Search Results (2,199)

Currently, machine learning (ML) methods provide a practical approach to model complex systems. Unlike purely analytical models, ML methods can describe the uncertainties (e.g., hysteresis, temperature effects) that are difficult to deal with, potentially yielding higher-precision dynamics by a learning plant given a high-volume dataset. However, employing learning plants that lack explicit mathematical representations in real-time control remains challenging, namely, the model can be conversely looked at as a mapping from input data to output, and it is difficult to represent the corresponding time relationships in real applications. Hence, an ML and operator-based nonlinear control design is proposed in this paper. In this new framework, the bounded input/output spaces of the learning plant are addressed rather than mathematical dynamic formulation, which is realized by robust right coprime factorization (RRCF). While the stabilized learning plant is explored by RRCF, the desired tracking performance is also considered by an operator-based nonlinear internal model control (IMC) design. Eventually, practical application on a soft robotic finger system is conducted, which indicates the better performance of using the controlled learning plant and the feasibility of the proposed framework. Full article

Robotic peach harvesting represents a pivotal strategy for reducing labor costs and improving production efficiency. The fundamental prerequisite for a harvesting robot to successfully complete picking tasks is the accurate recognition of fruit growth posture subsequent to target identification. This study proposes a novel methodology for peach growth posture recognition by integrating an enhanced YOLOv8 algorithm with the RTMpose keypoint detection framework. Specifically, the conventional Neck network in YOLOv8 was replaced by an Atrous Feature Pyramid Network (AFPN) to bolster multi-scale feature representation. Additionally, the Soft Non-Maximum Suppression (Soft-NMS) algorithm was implemented to suppress redundant detections. The RTMpose model was further employed to locate critical morphological landmarks, including the stem and apex, to facilitate precise growth posture recognition. Experimental results indicated that the refined YOLOv8 model attained precision, recall, and mean average precision (mAP) of 98.62%, 96.3%, and 98.01%, respectively, surpassing the baseline model by 8.5%, 6.2%, and 3.0%. The overall accuracy for growth posture recognition achieved 89.60%. This integrated approach enables robust peach detection and reliable posture recognition, thereby providing actionable guidance for the end-effector of an autonomous harvesting robot. Full article

To address the current reliance on manual labor in traditional logistics sorting operations, which leads to low sorting efficiency and high operational costs, this study presents the design of an unmanned logistics vehicle based on the Robot Operating System (ROS). To overcome bounding-box loss issues commonly encountered by mainstream video-stream image segmentation algorithms under complex conditions, the novel SMITE video image segmentation algorithm is employed to accurately extract key regions of mail items while eliminating interference. Extracted logistics information is mapped to corresponding grid points within a map constructed using Simultaneous Localization and Mapping (SLAM). The system performs global path planning with the A* heuristic graph search algorithm to determine the optimal route, autonomously navigates to the target location, and completes the sorting task via a robotic arm, while local path planning is managed using the Dijkstra algorithm. Experimental results demonstrate that the SMITE video image segmentation algorithm maintains stable and accurate segmentation under complex conditions, including object appearance variations, illumination changes, and viewpoint shifts. The PaddleOCR text recognition algorithm achieves an average recognition accuracy exceeding 98.5%, significantly outperforming traditional methods. Through the analysis of existing technologies and the design of a novel parcel-grasping control system, the feasibility of the proposed system is validated in real-world environments. Full article

Instance segmentation in agricultural robotics requires a balance between real-time performance and accuracy. This study proposes a lightweight pomelo image segmentation method based on the YOLOv8n-seg model integrated with the RepGhost module. A pomelo dataset consisting of 5076 samples was constructed through systematic image acquisition, annotation, and data augmentation. The RepGhost architecture was incorporated into the C2f module of the YOLOv8-seg backbone network to enhance feature reuse capabilities while reducing computational complexity. Experimental results demonstrate that the YOLOv8-seg-RepGhost model enhances efficiency without compromising accuracy: parameter count is reduced by 16.5% (from 3.41 M to 2.84 M), computational load decreases by 14.8% (from 12.8 GFLOPs to 10.9 GFLOPs), and inference time is shortened by 6.3% (to 15 ms). The model maintains excellent detection performance with bounding box mAP50 at 97.75% and mask mAP50 at 97.51%. The research achieves both high segmentation efficiency and detection accuracy, offering core support for developing visual systems in harvesting robots and providing an effective solution for deep learning-based fruit target recognition and automated harvesting applications. Full article

