Object Manipulation Research Articles

Reinforcement Learning in Real Life Applications

Reinforcement Learning is a crucial subset of machine learning that enables agents to learn decision-making through interaction with their environments, guided by feedback like rewards or penalties. This paper delves into Reinforcement Learning's applications across diverse sectors such as robotics, finance, healthcare, and gaming. In robotics, Reinforcement Learning facilitates tasks like object manipulation and environmental adaptation. In finance, it aids in portfolio management and trading strategy development, adapting to market dynamics. In healthcare, Reinforcement Learning assists in generating personalized treatment plans and analyzing medical images. Meanwhile, the gaming industry benefits from Reinforcement Learning -driven intelligent agents capable of challenging human players. Throughout, we explore Reinforcement Learning's fundamental principles, core components, and its transformative potential across these real-world applications. Keywords—Reinforcement Learning, Decision-Making, Adaptive Agents.

The ECOLANG Multimodal Corpus of adult-child and adult-adult Language

Communication comprises a wealth of multimodal signals (e.g., gestures, eye gaze, intonation) in addition to speech and there is a growing interest in the study of multimodal language by psychologists, linguists, neuroscientists and computer scientists. The ECOLANG corpus provides audiovisual recordings and ELAN annotations of multimodal behaviours (speech transcription, gesture, object manipulation, and eye gaze) by British and American English-speaking adults engaged in semi-naturalistic conversation with their child (N = 38, children 3-4 years old, face-blurred) or a familiar adult (N = 31). Speakers were asked to talk about objects to their interlocutors. We further manipulated whether the objects were familiar or novel to the interlocutor and whether the objects could be seen and manipulated (present or absent) during the conversation. These conditions reflect common interaction scenarios in real-world communication. Thus, ECOLANG provides ecologically-valid data about the distribution and co-occurrence of multimodal signals across these conditions for cognitive scientists and neuroscientists interested in addressing questions concerning real-world language acquisition, production and comprehension, and for computer scientists to develop multimodal language models and more human-like artificial agents.

Technologies for enhancing tactile perception in prosthetic devices

Tactile perception is a vital sensory function, and its role has been widely researched in the development of sensor technologies. The role of tactile feedback in augmenting the functional attributes of prosthetic devices is well-documented, as it facilitates a more seamless and natural engagement between the user and the surrounding environment. This paper explores advancements in tactile sensor technologies used to enhance sensory feedback in prosthetics, focusing on piezoresistive, piezoelectric, and capacitive sensors. The integration of these sensors allows for precise control, improving object manipulation and overall user experience. By reviewing recent innovations such as multimodal sensors, artificial skin technologies, and nerve interfacing systems, this research highlights how these advancements have contributed to enhanced motor control and real-time feedback mechanisms in prosthetics. Despite significant progress, challenges such as high costs and limited accessibility remain. However, potentially leading to the widespread adoption of more effective and equitable prosthetic solutions.

Reprogrammable Flexible Piezoelectric Actuator Arrays with a High Degree of Freedom for Shape Morphing and Locomotion.

The high degree of freedom (DoF) shape morphing widely exists in biology for mimicry, camouflage, and locomotion. Currently, a lot of bionic soft/flexible actuators and robots with shape-morphing functions have been developed to realize conformity, grasp, and movement. Among these solutions, two-dimensional responsive materials and structures that can shape morph into different three-dimensional configurations are valuable for creating reversible high DoF shape morphing. However, most existing methods are predetermined through the fabrication process and cannot reprogram their shape, facing limitations on multifunction. Besides, the achievable geometries are very limited due to the device's low integrated level of actuator elements. Here, we develop a polyvinylidene fluoride flexible piezoelectric actuator array based on a row/column addressing (RCA) scheme for reprogrammable high DoF shape morphing and locomotion. The specially designed row/column electrodes form a 6 × 6 array, which contains 36 actuator elements. By developing a high-voltage RCA control system, we can individually control all the elements in the array, leading to a highly reprogrammable array with various sophisticated high DoF shape morphing. We also demonstrate that the array is capable of propelling a robotic fish with various locomotions. This research provides a new method and approach for biomimetic robotics with better mimicry, aero/hydrodynamic efficiency, and maneuverability, as well as haptic display and object manipulation.

