Capabilities Of Robots Research Articles

Vision System for a Forestry Navigation Machine.

This article presents the development of a vision system designed to enhance the autonomous navigation capabilities of robots in complex forest environments. Leveraging RGBD and thermic cameras, specifically the Intel RealSense 435i and FLIR ADK, the system integrates diverse visual sensors with advanced image processing algorithms. This integration enables robots to make real-time decisions, recognize obstacles, and dynamically adjust their trajectories during operation. The article focuses on the architectural aspects of the system, emphasizing the role of sensors and the formulation of algorithms crucial for ensuring safety during robot navigation in challenging forest terrains. Additionally, the article discusses the training of two datasets specifically tailored to forest environments, aiming to evaluate their impact on autonomous navigation. Tests conducted in real forest conditions affirm the effectiveness of the developed vision system. The results underscore the system's pivotal contribution to the autonomous navigation of robots in forest environments.

The Impact of Changing Collaborative Workplace Parameters on Assembly Operation Efficiency

Human–robot collaborative systems bring several benefits in using human and robot capabilities simultaneously. One of the critical questions is the impact of these systems on production process efficiency. The search for high-level efficiency is severely dependent on collaborative robot characteristics and motion parameters, and the ability of humans to adjust to changing circumstances. Therefore, our research analyzes the effect of the changing collaborative robot motion parameters, acoustic parameters and visual factors in a specific assembly operation, where efficiency is measured through operation times. To conduct our study, we designed a digital twin-based model and a laboratory environment experiment in the form of a collaborative workplace. The results show that changing the motion, acoustic and visual parameters of the collaborative workplace impact the assembly process efficiency significantly.

Computational design of ultra-robust strain sensors for soft robot perception and autonomy

Compliant strain sensors are crucial for soft robots’ perception and autonomy. However, their deformable bodies and dynamic actuation pose challenges in predictive sensor manufacturing and long-term robustness. This necessitates accurate sensor modelling and well-controlled sensor structural changes under strain. Here, we present a computational sensor design featuring a programmed crack array within micro-crumples strategy. By controlling the user-defined structure, the sensing performance becomes highly tunable and can be accurately modelled by physical models. Moreover, they maintain robust responsiveness under various demanding conditions including noise interruptions (50% strain), intermittent cyclic loadings (100,000 cycles), and dynamic frequencies (0–23 Hz), satisfying soft robots of diverse scaling from macro to micro. Finally, machine intelligence is applied to a sensor-integrated origami robot, enabling robotic trajectory prediction (<4% error) and topographical altitude awareness (<10% error). This strategy holds promise for advancing soft robotic capabilities in exploration, rescue operations, and swarming behaviors in complex environments.

High Dynamic Bipedal Robot with Underactuated Telescopic Straight Legs

Bipedal robots have long been a focal point of robotics research with an unwavering emphasis on platform stability. Achieving stability necessitates meticulous design considerations at every stage, encompassing resilience against environmental disturbances and the inevitable wear associated with various tasks. In pursuit of these objectives, here, the bipedal L04 Robot is introduced. The L04 Robot employs a groundbreaking approach by compactly enclosing the hip joints in all directions and employing a coupled joint design. This innovative approach allows the robot to attain the traditional 6 degrees of freedom in the hip joint while using only four motors. This design not only enhances energy efficiency and battery life but also safeguards all vulnerable motor reducers. Moreover, the double-slider leg design enables the robot to simulate knee bending and leg height adjustment through leg extension. This simulation can be mathematically modeled as a linear inverted pendulum (LIP), rendering the L04 Robot a versatile platform for research into bipedal robot motion control. A dynamic analysis of the bipedal robot based on this structural innovation is conducted accordingly. The design of motion control laws for forward, backward, and lateral movements are also presented. Both simulation and physical experiments corroborate the excellent bipedal walking performance, affirming the stability and superior walking capabilities of the L04 Robot.

A contingency-based approach to service robot design: Role of robot capabilities and personalities

The rise of service robots is changing how products and services are delivered, significantly affecting customer outcomes. However, research has yet to specifically examine how the design of a service robot to specific service contexts influences customer engagement and value co-creation. Our study adopts a contingency perspective to investigate how the design of robot capabilities and personalities aligned with specific service contexts impacts customer engagement and value co-creation intentions. We tested this proposition through three experiments carried out in the banking and restaurant service contexts. Our findings revealed the effectiveness of carefully designed robotic capabilities and personalities within a service infrastructure depends on the specific service contexts. The study findings have important implications for service firms in designing service robots through managing robot capabilities and personalities to align with specific service contexts.