This paper presents an immersive teleoperation framework for service robots that combines real-time 3D human pose estimation with a Virtual Reality (VR) interface to support intuitive, natural robot control. The operator is tracked using MediaPipe for 2D landmark detection and an Intel RealSense D455 RGB-D (Red-Green-Blue plus Depth) camera for depth acquisition, enabling 3D reconstruction of key joints. Joint angles are computed using efficient vector operations and mapped to the kinematic constraints of an anthropomorphic arm on the CHARMIE service robot. A VR-based telepresence interface provides stereoscopic video and head-motion-based view control to improve situational awareness during manipulation tasks. Experiments in real-world object grasping demonstrate reliable arm teleoperation and effective telepresence; however, vision-only estimation remains limited for axial rotations (e.g., elbow and wrist yaw), particularly under occlusions and unfavorable viewpoints. The proposed system provides a practical pathway toward low-cost, sensor-driven, immersive human–robot interaction for service robotics in dynamic environments. Full article

Electric vehicles (EVs) rely on a battery pack as their primary energy source, making it a critical component for their operation. To guarantee safe and correct functioning, a Battery Management System (BMS) is employed, which uses variables such as State of Charge (SOC) to set charge/discharge limits and to monitor pack health. In this article, we propose a Multilayer Perceptron (MLP) network to estimate the SOC of a 14.8 V battery pack installed in a robotic vacuum cleaner. Both offline and online (real-time) tests were conducted under continuous load and with rest intervals. The MLP’s output is compared against two commonly used approaches: NARX (Nonlinear Autoregressive Exogenous) and CNN (Convolutional Neural Network). Performance is evaluated via statistical metrics, Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE), and we also assess computational cost using Operational Intensity. Finally, we map these results onto a Roofline Model to predict how the MLP would perform on an automotive-grade microcontroller unit (MCU). A generalization analysis is performed using Transfer Learning and optimization using MLP–Kalman. The best performers are the MLP–Kalman network, which achieved an RMSE of approximately 13% relative to the true SOC, and NARX, which achieved approximately 12%. The computational cost of both is very close, making it particularly suitable for use in BMS. Full article

The widespread application of robots in complex and dynamic environments demands that Visual SLAM is both robust and accurate. However, dynamic objects, varying illumination, and environmental complexity fundamentally challenge the static world assumptions underlying traditional SLAM methods. This review provides a comprehensive investigation into the mathematical foundations of V-SLAM and systematically analyzes the key optimization techniques developed for dynamic environments, with particular emphasis on advances since 2020. We begin by rigorously deriving the probabilistic formulation of V-SLAM and its basis in nonlinear optimization, unifying it under a Maximum a Posteriori (MAP) estimation framework. We then propose a taxonomy based on how dynamic elements are handled mathematically, which reflects the historical evolution from robust estimation to semantic modeling and then to deep learning. This framework provides detailed analysis of three main categories: (1) robust estimation theory-based methods for outlier rejection, elaborating on the mathematical models of M-estimators and switch variables; (2) semantic information and factor graph-based methods for explicit dynamic object modeling, deriving the joint optimization formulation for multi-object tracking and SLAM; and (3) deep learning-based end-to-end optimization methods, discussing their mathematical foundations and interpretability challenges. This paper delves into the mathematical principles, performance boundaries, and theoretical controversies underlying these approaches, concluding with a summary of future research directions informed by the latest developments in the field. The review aims to provide both a solid mathematical foundation for understanding current dynamic V-SLAM techniques and inspiration for future algorithmic innovations. By adopting a math-first perspective and organizing the field through its core optimization paradigms, this work offers a clarifying framework for both understanding and advancing dynamic V-SLAM. Full article

In large-scale Unmanned Aerial Vehicle (UAV) and task environments—particularly those involving obstacles—dimensional explosion remains a significant challenge in Multi-Robot Task Allocation (MRTA). To this end, a novel heuristic MRTA framework based on Topological Graph Construction (TGC) is proposed. First, the physical map is transformed into a pixel map, from which a Generalized Voronoi Graph (GVG) is generated by extracting clearance points, which is then used to construct the topological graph of the obstacle environment. Next, the affiliations of UAVs and tasks within the topological graph are determined to partition different topological regions, and the task value of each topological node is calculated, followed by the first-phase Task Allocation (TA) on these topological nodes. Finally, UAVs within the same topological region with their allocated tasks perform a local second-phase TA and generate the final TA result. The simulation experiments analyze the influence of different pixel resolutions on the performance of the proposed method. Subsequently, robustness experiments under localization noise, path cost noise, and communication delays demonstrate that the total benefit achieved by the proposed method remains relatively stable, while the computational time is moderately affected. Moreover, comparative experiments and statistical analyses were conducted against k-means clustering-based MRTA methods in different UAV, task, and obstacle scale environments. The results show that the proposed method improves computational speed while maintaining solution quality, with the PI-based method achieving speedups of over 60 times and the CBBA-based method over 10 times compared with the baseline method. Full article

