Development and field evaluation of a UWB-IMU navigated autonomous spraying robot for papaya greenhouses

Pro-routing: Proactive routing of autonomous multi-capacity robots for pickup-and-delivery tasks

Focusing on the localization challenges for robots in dynamic navigation environments, this study proposes a direct LiDAR-inertial odometry (LIO) system named ADC-LIO, which achieves robust pose estimation and accurate map reconstruction using adaptive distortion covariance. ADC-LIO is engineered to address uncertain motion patterns in autonomous mobile robots, effectively integrating LiDAR scan undistortion within the Kalman filtering update process by embedding an iterative smoothing process and a backpropagation strategy. The ADC-LIO architecture enhances point cloud accuracy, improving the system's overall performance and robustness. In addition, an adaptive covariance processing method is developed to resolve motion-induced sensing uncertainties, which calculates different covariances according to the error characteristics of the point cloud. This method enhances the constraints of high-quality point clouds, reduces the limitations on low-quality point clouds, and utilizes information more effectively. Experiments on the publicly available NTU-VIRAL dataset validate the effectiveness of ADC-LIO, which improves pose estimation accuracy and reduces absolute position errors compared to other state-of-the-art methods, including FAST-LIO, Faster-LIO, FR-LIO, and Point-LIO. The proposed ADC-LIO is an appealing odometry method that delivers accurate, real-time, and reliable tracking and map-building results, posing a practical solution for robotic applications in structured indoor and GPS-denied outdoor environments.

Design, construction, and evaluation of an autonomous robot for harvesting damask roses, equipped with a specialized end-effector

A multi-view ultrasonic imaging solution for buried sewer pipe inspection.

This study provides a comprehensive bibliometric analysis of 1,226 Scopus-indexed publications on social commerce, direct shopping, digital consumer behavior, and Fear of Missing Out (FoMO) between 2005 and 2025. Using Bibliometrix (R) and VOSviewer, the research maps the intellectual development of the field through co-authorship, co-citation, keyword co-occurrence, and international collaboration networks. The findings reveal that electronic commerce and online shopping remain the conceptual core of the literature, while emerging themes include live streaming commerce, chatbot-assisted shopping, augmented reality, impulsive buying, and social presence. China, the United States, and India are the most influential contributors, reflecting global academic engagement with digital consumption trends. Citation analysis shows that studies on live streaming trust formation, chatbot adoption, autonomous delivery robots, and m-commerce drive the field’s recent evolution. The results highlight a clear shift from early research focused on website quality and online trust toward interactive, technology-driven, and psychologically informed models of consumer behavior. This study contributes to a deeper understanding of how digital technologies and socio-psychological mechanisms shape contemporary shopping practices and provides direction for future research in immersive and socially embedded digital commerce ecosystems.

Reliable transfer of control policies from simulation to real-world robotic systems remains a central challenge in robotics, particularly for car-like mobile robots. Digital Twin (DT) technology provides a robust framework for high-fidelity replication of physical platforms and bi-directional synchronization between virtual and real environments. In this study, a DT-based testbed is developed to train and evaluate an imitation learning (IL) control framework in which a neural network policy learns to replicate the behavior of a hybrid Model Predictive Control (MPC)–Backstepping expert controller. The DT framework ensures consistent benchmarking between simulated and physical execution, supporting a structured and safe process for policy validation and deployment. Experimental analysis demonstrates that the learned policy effectively reproduces expert behavior, achieving bounded trajectory-tracking errors and stable performance across simulation and real-world tests. The results confirm that DT-enabled IL provides a viable pathway for Sim2Real transfer, accelerating controller development and deployment in autonomous mobile robotics.

Medical robots capable of autonomously performing interventional and surgical procedures are becoming a reality. Autonomous medical robots promise enhanced accuracy, reduced medical errors, improved accessibility to specialized care, and lower healthcare costs through efficient, minimally invasive procedures. This review examines motion planning as a fundamental building block enabling autonomous medical robots. Motion planning aims to compute high-quality and safe motions for robotic instruments to accomplish interventional and surgical procedures while considering anatomical constraints and physical limitations. We categorize medical robot motion planning into navigation planning (maneuvering instruments to targets via intratissue or endoluminal paths) and manipulation planning (tissue interaction through contact or contact-free approaches). We frame motion planning as a type of AI guidance that can enable eyes-on/hands-off automation. We review state-of-the-art methods in navigation and manipulation planning for medical robots, discuss challenges to clinical adoption, and explore future opportunities for autonomous medical robots.

