simulations and real-world experiments, demonstrating their ability to generate resolution-complete, resolution-optimal, collision-free, and dynamically feasible trajectories. Finally, a comparative analysis highlights the advantages, disadvantages, and optimal usage scenarios for each approach.

Renewable Electroconductive Hydrogels for Accelerated Diabetic Wound Healing and Motion Monitoring.

Diabetic foot ulcers (DFUs), a prevalent complication of diabetes mellitus, may result in an amputation. Natural and renewable hydrogels are desirable materials for DFU dressings due to their outstanding biosafety and degradability. However, most hydrogels are usually only used for wound repair and cannot be employed to monitor motion because of their inherent poor mechanical properties and electrical conductivity. Given that proper wound stretching is beneficial for wound healing, the development of natural hydrogel patches integrated with wound repair properties and motion monitoring was expected to achieve efficient and accurate wound healing. Here, we designed a dual-network (chitosan and sodium alginate) hydrogel embedded with lignin-Ag and quercetin-melanin nanoparticles to achieve efficient wound healing and motion monitoring. The double network formed by the covalent bond and electrostatic interaction confers the hydrogel with superior mechanical properties. Instead of the usual chemical reagents, genipin extracted from Gardenia was used as a cross-linking agent for the hydrogel and consequently improved its biosafety. Furthermore, the incorporation of lignin-Ag nanoparticles greatly enhanced the mechanical strength, antibacterial efficacy, and conductivity of the hydrogel. The electrical conductivity of hydrogels gives them the capability of motion monitoring. The motion sensing mechanism is that stretching of the hydrogel induced by motion changes the conductivity of the hydrogel, thus converting the motion into an electrical signal. Meanwhile, quercetin-melanin nanoparticles confer exceptional adhesion, antioxidant, and anti-inflammatory properties to the hydrogels. The system ultimately achieved excellent wound repair and motion monitoring performance and was expected to be used for stretch-assisted safe and accurate wound repair in the future.

A high-adhesive and sensitive hydrogel with interpenetrating and interlocking networked structure for efficient biological signal monitoring

Smart flexible sensing materials and devices for wearable health monitoring are considered as prospective and promising areas in healthcare that are currently in high demand in the market. Conductive hydrogel-based sensors, which closely resemble human tissue, encounter notable challenges in attaining high electronic conduction, robust mechanical properties, biocompatibility, and intimate tissue adhesion simultaneously. In this work, a poly(2-acrylamide-2-methylpropane sulfonic acid-co-acrylamide)/bacterial cellulose (P(AMPS-co-AM)/BC) hydrogel with a particular interpenetrating and interlocking networked structure is reported. This hydrogel possesses all the mentioned intriguing properties plus easy degradability. It is realized by utilizing the interaction between amino, amide, and sulfonic groups on polymer molecular chains and polyhydroxy groups on bacterial cellulose. This hydrogel exhibits high strength (1.28 MPa) and tensile strain (525 %), remarkable tissue adhesion (697 kPa), exceptional antibacterial property and low cytotoxicity. Furthermore, it can degrade in the natural environment when exposed to UV light irradiation. The hydrogel-based strain sensors have demonstrated efficient human motion detection with a broad strain detection range (0–360 %) and a high sensitivity (GF = 11.36). Moreover, this hydrogel can be assembled into Triboelectric Nanogenerator for monitoring biological signals. This work presents a new avenue for human-machine interaction and electronic robotic skins.

Application of VR motion intelligent capture based on DLPMA algorithm in sports training

With the rapid development of Virtual Reality (VR) technology, its application in the field of sports training is also receiving increasing attention. This study applies the Distance Likelihood Based Probabilistic Model Averaging (DLPMA) algorithm to the VR motion intelligent capture system, aiming to provide an efficient and accurate motion data collection method to improve existing sports training methods. Introduced the design and implementation of a VR motion intelligent capture system based on DLPMA algorithm, and applied it to sports training. By conducting comparative experiments with traditional training methods, the advantages of the system in motion capture accuracy, real-time performance, and user experience are verified. The research results indicate that the system can accurately capture the movements of athletes and provide timely feedback to users, providing an effective auxiliary means for sports training. Although the system has shown good performance in sports training, there are still some limitations. Future research can further optimize algorithms, enhance system stability and flexibility, to meet a wider range of sports training needs.