The disencapsulated mind: A premotor theory of human imagination.

Our premodern ancestors had perceptual, motoric, and cognitive functional domains that were modularly encapsulated. Some of these came to interact through a new type of cross-modular binding in our species. This allowed previously domain-dedicated, encapsulated motoric and sensory operators to operate on operands for which they had not evolved. Such operators could at times operate nonvolitionally, while at other times they could be governed volitionally. In particular, motoric operations that derive from the same circuits that compute hand motions for object manipulation could now be retooled for virtual manipulation in a mental workspace in the absence of any physical hand or other effector movements. I hypothesize that the creativity of human imagination and mental models is rooted in premotor simulation of sequential manipulations of objects and symbols in the mental workspace, in analogy with the premotor theory of attention, which argues that attention evolved from "internalized" eye movement circuitry. Overall, operator "disencapsulation" led to a bifurcation of consciousness in humans: a concrete form centered on perception of the body in the physical world and an abstract form focused on explanatory mental models. One of the consequences of these new abilities was the advent of psychotic disorders that do not exist in species possessed solely of the concrete type of consciousness. (PsycInfo Database Record (c) 2025 APA, all rights reserved).

Thermally responsive spatially programmable soft actuators with multiple response states enabled by Grayscale UV light processing.

Soft actuators hold great promise for applications in biomimetic robots, artificial muscles, and drug delivery systems due to their adaptability in diverse environments. A critical aspect of designing thermally responsive soft actuators is to achieve spatially programmable actuation under a global thermal stimulus. Different local actuation behaviors can be encoded in one actuator to enable complex morphing structures for different tasks. However, it is challenging to achieve programmability beyond one or binary states. This work introduces a new grayscale ultraviolet (UV) light processing method to fabricate soft actuators with spatially tunable Young's modulus, enabling multiple programmable states in one actuator. Together with a liquid crystal elastomer actuation layer and a photothermal heating layer, the LCE programming layer with spatially programmable moduli allows different regions of the soft actuator to bend to controllable extents under a global thermal stimulus. Various shape morphing patterns can be encoded using UV photomasks with spatially controlled grayscales. Additionally, caterpillar-inspired robots capable of bi-directional crawling and octopus-arm-inspired structures for object manipulation are demonstrated. This work represents advancements in the programmability of thermally responsive soft actuators, laying the foundation for their applications in advanced soft robotic systems.

3D-printed acoustic metasurface with encapsulated micro-air-bubbles for frequency-selective manipulation.

Acoustic waves provide an effective method for object manipulation in microfluidics, often requiring high-frequency ultrasound in the megahertz range when directly handling microsized objects, which can be costly. Micro-air-bubbles in water offer a solution toward low-cost technologies using low-frequency acoustic waves. Owing to their high compressibility and low elastic modulus, these bubbles can exhibit significant expansion and contraction in response to even kilohertz acoustic waves, leading to resonances with frequencies determined and tuned by air-bubble size. The resonances amplify vibrational amplitude and generate localized turbulence, enabling selective, non-invasive, and high-precision manipulation of microsized objects. However, conventional bubble formation relies on the shear force of the liquid flow and bubble surface tension, facing challenges of instability and random vibration that can impair manipulation precision and performance. To address these issues, we propose a coupled vibration structure with 3D-printed circular microsized air holes encapsulated by a PDMS film. These airholes act as artificial micro-air-bubbles, with their expansion and contraction stabilized by acoustic hard boundaries. The PDMS film further regulates vibration modes through the interaction between air movement and the film's vibration, eliminating randomness. Compared to conventional air-bubbles held by surface tension, these artificial air-bubbles are mechanically stable, allowing for enhanced gas volume changes and stronger forces for object manipulation. We experimentally confirm the stable vibration modes and their frequency-dependent behavior using laser Doppler vibrometry. Precise aggregation, rotation, and separation of micro-objects are demonstrated by adjusting the film's vibration mode. Furthermore, we propose a metasurface design featuring a multi-size microbubble array for frequency-selective manipulation, enabling flexible control of sample trajectory by changing the exciting frequency of an embedded piezoelectric transducer. Our low-frequency acoustic metasurface device offers a versatile, cost-effective solution for drug screening and automated sample handling.

