Search Results (262)

This paper presents the design and testing of a lightweight, low-cost robotic arm with an extended vertical range. The 9-degree-of-freedom (DOF) system comprises a 6-DOF arm and a 3-DOF gripper. To minimize weight, the six wrist and gripper joints are cable-driven, with all actuators relocated to the shoulder assembly. As a result, the wrist and gripper only weigh 222 g and 113 g, respectively, significantly reducing the inertia on the end effector. The arm utilizes a SCARA-configuration that slides along a tower for extended vertical reach. A key innovation is a closed-section frame that attaches the arm to the tower, in which the bending and torsional loads from the payload can be directly transferred onto the static structure. In contrast to conventional design, this design does not require the shoulder motor to take the bending load directly. Instead, the motor only needs to overcome the rolling friction of the reaction load. Experimental results demonstrate that this approach reduces the required motor torque by a factor of 30. Consequently, the prototype can manipulate a 3 kg payload at a 0.5 m lateral reach while weighing only 4.5 kg, costing USD 1200, and consuming a maximum of 11.1 W of power. Full article

Learning from Demonstration (LfD) enables robots to acquire manipulation skills by observing human actions. However, existing methods often face challenges such as high computational cost, limited generalizability, and a loss of key interaction details. This study presents a compact representation for interaction recognition in LfD that encodes human–object interactions using 2D wrist trajectories and 3D object poses. A lightweight extraction pipeline combines MediaPipe-based wrist tracking with FoundationPose-based 6-DoF object estimation to obtain these trajectories directly from RGB-D video without specialized sensors or heavy preprocessing. Experiments on the GRAB and FPHA datasets show that the representation effectively captures task-relevant interactions, achieving 94.6% accuracy on GRAB and 96.0% on FPHA with well-calibrated probability predictions. Both Bidirectional Long Short-Term Memory (Bi-LSTM) with attention and Transformer architectures deliver consistent performance, confirming robustness and generalizability. The method achieves sub-second inference, a memory footprint under 1 GB, and reliable operation on both GPU and CPU platforms, enabling deployment on edge devices such as NVIDIA Jetson. By bridging pose-based and object-centric paradigms, this approach offers a compact and efficient foundation for scalable robot learning while preserving essential spatiotemporal dynamics. Full article

The six-degree-of-freedom (6-DoF) interaction forces/torque of the tool-end play an important role in the robotic tool manipulation using a gripper, which are usually indirectly measured by a robot wrist force/torque sensor. However, the real-time decoupling of the tool’s inertial force remains a challenge when different tools and grasping postures are involved. This paper presents a universal tool-end interaction forces estimation approach, which is capable of handling diverse grippers and tools. Firstly, to address uncertainties from varying tools and grasping postures, an online-identifiable tool dynamics model was built based on the Newton–Euler approach for the integrated gripper–tool system. Sensor zero-drift caused by factors such as the tool weight and prolonged operation is incorporated into the dynamic model and identified online in real time, enabling a coarse estimation of the interaction forces. Secondly, a spiking neural network (SNN) is specially employed to compensate for uncertainties caused by the wrist sensor creep effect, since its temporal processing and event-driven characteristics match the time-varying creep effects introduced by tool changes. The proposed method is experimentally validated on a robotic arm with a gripper, and the results show that the root mean square errors of the estimated tool-end interaction forces are below 0.5 N with $x$, $y$, and $z$ axes and 0.03 Nm with ${\tau }_x$, ${\tau }_y$, and ${\tau }_z$ axes, which has a comparable precision with the in situ measurement of the interaction forces at the tool-end. The proposed method is further applied to robotic scraper manipulation with impedance control, achieving the interaction forces feedback during compliant operation precisely and rapidly. Full article

This paper outlines the inception, conceptualization and primary morphological selection of a robotic system that employs raw lunar regolith for constructing protective berms and shelters on the Moon’s surface. The lunar regolith is considered the most readily available material for in situ resource utilization on the Moon. The lunar environment is characterized, and the operational task is defined, informing the development of high-level system requirements and a functional analysis through the glass-box method. The key morphological areas are identified, and candidate concepts are evaluated using the Analytic Hierarchy Process (AHP). The evaluation process employs a new approach to aggregating expert data through the ZM_II method to establish priorities of the design criteria, which eliminates the need for pairwise comparisons in data collection. Each criterion is associated with a specific and quantifiable metric, which is then used to evaluate the morphologies during the AHP. The selected morphologies are determined as: a vibrating hopper for intake (normalized decision value of 27.5% out of 5 candidate solutions), a roller system for container deployment and filling (26.2% out of 7), a magnetic RCU interface (22.6% out of 7), and a 4-DoF manipulator to place the RCUs in the environment (23.6% out of 5). The final morphology is selected by combining the decision values across the primary morphological areas into a unified decision metric. This is followed by the preliminary selection of the system’s surrounding architecture. The design conceptualization is performed within a real-life operational scenario, namely, to create a blast berm for the landing pad using the lunar regolith provided by an existing excavator. The next phase of the work will include the system’s detailed design, as well as investigations on the requirements for a variety of construction tasks on the lunar surface. Full article