To address the problems of low success rate, excessively long obstacle avoidance paths, and a large number of invalid nodes in path planning for robotic arms in complex environments, this paper proposes an obstacle avoidance path planning method based on the Cauchy Chaotic African Vulture Optimization Algorithm (CC-AVOA). By introducing a Cauchy perturbation term, the algorithm retains a certain degree of randomness in the later stages of the search, which helps to escape local optima. Furthermore, the introduction of a logical chaotic mapping increases the diversity of the initial vulture population, thereby improving the overall search efficiency of the algorithm. This paper compares the performance of the CC-AVOA algorithm with the standard African Vulture Optimization Algorithm (AVOA), the Rapid Exploratory Random Tree (RRT) algorithm, and the A* algorithm through simulation experiments in MATLAB R2024a under two-dimensional, three-dimensional, and robotic arm space environments. The results show that the CC-AVOA algorithm can generate paths with fewer nodes and shorter paths. Finally, the CC-AVOA algorithm is validated on both the RoboGuide industrial simulation platform and a physical FANUC robotic arm. The planned trajectories can be accurately executed without collisions, further confirming the feasibility and reliability of the proposed method in real industrial scenarios. Full article

Three-dimensional visual grounding is a core technology that identifies specific objects within complex 3D scenes based on natural language instructions, enhancing human–machine interactions in robotics and augmented reality domains. Traditional approaches have focused on supervised learning, which relies on annotated data; however, zero-shot methodologies are emerging due to the high costs of data construction and limitations in generalization. SeeGround achieves state-of-the-art performance by integrating 2D rendered images and spatial text descriptions. Nevertheless, SeeGround exhibits vulnerabilities in clearly discerning relative depth relationships owing to its implicit depth representations in 2D views. This study proposes the relational depth text (RDT) technique to overcome these limitations, utilizing a Monocular Depth Estimation model to extract depth maps from rendered 2D images and applying the K-Nearest Neighbors algorithm to convert inter-object relative depth relations into natural language descriptions, thereby incorporating them into Vision–Language Model (VLM) prompts. This method distinguishes itself by augmenting spatial reasoning capabilities while preserving SeeGround’s existing pipeline, demonstrating a 3.54% improvement in the Acc@0.25 metric on the Nr3D dataset in a 7B VLM environment that is approximately 10.3 times lighter than the original model, along with a 6.74% increase in Unique cases on the ScanRefer dataset, albeit with a 1.70% decline in Multiple cases. The proposed technique enhances the robustness of grounding through viewpoint anchoring and candidate discrimination in complex query scenarios, and is expected to improve efficiency in practical applications through future multi-view fusion and conditional execution optimizations. Full article

To address the challenging requirements of citrus detection in complex orchard environments, this paper proposes ACDNet (Adaptive Citrus Detection Network), a novel deep learning framework specifically designed for automated citrus harvesting. The proposed method introduces three key innovations: (1) Citrus-Adaptive Feature Extraction (CAFE) module that combines fruit-aware partial convolution with illumination-adaptive attention mechanisms to enhance feature representation with improved efficiency; (2) Dynamic Multi-Scale Sampling (DMS) operator that adaptively focuses sampling points on fruit regions while suppressing background interference through content-aware offset generation; and (3) Fruit-Shape Aware IoU (FSA-IoU) loss function that incorporates citrus morphological priors and occlusion patterns to improve localization accuracy. Extensive experiments on our newly constructed CitrusSet dataset, which comprises 2887 images capturing diverse lighting conditions, occlusion levels, and fruit overlapping scenarios, demonstrate that ACDNet achieves superior performance with mAP@0.5 of 97.5%, precision of 92.1%, and recall of 92.8%, while maintaining real-time inference at 55.6 FPS. Compared to the baseline YOLOv8n model, ACDNet achieves improvements of 1.7%, 3.4%, and 3.6% in mAP@0.5, precision, and recall, respectively, while reducing model parameters by 11% (to 2.67 M) and computational cost by 20% (to 6.5 G FLOPs), making it highly suitable for deployment in resource-constrained robotic harvesting systems. However, the current study is primarily validated on citrus fruits, and future work will focus on extending ACDNet to other spherical fruits and exploring its generalization under extreme weather conditions. Full article