Surgical Reconstruction of Unstable, Hypoplastic Fingertips With Allograft and BMP-2 Augmentation: Surgical Technique and Case Series

Objective: Unstable hypoplastic digits can lead to poor function due to instability with pinch and manipulation of objects. The primary goals of surgical reconstruction in these patients are to create 2 stable digits for pinch and improve finger opposition, pinch strength, and digit mobility. In this paper, we present a surgical technique and case series of pediatric patients who underwent surgical reconstruction of unstable/telescoping hypoplastic fingertips using bony allograft augmented with BMP-2. Materials and Methods: A surgical technique for reconstruction of unstable, hypoplastic fingertips was performed using a bony allograft augmented with BMP-2. The series included pediatric patients with hypoplastic digits with instability affecting grip-pinch strength and hand prehension. Results: Ten patients between the ages of 2 and 4 years were included, with 8 thumbs and 2 index fingers being reconstructed. All 10 patients developed clinically stable digits with parent-reported improvements in pinch-grip function including using a switch, opening a bag, and putting on clothes. Postoperative radiographic outcomes did not show any cases of bony overgrowth; 2 patients had evidence of bony resorption though this did not correspond to a significant change in finger length postoperatively. Conclusion: Hypoplastic fingertip reconstruction using bony allograft augmented with BMP-2 is a surgical option for the stabilization of unstable hypoplastic fingertips in congenital hand anomalies. The use of allograft augmented with BMP-2 eliminates donor site morbidity seen with autograft reconstructive options and may limit the concerns with healing/incorporation traditionally reported with allograft use in the literature.

Enhancing the rocker-bogie Mechanism with automation: A study on sensor integration and Mechanical arm functionality

The rocker-bogie mechanism is a well-known design in robotic mobility, particularly effective for rovers traversing rugged terrains. This research improves upon the traditional rocker-bogie system by integrating ultrasonic sensors, a GPS module, and a mechanical arm to enhance autonomy and versatility. The system is controlled by an Arduino Uno and powered by six 12V DC motors using an L298 2A motor circuit board, ensuring precise and reliable movement in challenging environments. Ultrasonic sensors provide effective obstacle detection by triggering a turn when objects are within 50 cm. This is a simpler alternative to complex AI-based path planning. Additionally, the integration of GPS enhances navigation capabilities. The mechanical arm allows for interaction with the environment, enabling tasks such as object manipulation and repairs. The project aims to enhance autonomous navigation and improve sensor-based obstacle avoidance, motivated by Experimental methods including testing the rover’s obstacle detection capabilities using ultrasonic sensors in controlled environments with varying obstacle distances. The rover’s navigation was evaluated across different terrains, including flat surfaces and uneven terrains to assess their mobility and stability. Optionally, GPS accuracy was tested by guiding the rover to predefined waypoints, while power efficiency was monitored during continuous operation to measure battery life and overall system performance. Results showed that. This work improves robotic autonomy in harsh conditions and uses mechanical parts to reduce the margin of error in fields such as agriculture, disaster response robots, Autonomous Mining Vehicles, Pipeline and Infrastructure Inspection, Volcanoes, Deep Caves, and Extreme Terrains.

Visual Functions in Patients With Leber Hereditary Optic Neuropathy (LHON)

Background: Most of the data on visual functions in Leber hereditary optic neuropathy (LHON) is based on patient questionnaires. Our study assessed the impact of LHON on visual function by testing facial recognition and execution of purposeful actions. Methods: Twelve participants with LHON with central scotoma ranging from 5° to 20° and 12 unaffected age-matched controls were involved in our study. In the face recognition test, participants were asked to recognize the sex and the facial expression of photographs of faces increasing in size to simulate approaching faces. In the purposeful action test, they were asked to manipulate real objects while their eye movements were recorded. Results: Although most patients were able to recognize the correct sex of a face at a size corresponding to a 1-m viewing distance, recognition of facial expressions was severely impaired. Patients were slower than control subjects in executing purposeful tasks. A dynamic strategy to sample information needed for the execution of a task was documented in a longer scanpath and in higher frequency of saccades and fixation eye movements in patients than in control subjects. Conclusions: Face perception is strongly impaired in patients with LHON. In addition, although the selection and manipulation of real objects to execute a task are slowed, they can be performed efficiently using peripheral vision.