Numerical Simulation of the Advantages of the Figure-Eight Flapping Motion of an Insect on Aerodynamics under Low Reynolds Number Conditions.

In proceeding with the advanced development of small unmanned aerial vehicles (UAVs), which are small flying machines, understanding the flight of insects is important because UAVs that use flight are attracting attention. The figure-eight trajectory of the wing tips is often observed in the flight of insects. In this study, we investigated the more efficient figure-eight motion patterns in generating lift during the hovering motion and the relationship between figure-eight motion and Reynolds number. For this purpose, we compared the ratios of the cycle-averaged lift coefficient to the power coefficient generated from each motion by varying the elevation motion angle, which is the rotational motion that represents the figure-eight motion, and the Reynolds number. The result showed that the motion with a smaller initial phase of the elevation motion angle (φe0≤90°) could generate lift more efficiently at all Reynolds numbers. In addition, the figure-eight motion was more effective when the Reynolds number was low.

Teacher-student guided knowledge distillation for unsupervised convolutional neural network-based speckle tracking in ultrasound strain elastography.

Accurate and efficient motion estimation is a crucial component of real-time ultrasound elastography (USE). However, obtaining radiofrequency ultrasound (RF) data in clinical practice can be challenging. In contrast, although B-mode (BM) data is readily available, elastographic data derived from BM data results in sub-optimal elastographic images. Furthermore, existing conventional ultrasound devices (e.g., portable devices) cannot provide elastography modes, which has become a significant obstacle to the widespread use of traditional ultrasound devices. To address the challenges above, we developed a teacher-student guided knowledge distillation for an unsupervised convolutional neural network (TSGUPWC-Net) to improve the accuracy of BM motion estimation by employing a well-established convolutional neural network (CNN) named modified pyramid warping and cost volume network (MPWC-Net). A pre-trained teacher model based on RF is utilized to guide the training of a student model using BM data. Innovations outlined below include employing spatial attention transfer at intermediate layers to enhance the guidance effect of the model. The loss function consists of smoothness of the displacement field, knowledge distillation loss, and intermediate layer loss. We evaluated our method on simulated data, phantoms, and in vivo ultrasound data. The results indicate that our method has higher signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) values in axial strain estimation than the model trained on BM. The model is unsupervised and requires no ground truth labels during training, making it highly promising for motion estimation applications.

Simplified neural architecture for efficient human motion prediction in human-robot interaction

Human motion prediction is essential for safe and effective human-robot interaction, but modeling the intricate spatio-temporal dynamics inherent in human movement remains challenging. While recent methods have advanced motion prediction accuracy, they rely on complex neural architectures such as Graph Convolutional Networks and Recurrent Neural Networks, demanding extensive hyperparameter tuning. To overcome this limitation, we propose a streamlined multi-stage layer incremental perceptron (MSLP) architecture that achieves competitive results with far fewer parameters, improving efficiency. The MSLP eschews the complexity of prevalent networks and instead takes a stepped refinement approach to predict intricate motions using a lightweight model. This simplified yet effective design enables nuanced learning of spatio-temporal relationships without exhaustive tuning. Specifically, the MSLP incorporates two key components: a multi-channel feature extraction and enhancement block (MFE-block) and a temporal feature extraction module (TFE-block). The MFE-block strengthens the representation of each action node by integrating multi-dimensional action features. The TFE-block then captures the contextual relationships between actions over time. Together, the MFE-block and TFE-block allow the MSLP to model the complex spatial and temporal dynamics of human movement using a streamlined architecture and minimal parameter tuning. When evaluated on established datasets including Human3.6 M, CMU, 3DPW, and AMASS, the proposed MSLP method achieves improved accuracy gains of 16.7%-67.0% over existing state-of-the-art techniques. Additionally, the MSLP significantly reduces the number of parameters by 35.7%-99.5% compared to prior architectures. We find that the proposed MSLP significantly improves both long-term prediction and generalization capabilities of the model.