This paper presents a hybrid reinforcement learning framework for trajectory tracking control of a 5-degree-of-freedom (DOF) Mitsubishi RV-2AJ robotic arm by integrating model-free deep reinforcement learning (DRL) algorithms with classical control strategies. A novel hybrid PID + TD3 agent is proposed, combining a Proportional–Integral–Derivative (PID) controller with the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, and is compared against standalone TD3 and PID controllers. In this architecture, the PID controller provides baseline stability and deterministic disturbance rejection, while the TD3 agent learns residual corrections to enhance tracking accuracy, robustness, and control smoothness. The robotic system is modeled in MATLAB/Simulink with Simscape Multibody, and the agents are trained using a reward function inspired by artificial potential fields, promoting energy-efficient and precise motion. Extensive simulations are performed under internal disturbances (e.g., joint friction variations, payload changes) and external disturbances (e.g., unexpected forces, environmental interactions). Results demonstrate that the hybrid PID + TD3 approach outperforms both standalone TD3 and PID controllers in convergence speed, tracking precision, and disturbance rejection. This study highlights the effectiveness of combining reinforcement learning with classical control for intelligent, robust, and resilient robotic manipulation in uncertain environments. Full article

Tableware objects such as plates, bowls, and cups are usually textureless, uniform in color, and vary widely in shape, making it difficult to apply conventional pose estimation methods that rely on texture cues or object-specific CAD models. These limitations present a significant obstacle to robotic manipulation in restaurant environments, where reliable six-degree-of-freedom (6-DoF) pose estimation is essential for autonomous grasping and collection. To address this problem, we propose a model-free and texture-free 6-DoF pose estimation framework based on a transformer encoder architecture. This method uses only geometry-based features extracted from depth images, including surface vertices and rim normals, which provide strong structural priors. The pipeline begins with object detection and segmentation using a pretrained video foundation model, followed by the generation of uniformly partitioned grids from depth data. For each grid cell, centroid positions, and surface normals are computed and processed by a transformer-based model that jointly predicts object rotation and translation. Experiments with ten types of tableware demonstrate that the method achieves an average rotational error of 3.53 degrees and a translational error of 13.56 mm. Real-world deployment on a mobile robot platform with a manipulator further validated its ability to autonomously recognize and collect tableware, highlighting the practicality of the proposed geometry-driven approach for service robotics. Full article

Crack monitoring in concrete structures is essential to maintaining structural integrity. Therefore, this paper proposes a mobile ground robot equipped with a 2-DoF manipulator and stereo vision sensors for autonomous crack monitoring and mapping. To facilitate crack detection over large areas, a 2-DoF motorized manipulator providing linear and rotational motions, with a stereo vision sensor mounted on the end effector, was deployed. In combination with a manual rotation plate, this configuration enhances accessibility and expands the field of view for crack monitoring. Another stereo vision sensor, mounted at the front of the robot, was used to acquire point cloud data of the surrounding environment, enabling tasks such as SLAM (simultaneous localization and mapping), path planning and following, and obstacle avoidance. Cracks are detected and segmented using the deep learning algorithms YOLO (You Only Look Once) v6-s and SFNet (Semantic Flow Network), respectively. To enhance the performance of crack segmentation, synthetic image generation and preprocessing techniques, including cropping and scaling, were applied. The dimensions of cracks are calculated using point clouds filtered with the median absolute deviation method. To validate the performance of the proposed crack-monitoring and mapping method with the robot system, indoor experimental tests were performed. The experimental results confirmed that, in cases of divided imaging, the crack propagation direction was predicted, enabling robotic manipulation and division-point calculation. Subsequently, total crack length and width were calculated by combining reconstructed 3D point clouds from multiple frames, with a maximum relative error of 1%. Full article