Neuromechanical Circuits of the Spinal Motor Apparatus.

The evolution of mechanisms for terrestrial locomotion has resulted in multi-segmented limbs that allow navigation on irregular terrains, changing of direction, manipulation of external objects, and control over the mechanical properties of limbs important for interaction with the environment, with corresponding changes in neural pathways in the spinal cord. This article is focused on the organization of these pathways, their interactions with the musculoskeletal system, and the integration of these neuromechanical circuits with supraspinal mechanisms to control limb impedance. It is argued that neural pathways from muscle spindles and Golgi tendon organs form a distributive impedance controller in the spinal cord that controls limb impedance and coordination during responses to external disturbances. These pathways include both monosynaptic and polysynaptic components. Autogenic, monosynaptic pathways serve to control the spring-like properties of muscles preserving the nonlinear relationship between stiffness and force. Intermuscular monosynaptic pathways compensate for inertial disparities between the inertial properties of limb segments and help to control inertial coupling between joints and axes of rotation. Reciprocal inhibition controls joint stiffness in conjunction with feedforward cocontraction commands. Excitatory force feedback becomes operational during locomotion and increases muscular stiffness to accommodate the higher inertial loads. Inhibitory force feedback is widely distributed among muscles. It is integrated with excitatory pathways from muscle spindles and Golgi tendon organs to determine limb stiffness and interjoint coordination during interactions with the environment. The intermuscular distribution of force feedback is variable and serves to modulate limb stiffness to meet the physical demands of different motor tasks. © 2024 American Physiological Society. Compr Physiol 14:5789-5838, 2024.

Game-based physical education learning to improve basic manipulative movement skills in primary school children

Physical education plays an important role in the development of children's motor skills, especially at primary school age. Basic manipulative movement exercises that focus on object manipulation, ball games and other games can accelerate the development of hand-eye coordination and gross motor skills. This study aims to develop and implement an effective game-based physical education learning model to improve the basic manipulative movement skills of primary school children. The type of research used is pre-experimental research, one group pre-test post-test design. The study population consisted of students aged 9-10 years of grade 4 in Palembang City, with a sample of grade 4A total 25 students who participated in game-based learning for 8 sessions. The results of this study indicate that the use of the game model in learning has a significant effect on the improvement of learners' manipulative movement skills. Educators and coaches are advised to use the game model as the main tool in children's motor development, with adaptations based on learners' initial abilities.

TacFR-Gripper: A Reconfigurable Fin-Ray-Based Gripper with Tactile Skin for In-Hand Manipulation

This paper introduces the TacFR-Gripper, a novel reconfigurable soft robotic gripper inspired by the Fin-Ray effect and equipped with tactile skin. The gripper incorporates a four-bar mechanism for accurate finger bending and a reconfigurable design to change the relative positions between the fingers and palm, enabling precise and adaptable object grasping. This 5-Degree-of-Freedom (DOF) soft gripper can facilitate dexterous manipulation of objects with diverse shapes and stiffness and is beneficial to the safe and efficient grasping of delicate objects. An array of Force Sensitive Resistor (FSR) sensors is embedded within each robotic fingertip to serve as the tactile skin, enabling the robot to perceive contact information during manipulation. Moreover, we implemented a threshold-based tactile perception approach to enable reliable grasping without accidental slip or excessive force. To verify the effectiveness of the TacFR-Gripper, we provide detailed workspace analysis to evaluate its grasping performance and conducted three experiments, including (i) assessing the grasp success rate across various everyday objects through different finger configurations, (ii) verifying the effectiveness of tactile skin with different control strategies in grasping, and (iii) evaluating the in-hand manipulation capabilities through object pose control. The experimental results indicate that the TacFR-Gripper can grasp a wide range of complex-shaped objects with a high success rate and deliver dexterous in-hand manipulation. Additionally, the integration of tactile skin is demonstrated to enhance grasp stability by incorporating tactile feedback during manipulations.