Motion Learning and Generalization of Musculoskeletal Robot Using Gain Primitives

Organisms have an innate ability to rapidly produce diverse and flexible movement. Biological motor systems are composed of highly redundant muscle actuators and have strongly nonlinear dynamic characteristics. How organisms cope with such complex system is still an open question. Motor primitive theory proposed by neuroscientists has provided a convincing explanation for this extraordinary ability and have supported by several biological evidence. In this paper, based on the gain primitive model of cortical network proposed by neuroscientists, new algorithms for learning and combining gain primitives were designed to control musculoskeletal and robotic system with highly redundant actuators. It can realize dimensionality reduction of controll from the number of actuators to the number of primitives. A parameter adaptation algorithm inspired by monoamines modulation mechanism was applied to improve the learning efficiency of gain primitive. Learned motion experiences and primitives were introduced to effectively generate new movements. Validation experiments were carried out on a musculoskeletal model with 9 muscles and an articulated robot Baxter with redundant actuators. The experimental results demonstrated that the recurrent neural network modulated by gain primitives can generate high-dimensional control signals and realize efficient motion generalization for practical systems. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper applied a biologically plausible control method with gain primitive to practical systems with highly redundant actuators. To reduce the cumulative error occurring in learning gain primitive for control networks with high dimensional output, a bioinspired Hebbian learning rule was applied to train a recurrent neural network for optimizing the gain primitive. During the training process, systematic entropy was introduced as an index to adaptively adjust learning parameters, so as to reduce the exploration cost and improve the learning stability of the system. To realize easy implementation and generalization, prior motion experiences were introduced into the initialization of the optimization algorithm, and motion generalization was realized by using the particle swarm optimization algorithm. The algorithms designed in this paper are applicable to complex systems with highly redundant actuators such as humanoid robots.

Coupled Dynamics of Steady Jet Flow Control for Flexible Membrane Wings

We present a steady jet-flow-based flow control of flexible membrane wings for the adaptive and efficient motion of bat-inspired drones in complex flight environments. A body-fitted variational computational aeroelastic framework is adopted for the modeling of fluid–structure interactions. High-momentum jet flows are injected from the leading edge and transported to the wake flows to alter the aerodynamic performance and the membrane vibration. The coupled dynamic effect of active jet flow control on membrane performance is systematically explored. While the results indicate that the current active flow control strategy performs well at low angles of attack, its effectiveness degrades at high angles of attack with large flow separation. To understand the coupling mechanism, the variations of the vortex patterns are examined by the proper orthogonal decomposition modes, and the fluid transport process is studied by the Lagrangian coherent structures. Two scaling relations that quantitatively connect the membrane deformation with the aerodynamic loads presented in our previous work are verified even when active jet flow control is applied. A unifying feedback loop that reveals the fluid–membrane coupling mechanism is proposed. These findings can facilitate the development of next-generation bio-inspired drones that incorporate smart sensing and intelligent control.

Everything2Motion: Synchronizing Diverse Inputs via a Unified Framework for Human Motion Synthesis

In the dynamic field of film and game development, the emergence of human motion synthesis methods has revolutionized avatar animation. Traditional methodologies, typically reliant on single modality inputs like text or audio, employ modality-specific model frameworks, posing challenges for unified model deployment and application. To address this, we propose Everything2Motion, a unified model framework. Everything2Motion consists of three key modules. The Input-Output Modality Modulation module tailors structures for specific multimodal inputs, eliminating the need for modality-specific frameworks. The Query-aware Autoencoder, based on the transformer encoder-decoder architecture, enables efficient latent motion generation. Lastly, the Prior Motion Distillation Decoder, a pretrained module, enhances the final skeleton sequence's naturalness and fluidity. Comprehensive experiments on several public datasets demonstrate the effectiveness of Everything2Motion, highlighting its potential for practical applications and setting a new benchmark in human motion synthesis.