This paper addresses the challenge of safe path planning for mobile robots operating in human-shared environments, where human movements are inherently stochastic. To this end, we propose a reinforcement-learning-based path planning algorithm that accounts for human-related uncertainties at the planning level. The algorithm first employs a Markov decision process learner to explore the environment and generate multiple candidate paths. Second, to reduce computational redundancy, a path eliminator module filters out similar paths based on a proposed diversity metric, ensuring path diversity with minimal overhead. Simultaneously, a Monte Carlo-simulated human risk predictor is integrated into the decision-making unit to select the safest path among the candidates. This integrated algorithm enables robots to generate safe and efficient trajectories without the need for frequent re-planning, even in environments with stochastic human behavior. Simulation results demonstrate the effectiveness of the proposed method. In high-density settings, a 40×40 grid map with 10 humans, the proposed method reduces the average number of conflicts by −69.8%, −54.8%, and −73.4% compared with A*, MDP, and RRT methods, respectively. Meanwhile, it improves task success rates by 94.4%, 70.7%, and 118.75% relative to the same baseline methods.

Aiming at the problems of insufficient environmental perception capability of autonomous mobile robots and low multi-modal data fusion efficiency in the complex underground coal mine environment featuring low illumination, high dust, and dynamic obstacles, a reliable passable region identification method for autonomous mobile robots operating in underground coal mine is proposed in this paper. Through the spatial synchronous installation strategy of dual 4D millimeter-wave radars and dynamic coordinate system registration technology, it increases point cloud density and effectively enhances the spatial characterization of roadway structures and obstacles. Combining the characteristics of infrared thermal imaging and the penetration advantage of millimeter-wave radar, a multi-modal data complementary mechanism based on decision-level fusion is proposed to solve the perceptual blind zones of single sensors in extreme environments. Integrated with lightweight model optimization and system integration technology, an intelligent environmental perception system adaptable to harsh working conditions is constructed. The experiments were carried out in the simulated tunnel. The experiments were carried out in the simulated tunnel. The experimental results indicate that the robot can utilize the data collected by the infrared camera and the radar to identify the specific distance to obstacles, and can smoothly achieve the recognition and marking of passable areas.

ABSTRACT This paper presents advanced methodologies for real‐time terrain analysis and mapping in autonomous robotic systems. The focus is on appearance‐based terrain traversability analysis and geometric‐based terrain traceability analysis. In the appearance‐based approach, an enhanced segmentation model using pixel‐based augmentation and 13 unique classes is proposed for reliable terrain classification. Semantic images are projected onto a 2.5D map by transforming two‐dimensional image data into a three‐dimensional coordinate system. The geometric‐based approach involves depth estimation from stereo cameras, employing three Zed‐2 cameras and the Depth Sensing application programming interface. The research contributes to improved perception and decision‐making capabilities of autonomous robots operating in complex and dynamic environments and also provides a new comprehensive data set named CranfieldTerra. Experimental results validate the effectiveness of the proposed methodologies, demonstrating their potential in various applications, such as search and rescue, agriculture, and exploration. This study establishes a foundation for further advancements in autonomous robotics, enhancing their ability to navigate safely and efficiently in challenging terrains.

In the context of accelerating digitalization, reliable object reconstruction represents a key prerequisite for developing accurate and functional digital twins. This study introduces a unified evaluation methodology designed to assess and compare optical 3D scanning technologies in terms of geometric accuracy, data completeness, and model consistency. The framework integrates all essential stages of digital reconstruction—from data acquisition to quantitative validation—ensuring reproducibility and comparability of results across different optical systems. To verify its applicability, two optical principles, photogrammetry and structured-light scanning, were implemented on the autonomous mobile robot MiR100. The reference CAD model in a 1:1 scale served as the ground-truth geometry for all analyses. Evaluation procedures included visual inspection, dimensional measurements, and statistical error analysis performed in MeshLab, CloudCompare, and MATLAB. The results confirmed that photogrammetry provides high-quality textural detail but suffers from geometric noise and scale drift (relative error > 10%), whereas structured-light scanning delivers more stable and metrically accurate results. In particular, the scanner mode achieved the highest precision, with a mean deviation of 17.4 mm, RMSE of 26.8 mm, and relative error of 7.6%. The proposed methodological framework thus establishes a reproducible basis for evaluating 3D reconstruction accuracy and supports the integration of optimized digital models into digital twin environments.

