Donghun Lee

Soft pneumatic grippers are well-suited for grasping irregular objects owing to their inherent compliance and ability to adapt to a wide range of shapes and sizes. However, their ability to quantitatively estimate object size during the grasping process remains limited. To address this limitation, this study proposes a soft pneumatic gripper integrated with a piezoresistive CNT/PDMS composite sensor and investigates the feasibility of object size estimation using only sensor signals. The pressure-sensing characteristics of the CNT/PDMS sensor were evaluated over a pressure range of 0–500 kPa, and the 1 wt% CNT/PDMS sensor exhibited the highest sensitivity of approximately 0.016 kPa⁻¹ in the initial linear pressure region. To this end, the normalized resistance response under applied pneumatic pressure was analyzed independent of external visual information, and a size estimation method was established based on the relationship between initial contact pressure and object diameter. Grasping experiments using spherical objects of varying diameters revealed that the resistance response patterns were clearly distinguishable according to object size, with larger objects exhibiting significant resistance changes at lower applied pressures. These findings demonstrate the feasibility of estimating the size of a grasped object based on the grasp onset pressure derived from the sensor response. The results of this study provide a foundation for future soft robotic systems capable of recognizing contact conditions and object size through sensor-based feedback. Furthermore, these findings may be extended to adaptive manipulation technologies involving real-time pneumatic pressure control.

In industrial environments, providing intuitive spatial information via 3D maps is essential for maximizing the efficiency of teleoperation. However, existing SLAM algorithms generating 3D maps predominantly focus on improving robot localization accuracy, often neglecting the optimization of viewability required for human operators to clearly perceive object depth and structure in virtual environments. To address this, this study proposes a methodology to optimize the viewability of RTAB-Map-based 3D maps using the Taguchi method, aiming to enhance VR teleoperation efficiency and reduce cognitive workload. We identified eight key parameters that critically affect visual quality and utilized an L18 orthogonal array to derive an optimal combination that controls point cloud density and noise levels. Experimental results from a target object picking task demonstrated that the optimized 3D map reduced task completion time by approximately 9 s compared to the RGB image condition, achieving efficiency levels approaching those of the physical-world baseline. Furthermore, evaluations using NASA-TLX confirmed that intuitive visual feedback minimized situational awareness errors and substantially alleviated cognitive workload. This study suggests a new direction for constructing high-efficiency teleoperation interfaces from a Human–Robot Interaction perspective by expanding SLAM optimization criteria from geometric precision to user-centric visual quality.

This study investigates how control modalities and recognition accuracy influence construction workers’ trust and acceptance of collaborative robots. Sixty participants evaluated voice and gesture control under varying levels of recognition accuracy while performing tiling together with collaborative robots. Experimental results indicated that recognition accuracy significantly affected perceived enjoyment (PE, p = 0.010), ease of use (PEOU, p = 0.030), and intention to use (ITU, p = 0.022), but not trust, usefulness (PU), or attitude (ATT). Furthermore, the interaction between control modality and accuracy shaped most acceptance factors (PE, p = 0.049; PEOU, p = 0.006; PU, p = 0.006; ATT, p = 0.003, and ITU, p < 0.001) except trust. In general, high recognition accuracy enhanced user experience and adoption intentions. Voice interfaces were favored when recognition accuracy was high, whereas gesture interfaces were more acceptable under low-accuracy conditions. These findings highlight the importance of designing high-accuracy, task-appropriate interfaces to support technology acceptance in construction. The preference for voice interfaces under accurate conditions aligns with the noisy, fast-paced nature of construction sites, where efficiency is paramount. By contrast, gesture interfaces offer resilience when recognition errors occur. The study provides practical guidance for robot developers, interface designers, and construction managers, emphasizing that carefully matching interaction modalities and accuracy levels to on-site demands can improve acceptance and long-term adoption in this traditionally conservative sector.

Teleoperation-based order picking in logistics warehouse environments has been advancing steadily. However, the accuracy of such operations varies depending on the type of human–robot interface (HRI) employed. Immersive HRI, which uses a head-mounted display (HMD) and controllers, can significantly reduce task accuracy due to the limited field of view in virtual environments. To address this limitation, this study proposes a semi-autonomous telemanipulation order-picking control method based on operator intent estimation using intersection points between the end-effector and the target logistics plane in box-stacking storage environments. The proposed method consists of two stages. The first stage involves operator intent estimation, which approximates the target logistics plane using objects identified through camera vision and calculates the intersection points by intersecting the end-effector heading vector with the plane. These points are accumulated and modeled as a Gaussian distribution, with the probability density function (PDF) of each target object treated as its likelihood. Bayesian probability filtering is then applied to estimate target probabilities, and predefined conditions are used to switch control between autonomous and manual controllers. Results show that the proposed operator intent estimation method identified the correct target in 74.6% of the task’s duration. The proposed semi-autonomous control method successfully transferred control to the autonomous controller within 32.2% of the total task duration using a combination of three parameters. This approach inferred operator intent based solely on manipulator motion and reduced the fatigue of the operator. This method demonstrates potential for broad application in teleoperation systems, offering high operational efficiency regardless of operator expertise or training level.