Fast Inter-frame Motion Prediction for Compressed Dynamic Point Cloud Attribute Enhancement

Recent years have witnessed the success of deep learning methods in quality enhancement of compressed point cloud. However, existing methods focus on geometry and attribute enhancement of single-frame point cloud. This paper proposes a novel compressed quality enhancement method for dynamic point cloud (DAE-MP). Specifically, we propose a fast inter-frame motion prediction module (IFMP) to explicitly estimate motion displacement and achieve inter-frame feature alignment. To maintain motion continuity between consecutive frames, we propose a motion consistency loss for supervised learning. Furthermore, a frequency component separation and fusion module is designed to extract rich frequency features adaptively. To the best of our knowledge, the proposed method is the first deep learning-based work to enhance the quality for compressed dynamic point cloud. Experimental results show that the proposed method can greatly improve the quality of compressed dynamic point cloud and provide a fast and efficient motion prediction plug-in for large-scale point cloud. For dynamic point cloud attribute with severely compressed artifact, our proposed DAE-MP method achieves up to 0.52dB (PSNR) performance gain. Moreover, the proposed IFMP module has a certain real-time processing ability for calculating the motion offset between dynamic point cloud frame.

CCTR: Calibrating Trajectory Prediction for Uncertainty-Aware Motion Planning in Autonomous Driving

Autonomous driving systems rely on precise trajectory prediction for safe and efficient motion planning. Despite considerable efforts to enhance prediction accuracy, inherent uncertainties persist due to data noise and incomplete observations. Many strategies entail formalizing prediction outcomes into distributions and utilizing variance to represent uncertainty. However, our experimental investigation reveals that existing trajectory prediction models yield unreliable uncertainty estimates, necessitating additional customized calibration processes. On the other hand, directly applying current calibration techniques to prediction outputs may yield sub-optimal results due to using a universal scaler for all predictions and neglecting informative data cues. In this paper, we propose Customized Calibration Temperature with Regularizer (CCTR), a generic framework that calibrates the output distribution. Specifically, CCTR 1) employs a calibration-based regularizer to align output variance with the discrepancy between prediction and ground truth and 2) generates a tailor-made temperature scaler for each prediction using a post-processing network guided by context and historical information. Extensive evaluation involving multiple prediction and planning methods demonstrates the superiority of CCTR over existing calibration algorithms and uncertainty-aware methods, with significant improvements of 11%-22% in calibration quality and 17%-46% in motion planning.

Research on resistance detection robot for UHV tension insulator string

Insulator inspection robots can realize automatic and rapid inspection of insulators of ultra-high voltage transmission lines, which is an important guarantee equipment for the continuous safe operation of the national power grid. Aiming at the needs of ultra-high voltage insulator string inspection, an insulator robot is designed to realize efficient and stable insulator string motion and insulator detection, and the main work includes proposing a new insulator string motion robot configuration and realizing its string motion and inspection functions in the form of a physical prototype. It has been proved that the robot has a large motion load and strong motion performance, and can be adapted to the complex working conditions consisting of a variety of insulators within a certain size range.

Mixed-Transducer Micro-Origami for Efficient Motion and Decoupled Sensing.

This work introduces a mixed-transducer micro-origami to achieve efficient vibration, controllable motion, and decoupled sensing. Existing micro-origami systems tend to have only one type of transducer (actuator/sensor), which limits their versatility and functionality because any given transducer system has a narrow range of advantageous working conditions. However, it is possible to harness the benefit of different micro-transducer systems to enhance the performance of functional micro-origami. More specifically, this work introduces a micro-origami system that can integrate the advantages of three transducer systems: strained morph (SM) systems, polymer based electro-thermal (ET) systems, and thin-film lead zirconate titanate (PZT) systems. A versatile photolithography fabrication process is introduced to build this mixed-transducer micro-origami system, and their performance is investigated through experiments and simulation models. This work shows that mixed-transducer micro-origami can achieve power efficient vibration with high frequency, large vibration ranges, and little degradation; can produce decoupled folding motion with good controllability; and can accomplish simultaneous sensing and actuation to detect and interact with external environments and small-scale samples. The superior performance of mixed-transducer micro-origami systems makes them promising tools for micro-manipulation, micro-assembly, biomedical probes, self-sensing metamaterials, and more.