Advancing Industrial Object Detection Through Domain Adaptation: A Solution for Industry 5.0

Domain adaptation (DA) is essential for developing robust machine learning models capable of operating across different domains with minimal retraining. This study explores the application of domain adaptation techniques to 3D datasets for industrial object detection, with a focus on short-range and long-range scenarios. While 3D data provide superior spatial information for detecting industrial parts, challenges arise due to domain shifts between training data (often clean or synthetic) and real-world conditions (noisy and occluded environments). Using the MVTec ITODD dataset, we propose a multi-level adaptation approach that leverages local and global feature alignment through PointNet-based architectures. We address sensor variability by aligning data from high-precision, long-range sensors with noisier short-range alternatives. Our results demonstrate an 85% accuracy with a minimal 0.02% performance drop, highlighting the resilience of the proposed methods. This work contributes to the emerging needs of Industry 5.0 by ensuring adaptable and scalable automation in manufacturing processes, empowering robotic systems to perform precise, reliable object detection and manipulation under challenging, real-world conditions, and supporting seamless human–robot collaboration.

Magnetic kirigami dome metasheet with high deformability and stiffness for adaptive dynamic shape-shifting and multimodal manipulation.

Soft shape-shifting materials offer enhanced adaptability in shape-governed properties and functionalities. However, once morphed, they struggle to reprogram their shapes and simultaneously bear loads for fulfilling multifunctionalities. Here, we report a dynamic spatiotemporal shape-shifting kirigami dome metasheet with high deformability and stiffness that responds rapidly to dynamically changing magnetic fields. The magnetic kirigami dome exhibits over twice higher doming height and 1.5 times larger bending curvature, as well as sevenfold enhanced structural stiffness compared to its continuous counterpart without cuts. The metasheet achieves omnidirectional doming and multimodal translational and rotational wave-like shape-shifting, quickly responding to changing magnetic fields within 2 milliseconds. Using the dynamic shape-shifting and adaptive interactions with objects, we demonstrate its applications in voxelated dynamic displays and remote magnetic multimodal directional and rotary manipulation of nonmagnetic objects without grasping. It shows high-load transportation ability of over 40 times its own weight, as well as versatility in handling objects of different materials (liquid and solid), sizes, shapes, and weights.

Multifunctional Sensor Array for User Interaction Based on Dielectric Elastomers with Sputtered Metal Electrodes.

The integration of textile-based sensing and actuation elements has become increasingly important across various fields, driven by the growing demand for smart textiles in healthcare, sports, and wearable electronics. This paper presents the development of a small, smart dielectric elastomer (DE)-based sensing array designed for user control input in applications such as human-machine interaction, virtual object manipulation, and robotics. DE-based sensors are ideal for textile integration due to their flexibility, lightweight nature, and ability to seamlessly conform to surfaces without compromising comfort. By embedding these sensors into textiles, continuous user interaction can be achieved, providing a more intuitive and unobtrusive user experience. The design of this DE array draws inspiration from a flexible and wearable version of a touchpad, which can be incorporated into clothing or accessories. Integrated advanced machine learning algorithms enhance the sensing system by improving resolution and enabling pattern recognition, reaching a prediction performance of at least 80. Additionally, the array's electrodes are fabricated using a novel sputtering technique for low resistance as well as high geometric flexibility and size reducibility. A new crimping method is also introduced to ensure a reliable connection between the sensing array and the custom electronics. The advantages of the presented design, data evaluation, and manufacturing process comprise a reduced structure size, the flexible adaptability of the system to the respective application, reliable pattern recognition, reduced sensor and line resistance, the adaptability of mechanical force sensitivity, and the integration of electronics. This research highlights the potential for innovative, highly integrated textile-based sensors in various practical applications.

Understanding user experience, task performance, and task interdependence in symmetric and asymmetric VR collaborations

Asymmetric collaboration is an important topic for the research of multiuser collaborative systems. Previous works have shown that by providing different abilities, devices or content to different users, users can take advantage of the unique features of each side and collaborate effectively with each other. However, there is limited work comparing the differences between asymmetric and symmetric Virtual Reality (VR) collaboration systems. How task complexity may affect symmetric and asymmetric VR collaboration is also unclear. In this paper, we present a comparative study that investigated how user experiences and task performance vary in symmetric and asymmetric VR collaboration. In addition, we also explored how task interdependence correlates with user experience and task performance. Participants were asked to collaboratively perform 3D object selection and manipulation tasks in pairs. A within-subjects study was conducted, where participants used PC and PC, VR and VR, and PC and VR, respectively in three conditions. Our results revealed that the asymmetric collaboration using both PC and VR showed the best results in closeness of relationship, social presence and task performance; the PC symmetric collaborative system showed the worst user experiences and task performance. Both user experience and task performance showed a positive correlation with task interdependence. We discussed the effects of the collaborativ mode and device on the user experience and task performance, and the implications for future symmetric and asymmetric VR collaboration systems.Graphical abstract