Autonomous robots play an important role in modern indoor navigation, but existing systems often struggle to achieve seamless human interaction and semantic understanding of environments. This paper presents an Artificial Intelligence (AI)-driven object recognition system enhanced by Large Language Models (LLMs), such as GPT-4 Vision and Gemini, to bridge this gap. Our approach combines vision-based mapping techniques with natural language processing and interactions to enable intuitive collaboration on navigation tasks. By leveraging multimodal input and vector space analysis, our system achieves enhanced object recognition, semantic embedding, and context-aware responses, setting a new standard for autonomous indoor navigation. This approach provides a novel framework for improving spatial understanding and dynamic interaction, making it suitable for complex indoor environments.

Agricultural productivity faces significant challenges from plant diseases and inefficient pesticide use. This paper presents an autonomous robotic system that integrates real-time machine vision with precision spraying technology. The platform navigates crop fields using a four-wheel drive system while capturing plant images through an onboard camera. These images are processed by a cloud-based Convolutional Neural Network that identifies specific plant diseases with 93% accuracy. Upon detection, the system activates targeted spraying mechanisms that deliver disease-specific pesticides only to infected plants, utilizing multiple chemical reservoirs. Experimental results demonstrate a 70% reduction in pesticide consumption compared to conventional methods while maintaining effective disease control. The system operates on battery power and incorporates real-time monitoring through a web interface and mobile alerts. This research represents a significant advancement in agricultural technology, offering an eco-friendly solution that enhances crop productivity while minimizing environmental impact. The integration of robotics, artificial intelligence, and precision agriculture techniques provides a sustainable approach to plant disease management that can be scaled for various farming applications. The system's practical implementation shows promising results for reducing chemical usage and operational costs while maintaining crop health and yield quality.

As human-robot systems and autonomous robots become increasingly prevalent, the need for task-oriented datasets to study human behaviors in shared spaces has grown significantly. We present a novel dataset focusing on sequential human assembly and disassembly motions in human-robot coexisting environments. It contains over 10,000 samples recorded from multi-view camera setups, each comprising synchronized RGB videos and 2D and 3D human skeletons. Data were collected from 33 participants with diverse physical characteristics and behavior preferences. This dataset highlights practical challenges such as partial occlusions, similar repetitive motions, and varying human behaviors, which are often overlooked in existing datasets and research. Technical validation using benchmarking with state-of-the-art deep learning models reveals significant potential in using this dataset for practical applications. To support diverse research applications, this dataset provides raw and processed data with detailed annotations, including precise timestamps, procedure annotations, and Python codes for reproducibility. It aims to advance research in human motion prediction, task-oriented robotic sequential decision-making, motion and task planning of autonomous robots, and human-robot collaborative policies.

Remote robotic surgery (RRS) represents a frontier in surgical innovation, integrating robotics, artificial intelligence (AI), and high-speed communication networks. Despite its clinical significance, the global research landscape and conceptual evolution of RRS remain insufficiently mapped. A comprehensive bibliometric analysis of 857 Scopus-indexed documents (1980-2025) was conducted using Bibliometrix (R-package), VOSviewer, and CiteSpace. Analyses covered descriptive trends, country productivity, citation impact, collaboration networks, keyword co-occurrence, Bradford's Law of journal concentration, CiteSpace co-citation clustering, and thematic evolution. Thematic mapping was performed using the Walktrap clustering algorithm (250 words, minimum cluster frequency = 5) to visualize conceptual structures and developmental trajectories. RRS research exhibited an annual growth rate of 10.35%, with strong international collaboration (26.96%). The United States, China, Japan, and France dominated global contributions. Keyword co-occurrence and CiteSpace clustering revealed five thematic domains-robotic systems, telemedicine integration, surgical innovation, AI-assisted imaging, and 5G-enabled connectivity. Bradford's Law identified a small core of specialized journals as primary publication outlets. Thematic evolution (1980-2025) indicated three conceptual eras: foundational simulation and telepresence (1980-2013), technological integration with 5G and AI (2014-2022), and intelligent convergence emphasizing deep learning, blockchain, and ultra-low-latency communication (2023-2025). Thematic mapping further highlighted telesurgery as a basic theme and surgery as a motor theme driving interdisciplinary expansion. This bibliometric synthesis reveals a paradigm shift from early teleoperation frameworks to AI-driven, 5G-powered, and cybersecure surgical ecosystems. Future research should prioritize real-time data fusion, robotic autonomy, and ethical frameworks guiding intelligent telesurgical networks.