Telemanipulation-based object-side picking with a suction gripper often faces challenges such as occlusion of the target object or the gripper and the need for precise alignment between the suction cup and the object’s surface. These issues can significantly affect task success rates in logistics environments. To address these problems, this study proposes a multi-mode hand gesture-based virtual reality (VR) locomotion method to enable intuitive and precise viewpoint control. The system utilizes a head-mounted display (HMD) camera to capture hand skeleton data, which a multi-layer perceptron (MLP) model processes. The model classifies gestures into three modes: translation, rotation, and fixed, corresponding to fist, pointing, and unknown gestures, respectively. Translation mode moves the viewpoint based on the wrist’s displacement, rotation mode adjusts the viewpoint’s angle based on the wrist’s angular displacement, and fixed mode stabilizes the viewpoint when gestures are ambiguous. A dataset of 4312 frames was used for training and validation, with 666 frames for testing. The MLP model achieved a classification accuracy of 98.4%, with precision, recall, and F1-score exceeding 0.98. These results demonstrate the system’s ability to address the challenges of telemanipulation tasks by enabling accurate gesture recognition and seamless mode transitions.

This study proposes a method for time-efficient order picking based on a structural stability assessment (SSA) when target boxes inside box-stacking storage (BSS) on multi-layer racks are removed. This method performs optimal order picking by generating a path to directly pick the target box without first picking the upper boxes in the BBS, if it is possible to pick the target box directly. The SSA algorithm generates images of the complement structure by removing the target box within BBS and uses them as input data for the CNN model to evaluate the stability of the structure. To create the CNN model, we generated a dataset using CoppeliaSim simulation, considering the size and shape of the overall structure of the BBS, the size and number of each box, and the number of target boxes. The accuracy of the generated CNN model was 95.1% on test data, while it achieved 97% accuracy when using real-world data. This validation process confirmed that the algorithm can be effectively applied to real BBS logistics environments to perform optimal order picking.

This paper presents the design of a Bowden-cable-based exoskeleton suit specifically developed for assisting with passive stretching exercises for patients with frozen shoulders. Passive stretching exercises are essential in the treatment of frozen shoulders, as they require a higher intensity than what patients can achieve through self-stretching alone. Consequently, the assistance of a therapistis necessary. However, current suits designed for this purpose have drawbacks. Some are too bulky, making it difficult for therapists to interact with patients, while others are too compact to adequately support passive stretching exercises. With this in mind, the objective of this paper is to explore the requirements that a suit must meet to effectively assist patients with frozen shoulder during passive stretching exercises. Based on our findings, we propose an exoskeleton suit that is easy to wear, utilizes a Bowden cable for reduced size, and incorporates a ratchet mechanism to support therapists in the most fatiguing movements, such as forward flexion and abduction. Furthermore, we conducted wearability and functional evaluations to validate the fabricated exoskeleton suit. The results confirmed that the proposed suit is comfortable to wear and effectively assists both the wearer and the therapist in performing forward flexion and abduction movements during stretching exercises.

With the evolution of robotic technology, the expansion of operations into challenging environments underscores the growing need for effective teleoperation systems. In such an environment, robots or machines can improve the efficiency and safety of tasks by delivering more detailed and accurate information to workers through virtual reality (VR). Current teleoperation systems have limitations in providing a comprehensive understanding of the work environment. Accordingly, this study proposes a technology that utilizes VR to provide a high level of telepresence to workers and enable intuitive control. To achieve this, we introduce a pregenerated computer-assisted design model for static objects beyond the viewing area of RGB-D cameras and a method to update the point cloud of the target objects, which are dynamic objects, in real-time. By incorporating this information, we created a 3D visual map and delivered it to the operator in real-time through HMD, enabling the operator to clearly recognize the robot’s current location and surroundings. In addition, we introduced hand motion recognition through HMD viewpoints and VR controllers, allowing the operator to intuitively control the robot. These techniques can improve the efficiency and safety of remote work.

Composite-based piezoelectric devices are extensively studied to develop sustainable power supply and selfpowered devices owing to their excellent mechanical durability and output performance. In this study, we design a leadfree piezoelectric nanocomposite utilizing (Ba0.85Ca0.15)(Ti0.9Zr0.1)O3 (BCTZ) nanomaterials for realizing highly flexible energy harvesters. To improve the output performance of the devices, we incorporate porous BCTZ nanowires (NWs) into the nanoparticle (NP)-based piezoelectric nanocomposite. BCTZ NPs and NWs are synthesized through the solidstate reaction and sol-gel-based electrospinning, respectively; subsequently, they are dispersed inside a polyimide matrix. The output performance of the energy harvesters is measured using an optimized measurement system during repetitive mechanical deformation by varying the composition of the NPs and NWs. A nanocomposite-based energy harvester with 4:1 weight ratio generates the maximum open-circuit voltage and short-circuit current of 0.83 V and 0.28 A, respectively. In this study, self-powered devices are constructed with enhanced output performance by using piezoelectric energy harvesting for application in flexible and wearable devices.