Scene depth information is a key component of any robotic mobile application. Range sensors, such as LiDAR, sonar, or radar, capture depth data of a scene. However, the data captured by these sensors frequently presents missing regions or information with a low confidence level. These missing regions in the depth data could be large areas without information, making it difficult to make decisions, for instance, for an autonomous vehicle. Recovering depth data has become a primary activity for computer vision applications. This work proposes and evaluates an interpolation model to infer dense depth maps from a Lab color space reference picture and an incomplete-depth image embedded in a completion pipeline. The complete proposal pipeline comprises convolutional layers and a convex combination of the infinity Laplacian and non-local means model. The proposed model infers dense depth maps by considering depth data and utilizing clues from a color picture of the scene, along with a metric for computing differences between two pixels. The work contributes (i) the convex combination of the two models to interpolate the data, and (ii) the proposal of a class of function suitable for balancing between different models. The obtained results show that the model outperforms similar models in the KITTI dataset and outperforms our previous implementation in the NYU_v2 dataset, dropping the MSE by 34.86%, 3.35%, and 34.42% for 4×, 8×, 16× upsampling tasks, respectively. Full article

Recent advances in legged robotics have highlighted deep reinforcement learning (DRL)-based controllers for their robust adaptability to diverse, unstructured environments. While position-based DRL controllers achieve high tracking accuracy, they offer limited disturbance rejection, which degrades walking stability; torque-based DRL controllers can mitigate this issue but typically require extensive time and trial-and-error to converge. To address these challenges, we propose a Real-Time Motion Generator (RTMG). At each time step, RTMG kinematically synthesizes end-effector trajectories from target translational and angular velocities (yaw rate) and step length, then maps them to joint angles via inverse kinematics to produce imitation data. The RL agent uses this imitation data as a torque bias, which is gradually annealed during training to enable fully autonomous behavior. We further combine the RTMG-generated imitation data with a decaying action priors scheme to ensure both initial stability and motion diversity. The proposed training pipeline, implemented in NVIDIA Isaac Gym with Proximal Policy Optimization (PPO), reliably converges to the target gait pattern. The trained controller is Tensor RT-optimized and runs at 50 Hz on a Jetson Nano; relative to a position-based baseline, torso oscillation is reduced by 24.88% in simulation and 21.24% on hardware, demonstrating the effectiveness of the approach. Full article

Path planning aims to find a safe and efficient path from a starting point to an end point, and it has been well developed in fields such as robot navigation, autonomous driving, and intelligent decision systems. However, traditional path planning faces challenges in an uncertain rescuing environment due to limited sensing range and a lack of accurate obstacle information. In order to address this issue, this paper proposes an improved two-stage Theta* algorithm for handling multi-probability obstacle scenarios in unstructured rescue environments. First, a global probability raster map is constructed by integrating historical maps and expert prediction maps with probability weights quantifying the uncertainty in the spatial and temporal distribution of obstacles. Second, a probability-sensitive heuristic function (PSHF) is designed, and a Sigmoid function is used to map the probability field of obstacles, thereby enabling limited penetration in low-risk areas and enforced avoidance in high-risk areas. Furthermore, a multi-stage line-of-sight detection optimization mechanism is proposed, which combines probability soft threshold penetration and backtracking verification to improve the noise robustness. Finally, a hierarchical planning architecture is constructed to separate global probabilistic guidance from local strict obstacle avoidance, ensuring both the global optimality and local adaptability of the path. Extensive simulation results in mine rescue scenarios demonstrate that the proposed method achieves lower path cost and fewer path nodes compared to traditional A*, Dijkstra, and Theta* algorithms, while significantly reducing local replanning overhead and maintaining stable performance across multiple uncertain environments. Full article

Dynamic objects present a major challenge for visual simultaneous localization and mapping (Visual SLAM), as feature measurements originating from moving regions can corrupt camera pose estimation and lead to inaccurate maps. In this paper, we propose a lightweight, semantic-free front-end enhancement for ORB-SLAM that detects and suppresses dynamic features using optical flow geometry. The key idea is to estimate a global motion direction point (MDP) from optical flow vectors and to classify feature points based on their angular consistency with the camera-induced motion field. Unlike magnitude-based flow filtering, the proposed strategy exploits the geometric consistency of optical flow with respect to a motion direction point, providing robustness not only to depth variation and camera speed changes but also to different camera motion patterns, including pure translation and pure rotation. The method is integrated into the ORB-SLAM front-end without modifying the back-end optimization or cost function. Experiments on public dynamic-scene datasets demonstrate that the proposed approach reduces absolute trajectory error by up to approximately 45% compared to baseline ORB-SLAM, while maintaining real-time performance on a CPU-only platform. These results indicate that reliable dynamic feature suppression can be achieved without semantic priors or deep learning models. Full article