Purpose This study investigates the factors influencing delivery workers’ willingness to collaborate with autonomous delivery robots (ADRs). As ADRs become more prevalent in Logistics 4.0 environments, understanding human–technology collaboration is critical for supporting both operational efficiency and decent work. Design/methodology/approach We draw from the technology acceptance model (TAM) and service robot acceptance model (sRAM) to develop a model and examine the impact of functional, social and relational factors on delivery workers’ willingness to collaborate with ADRs. A field survey with a sample size of 483 and an online survey with a sample size of 292 were conducted to test the relationships of interest. Findings The results indicate that perceived usefulness, social influence and anthropomorphism have a positive influence on willingness to collaborate with ADRs, with procedural fairness acting as a significant mediator. While the overall model holds across both samples, differences in the strength of relationships suggest that cultural context shapes how employees perceive and respond to ADRs. Originality/value This study contributes to the literature by extending TAM and sRAM to the logistics sector and providing a cross-cultural perspective on employee–ADR collaboration. It addresses a critical gap in logistics and supply chain research, providing practical approaches to technology integration that support decent work in the Logistics 4.0 era.

Current industrial robots deployed in small and medium-sized businesses (SMEs) are too complex, expensive, or dependent on external computing resources. In order to bridge this gap, we introduce an autonomous logistics robot that combines adaptive control and visual perception on a small edge computing platform. The NVIDIA Jetson Nano was equipped with a modified ResNet-18 model that allowed it to concurrently execute three tasks: object-handling zone recognition, obstacle detection, and path tracking. A lightweight rack-and-pinion mechanism enables payload lifting of up to 2 kg without external assistance. Experimental evaluation in semi-structured warehouse settings demonstrated a path tracking accuracy of 92%, obstacle avoidance success of 88%, and object handling success of 90%, with a maximum perception-to-action latency of 150 m. The system maintains stable operation for up to 3 hours on a single charge. Unlike other approaches that focus on single functions or require cloud support, our design integrates navigation, perception, and mechanical handling into a low-power, standalone solution. This highlights its potential as a practical and cost-effective automation platform for SMEs.

Piezoelectric materials possess a special property to produce electricity from mechanical motion and are therefore it is suitable for green energy solutions. In our project, we fabricated a flexible piezoelectric device through a simple, non-vacuum process. We prepared the device by a solution casting process with a thin poly (vinylidene fluoride) (PVDF) film. Under mechanical stress, the device shows a clear electrical response, confirming its functionality. This indicates that piezoelectric materials can be fabricated to utilize as a low-cost, eco-friendly, and efficient means to harvest energy. This device can also be used as a sensor in robots and robot-related applications. This device can sense movement, which can be used in autonomous robots to sense movement, feed back, or even to harvest energy to power robotic sensors. In the future, we can improve the device performance by modifying the film thickness, using more efficient electrode materials, and making it stable to operate in different conditions.

The integration of robotic systems into high-stakes medical procedures has ushered in a new era of surgical precision and capability. However, this advancement introduces complex challenges at the intersection of human and machine. As surgical robots evolve from teleoperated tools to semi-autonomous partners, the dynamics within the surgical team are fundamentally altered. This research investigates the intricate interplay between surgeon trust, cognitive load, and dynamic task allocation in human-robot collaborative surgery. The central thesis is that achieving optimal surgical outcomes and safety depends not merely on the robot's technical proficiency but on a calibrated and adaptive partnership between the surgeon and the autonomous system. Misaligned trust—manifesting as over-trust or under-trust—can lead to attentional misallocations, increased cognitive load, and compromised decision-making, thereby undermining the potential benefits of automation. This paper proposes a mixed-methods approach to explore these dynamics. Through simulation-based experiments with surgical professionals, we aim to quantify the impact of varying levels of robotic autonomy on surgical performance, cognitive load (measured via physiological and subjective metrics), and trust calibration. Complementary qualitative analysis of interviews and observational data will provide nuanced insights into the subjective experiences and decision-making heuristics of surgeons. The expected findings will illuminate the causal relationships between these core factors, revealing how surgeons adapt their trust and cognitive strategies in response to robot behavior. Ultimately, this study aims to contribute a novel, empirically grounded framework for dynamic task allocation. This framework is designed to optimize the human-robot partnership by modulating autonomy levels in real-time based on procedural context, surgeon state, and system confidence, thereby enhancing procedural efficacy, ensuring patient safety, and shaping the future of surgical team collaboration.