Research on Indoor 3D Reconstruction Technology Based on Semantic Visual Simultaneous Localization and Mapping

In response to the challenge that traditional visual simultaneous localization and mapping (SLAM) systems, based on the assumption of a static environment, struggle to achieve real-time indoor 3D reconstruction in complex dynamic scenes, this paper proposes a real-time indoor 3D reconstruction algorithm based on semantic visual SLAM. By leveraging object detection to obtain 2D semantic information and providing prior information for geometric methods, the fusion of the two effectively suppresses dynamic features, reduces reliance on deep learning methods, and ensures the algorithm's real-time performance. Experimental results on dynamic scenes in the TUM RGB-D dataset show that our algorithm maintains nearly unchanged real-time performance while achieving an average performance improvement of approximately 97.56% and 97.31% on the TUM dataset and Bonn dataset, respectively, compared to the ORB-SLAM2 system. Moreover, our algorithm can reconstruct more intuitive indoor global Octo-map and semantic metric maps compared to sparse point cloud maps, effectively enhancing the scene perception capability of mobile robots and laying the foundation for performing advanced tasks. Furthermore, our algorithm demonstrates a 3.5-10.5 times improvement in real-time performance compared to other mainstream semantic SLAM systems. Experimental results on the NVIDIA Jetson AGX Xavier confirm that our algorithm can run in real time on low-power platforms such as mobile robots or drones. However, the drawbacks of our algorithm include lower reconstruction accuracy in low-texture and large-scale scenes and ineffective suppression of dynamic features in low-dynamic scenes. Future work will consider replacing and improving deep learning methods and integrating IMU and other sensors to enhance system usability.

A comprehensive review of bug algorithms in path planning

The bug algorithm family is the well-known navigation algorithm for robots in unknown environments. However, different types of bug algorithms have their own priorities and weaknesses based on different environmental conditions. According to the characteristics of the bug navigation algorithms, the bug algorithm family is mainly divided into 4 parts. In this paper, four types of bug algorithms (original bug algorithm, M-line Bug, Angel Bug and Range Bug) are presented along with typical samples of each type. Each type of algorithm will be thoroughly explained and exemplified, highlighting its unique characteristics and the suitable environmental conditions for each algorithm. By presenting the basic logic behind each algorithm and examining the environmental conditions they are best suited for, this paper aims to provide researchers with a comprehensive understanding of the bug algorithm family. Ultimately, this knowledge will contribute to the advancement of navigation capabilities in robots operating in unknown and challenging environments.

Design and analysis of an autonomous warehouse robot system with 6-DOF manipulator

With the increasing need for efficiency and accuracy in warehouse operations, the functions and market demands of automated warehouse robots are constantly increasing. This study presents the design, simulation, and implementation of a warehouse robot, showcasing effective automation solution. Leveraging the Robot Operating System (ROS) and Gazebo, a robot with a six-degree-of-freedom robotic arm for diverse manipulation tasks and a differential drive base for broad-spectrum navigation was designed. The simulation environment in Gazebo faithfully replicates real-world warehouse conditions, enabling comprehensive path planning and real-time modifications, powered by move_base. A camera sensor serves as the robot's safety system, designed to detect moving obstacles and initiate appropriate responses, contributing to the enhancement of warehouse safety standards. Simulation results demonstrate the robot's effectiveness in performing pick-and-place tasks while successfully navigating through the environment, indicating the significant potential for real-world warehouse automation applications. Therefore, this work provides a foundation reference for future research aimed at optimizing and expanding the capabilities of autonomous warehouse robots.

Multimodal Locomotion in a Soft Robot Through Hierarchical Actuation.

Soft and continuum robots present the opportunity for extremely large ranges of motion, which can enable dexterous, adaptive, and multimodal locomotion behaviors. However, as the number of degrees of freedom (DOF) of a robot increases, the number of actuators should also increase to achieve the full actuation potential. This presents a dilemma in mobile soft robot design: physical space and power requirements restrict the number and type of actuators available and may ultimately limit the movement capabilities of soft robots with high-DOF appendages. Restrictions on actuation of continuum appendages ultimately may limit the various movement capabilities of soft robots. In this work, we demonstrate multimodal behaviors in an underwater robot called "Hexapus." A hierarchical actuation design for multiappendage soft robots is presented in which a single high-power motor actuates all appendages for locomotion, while smaller low-power motors augment the shape of each appendage. The flexible appendages are designed to be capable of hyperextension for thrust, and flexion for grasping with a peak pullout force of 32 N. For propulsion, we incorporate an elastic membrane connected across the base of each tentacle, which is stretched slowly by the high-power motor and released rapidly through a slip-gear mechanism. Through this actuation arrangement, Hexapus is capable of underwater locomotion with low cost of transport (COT = 1.44 at 16.5 mm/s) while swimming and a variety of multimodal locomotion behaviors, including swimming, turning, grasping, and crawling, which we demonstrate in experiment.

Design and implementation of a field robot using a parallelogram mechanism.