In this study, a vision-based remote and synchronized control scheme is proposed for the double six-DOF robotic manipulators. Using an Intel RealSense D435 depth camera and MediaPipe skeletal image feature technique, the operator’s 3D hand pose is captured and mapped to the robot’s workspace via coordinate transformation. Inverse kinematics is then applied to compute the necessary joint angles for synchronized motion control. Implemented on double robotic manipulators with the MoveIt framework, the system successfully achieves a collaborative teleoperation control task to transfer an object from a robotic manipulator to another one. Further, moving average filtering techniques are used to enhance trajectory smoothness and stability. The framework demonstrates the feasibility and effectiveness of non-contact, vision-guided multi-robot control for applications in teleoperation, smart manufacturing, and education. Full article

Autonomous robotic manipulators in industrial environments face significant challenges, including time-varying payloads, multi-source disturbances, and real-time computational constraints. Traditional model predictive control frameworks degrade by over 40% under model uncertainties, while conventional adaptive techniques exhibit convergence times incompatible with industrial cycles. This work presents a hybrid adaptive model predictive control framework integrating edge artificial intelligence with dual-stage parameter estimation for 6-DoF industrial manipulators. The approach combines recursive least squares with a resource-optimized neural network (three layers, 32 neurons, <500 KB memory) designed for industrial edge deployment. The system employs innovation-based adaptive forgetting factors, providing exponential convergence with mathematically proven Lyapunov-based stability guarantees. Simulation validation using the Fanuc CR-7iA/L manipulator demonstrates superior performance across demanding scenarios, including precision laser cutting and obstacle avoidance. Results show 52% trajectory tracking RMSE reduction (0.022 m to 0.012 m) under 20% payload variations compared to standard MPC, while achieving sub-5 ms edge inference latency with 99.2% reliability. The hybrid estimator achieves 65% faster parameter convergence than classical RLS, with 18% energy efficiency improvement. Statistical significance is confirmed through ANOVA (F = 24.7, p < 0.001) with large effect sizes (Cohen’s d > 1.2). This performance surpasses recent adaptive control methods while maintaining proven stability guarantees. Hardware validation under realistic industrial conditions remains necessary to confirm practical applicability. Full article

Bilateral teleoperation combines the agility of robotic manipulators with the ability to perform complex contact tasks guided by human expertise, thereby fulfilling a pivotal function in environments beyond human access. However, due to the limited workspace of existing master robots necessitating frequent mapping mode switches, coupled with the pronounced heterogeneity and asymmetry between the workspaces of the master and slave systems, achieving teleoperation of the mobile manipulator remains challenging. In this study, we innovatively introduced a 7 DOFs upper limb exoskeleton as the master control device, rigorously designed to align with the motion coordination of the human arm. Regarding teleoperation mapping, a hybrid heterogeneous teleoperation control framework with a variable mapping scheme, designed for an aerial manipulator performing physical operations, is proposed. The system incorporates mode switching driven by the operator’s hand gestures, seamlessly and intuitively integrating the advantages of position control and rate control modalities to enable adaptive transitions adaptable to diverse task requirements. Comparative teleoperation experiments were conducted using a fully actuated aerial equipped with a compliant 3D end-effector performing physical aerial writing tasks. The mode-switching algorithm was effectively validated in experiments, demonstrating no instability during transitions and achieving a position tracking RMSE of 7.7% and 5.2% in the X,Y-axis, respectively. This approach holds significant potential for future applications in UAM inspection and physical operational scenarios. Full article

This paper presents the design, implementation, and experimental results of a six-degree-of-freedom Delta-type parallel manipulator, in which all actuators were realized using proprietary pneumatic muscles. The objective of the study was to evaluate the suitability of this type of actuator for applications in parallel robotics, with particular attention to their dynamic properties, nonlinearities, and potential limitations. In the first part of the article, the details of the manipulator’s construction and the kinematic model, covering both the forward and inverse kinematics, are presented. The control system was based on antagonistic pairs of pneumatic muscles forming servo drives responsible for the motion of individual arms. The experimental investigations were focused on analyzing trajectory-tracking accuracy and positioning repeatability, both in unloaded conditions and under additional payload applied to the end-effector. The results indicate that positioning errors for simple trajectories were generally below 1 mm, whereas for complex trajectories and under load, they increased, particularly during changes in motion direction, which can be attributed to friction and hysteresis phenomena in the muscles. Repeatability tests confirmed the ability of the manipulator to repeatedly reach the desired positions with small deviations. The analysis carried out confirms that pneumatic muscles can be effectively applied to drive parallel manipulators, offering advantageous features such as high power density and low mass. At the same time, the need for further research on nonlinearity compensation and durability enhancement was demonstrated. Full article