Interfacial instability in a viscoelastic microfluidic coflow system

Understanding interfacial instability in a coflow system has relevance in the effective manipulation of small objects in microfluidic applications. We experimentally elucidate interfacial instability in stratified coflow systems of Newtonian and viscoelastic fluid streams in microfluidic confinements. By performing a linear stability analysis, we derive equations that describe the complex wave speed and the dispersion relationship between wavenumber and angular frequency, thus categorizing the behaviour of the systems into two main regimes: stable (with a flat interface) and unstable (with either a wavy interface or droplet formation). We characterize the regimes in terms of the capillary numbers of the phases in a comprehensive regime plot. We decipher the dependence of interfacial instability on fluidic parameters by decoupling the physics into viscous and elastic components. Remarkably, our findings reveal that elastic stratification can both stabilize and destabilize the flow, depending on the fluid and flow parameters. We also examine droplet formation, which is important for microfluidic applications. Our findings suggest that adjusting the viscous and elastic properties of the fluids can control the transition between wavy and droplet-forming unstable regimes. Our investigation uncovers the physics behind the instability involved in interfacial flows of Newtonian and viscoelastic fluids in general, and the unexplored behaviour of interfacial waves in stratified liquid systems. The present study can lead to a better understanding of the manipulation of small objects and production of droplets in microfluidic coflow systems.

High Strength and Dynamically Tunable Adhesion Enabled by Composite Micropillar Arrays Fabricated via Solvent‐Assisted Molding

AbstractThe ability to control adhesion on demand is important for a broad range of applications, including the gripping and manipulation of objects in robotics and manufacturing, and the temporary attachment of wearable devices. Despite recent advances in tunable adhesive materials, most existing solutions have modest adhesion strength and are limited by a compromise between the maximum and minimum adhesion, where increased strength prevents the release of lighter objects. To overcome these challenges, thermally responsive polymers, which can exhibit both high stiffness and a large reduction in stiffness via heating, have the potential to enable strong and tunable adhesion. Here, a microstructured composite adhesive with high strength (>2 MPa) and dynamically tunable adhesion (16×) is realized using a solvent‐assisted molding technique. The adhesive consists of an array of composite micropillars whose small scale and material composition enable strong and tunable adhesion. While thermally actuated systems often have slow response times, it is shown that miniaturization allows response times to be reduced to <1s for heating and <10s for cooling. These strong, fast, and dynamically tunable adhesives offer advantages over existing solutions and can be manufactured for practical adoption through the scalable solvent‐assisted molding technique.

TDSF: Two-phase tamper detection in semi-fragile watermarking using two-level integer wavelet transform

Image watermarking is one of techniques that can be used to protect and recover from the altered images. Tamper detection in semi-fragile still does not achieve high accuracy for tamper localization, especially in malicious attacks. This study proposes two-phase tamper detection in semi-fragile image watermarking using two-level Integer Wavelet Transform (IWT). The study proposes two-phases of tamper detection to achieve a high level of accuracy in the tamper localization. The initial phase will check four segments to determine the tampered bit or not. A tampered segment is identified if it contains at least one tampered bit. The second phase will be performed if the first phase has no tampered bit. The second phase checked each segment to determine whether it was tampered with or not. This study also used Normalized Hamming Similarity (NHS) to classify malicious and incidental attacks. The proposed scheme performed two-level integer wavelets transform to obtain the LL, LH, HL, and HH sub-bands. The authentication bits of LL are embedded into the LH and HL sub-bands to generate a watermarked image. The LH and HL are compared using XOR bitwise with authentication bitto localize the tamper detection. The experimental results show that the proposed scheme achieved high quality of the recovered images with an average PSNR score of 44.1864 dB, wPSNR score of 46.2218 dB and SSIM score of 0.9945. The proposed method produced high accuracy of tamper detection of about 98.33 % under object manipulation with the tampering rate of about 12.1643 %.