The art of folding paper, named “origami”, has transformed from serving religious and cultural purposes to various educational and entertainment purposes in the modern world. Significantly, the fundamental folds and creases in origami, which enable the creation of 3D structures from a simple flat sheet with unique crease patterns, serve as a great inspiration in engineering applications such as deployable mechanisms for space exploration, self-folding structures for exoskeletons and surgical procedures, micro-grippers, energy absorption, and programmable robotic morphologies. Therefore, this paper will provide a systematic review of the state-of-the-art origami-inspired structures that have been adopted and exploited in robotics design and operation, called origami-inspired robots (OIRs). The advantages of the flexibility and adaptability of these folding mechanisms enable robots to achieve agile mobility and shape-shifting capabilities that are suited to diverse tasks. Furthermore, the inherent compliance structure, meaning that stiffness can be tuned from rigid to soft with different folding states, allows these robots to perform versatile functions, ranging from soft interactions to robust manipulation and a high-DOF system. In addition, the potential to simplify the fabrication and assembly processes, together with its integration into a wide range of actuation systems, further broadens its capabilities. However, these mechanisms increase the complexity in theoretical analysis and modelling, as well as posing a challenge in control algorithms when the robot’s DOF and reconfigurations are significantly increased. By leveraging the principles of folding and integrating actuation and design strategies, these robots can adapt their shapes, stiffness, and functionality to meet the demands of diverse tasks and environments, offering significant advantages over traditional rigid robots. Full article

Addressing key challenges in unstructured environments, including local optimum traps, limited real-time interaction, and convergence difficulties, this research pioneers a hybrid reinforcement learning approach that combines simulated annealing (SA) with proximal policy optimization (PPO) for robotic arm trajectory planning. The framework enables the accurate, collision-free grasping of randomly appearing objects in dynamic obstacles through three key innovations: a probabilistically enhanced simulation environment with a 20% obstacle generation rate; an optimized state-action space featuring 12-dimensional environment coding and 6-DoF joint control; and an SA-PPO algorithm that dynamically adjusts the learning rate to balance exploration and convergence. Experimental results show a 6.52% increase in success rate (98% vs. 92%) and a 7.14% reduction in steps per set compared to the baseline PPO. A real deployment on the AUBO-i5 robotic arm enables real machine grasping, validating a robust transfer from simulation to reality. This work establishes a new paradigm for adaptive robot manipulation in industrial scenarios requiring a real-time response to environmental uncertainty. Full article

Variations in the drive motor’s load inertia during wafer transfer robot arm motion critically degrade end-effector trajectory accuracy. To address this challenge, this study proposes an anti-disturbance control strategy integrating Radial Basis Function Neural Network (RBFNN) and event-triggered mechanisms. Firstly, dynamic simulations reveal that nonlinear load inertia growth increases joint reaction forces and diminishes trajectory precision. The RBFNN dynamically approximates system nonlinearities, while an adaptive law updates its weights online to compensate for load variations and external disturbances. Secondly, an event-triggered mechanism is introduced, updating the controller only when specific conditions are met, thereby reducing communication burden and actuator wear. Subsequently, Lyapunov stability analysis proves the closed-loop system is Uniformly Ultimately Bounded (UUB) and prevents Zeno behavior. Finally, simulations on a planar 2-DOF manipulator demonstrate significantly enhanced trajectory tracking accuracy under variable loads. Critically, the adaptive neural network control method reduces trajectory tracking error by 50% and decreases controller update frequency by 84.7%. This work thus provides both theoretical foundations and engineering references for high-precision wafer transfer robot control. Full article

Contemporary visual assistive devices often lack immersive user experience due to passive control systems. This study introduces a neuronally controlled visual assistive device (NCVAD) that aims to assist visually impaired users in performing reach tasks with active, intuitive control. The developed NCVAD integrates computer vision, electroencephalogram (EEG) signal processing, and robotic manipulation to facilitate object detection, selection, and assistive guidance. The monocular vision-based subsystem implements the YOLOv8n algorithm to detect objects of daily use. Then, audio prompting conveys the detected objects’ information to the user, who selects their targeted object using a voluntary trigger decoded through real-time EEG classification. The target’s physical coordinates are extracted using ArUco markers, and a gradient descent-based path optimization algorithm (POA) guides a 3-DoF robotic arm to reach the target. The classification algorithm achieves over 85% precision and recall in decoding EEG data, even with coexisting physiological artifacts. Similarly, the POA achieves approximately 650 ms of actuation time with a 0.001 learning rate and 0.1 cm² error threshold settings. In conclusion, the study also validates the preliminary analysis results on a working physical model and benchmarks the robotic arm’s performance against human users, establishing the proof-of-concept for future assistive technologies integrating EEG and computer vision paradigms. Full article