To meet various industrial requirements such as ease of motion, scalability, and cost efficiency, it is necessary to innovate the design of robotic platforms. In this research, a novel approach, from mechanical design to control implementation, is introduced for launching a robotic platform using a parallelogram mechanism. First, a reverse engineering process is applied, progressing from kinematics to dynamics. Then, several mechanical computations are conducted to ensure the structural stability of the robot framework. Subsequently, the dynamic performance of the system is analyzed, focusing on the driving torque and moments in each link. Additionally, the electrical design and transfer function of each joint are identified to ensure practical execution. To validate the effectiveness and feasibility of the design, both numerical simulations and experimental tests are performed. Theoretical results show the dynamic response of the proposed method, particularly in terms of the driving moments of the robotic joints. In real-world tests, various trajectories, such as different rectangular paths, are demonstrated to showcase the robot's capabilities. From these results, it is clear that the proposed approach is both feasible and applicable in practical scenarios.

A Closed-Loop Shared Control Framework for Legged Robots

Shared control, as a combination of human and robot intelligence, has been deemed as a promising direction toward complementing the perception and learning capabilities of legged robots. However, previous works on human–robot control for legged robots are often limited to simple tasks, such as controlling movement direction, posture, or single-leg motion, yet extensive training of the operator is required. To facilitate the transfer of human intelligence to legged robots in unstructured environments, this article presents a user-friendly closed-loop shared control framework. The main novelty is that the operator only needs to make decisions based on the recommendations of the autonomous algorithm, without having to worry about operations or consider contact planning issues. Specifically, a rough navigation path from the operator is smoothed and optimized to generate a path with reduced traversing cost. The traversability of the generated path is assessed using fast Monte Carlo tree search, which is subsequently fed back through an intuitive image interface and force feedback to help the operator make decisions quickly, forming a closed-loop shared control. The simulation and hardware experiments on a hexapod robot show that the proposed framework gives full play to the advantages of human–machine collaboration and improves the performance in terms of learning time from the operator, mission completion time, and success rate than comparison methods.

An edge architecture for enabling autonomous aerial navigation with embedded collision avoidance through remote nonlinear model predictive control

In this article, we present an edge-based architecture for enhancing the autonomous capabilities of resource-constrained aerial robots by enabling a remote nonlinear model predictive control scheme, which can be computationally heavy to run on the aerial robots' onboard processors. The nonlinear model predictive control is used to control the trajectory of an unmanned aerial vehicle while detecting, and preventing potential collisions. The proposed edge architecture enables trajectory recalculation for resource-constrained unmanned aerial vehicles in relatively real-time, which will allow them to have fully autonomous behaviors. The architecture is implemented with a remote Kubernetes cluster on the edge side, and it is evaluated on an unmanned aerial vehicle as our controllable robot, while the robotic operating system is used for managing the source codes, and overall communication. With the utilization of edge computing and the architecture presented in this work, we can overcome computational limitations, that resource-constrained robots have, and provide or improve features that are essential for autonomous missions. At the same time, we can minimize the relative travel time delays for time-critical missions over the edge, in comparison to the cloud. We investigate the validity of this hypothesis by evaluating the system's behavior through a series of experiments by utilizing either the unmanned aerial vehicle or the edge resources for the collision avoidance mission.

Multistable States and Snap-Through Instabilities in an Interconnected Dielectric Elastomer Actuators System

Abstract Snap-through instabilities in single and interconnected dielectric elastomer actuators have demonstrated their potential in enabling many functionalities such as large deformation, high-speed actuation, and enhanced flowrates in fluid pumps. However, the nonlinear nature of dielectric elastomers and the complex interplay of mechanics in interconnected inflated actuators, make the modeling of such systems challenging. In this paper, we present a methodology to analytically model the instabilities in a system of three interconnected homogeneous spherical dielectric elastomer actuators through graphical and numerical approaches. The simulation results reveal the presence of a locus of initial stable states that the interconnected actuators can achieve at zero voltage. In specific loading conditions, the system exhibits multiple stable states which can be cyclically transitioned between by selectively applying voltage to specific actuators. In other conditions, the system may undergo two successive instabilities when the voltage applied to a single actuator in the system is increased monotonically. These results retrieve existing experimental results theoretically for the first time and identify a new behavior of cascading instabilities in inflated dielectric elastomer actuators. We hope this work will pave the way for programmable design of multistable systems to unravel new capabilities in dielectric elastomer actuators and soft robotics.

The Influence of Micro-Hexapod Walking-Induced Pose Changes on LiDAR-SLAM Mapping Performance.

Micro-hexapods, well-suited for navigating tight or uneven spaces and suitable for mass production, hold promise for exploration by robot groups, particularly in disaster scenarios. However, research on simultaneous localization and mapping (SLAM) for micro-hexapods has been lacking. Previous studies have not adequately addressed the development of SLAM systems considering changes in the body axis, and there is a lack of comparative evaluation with other movement mechanisms. This study aims to assess the influence of walking on SLAM capabilities in hexapod robots. Experiments were conducted using the same SLAM system and LiDAR on both a hexapod robot and crawler robot. The study compares map accuracy and LiDAR point cloud data through pattern matching. The experimental results reveal significant fluctuations in LiDAR point cloud data in hexapod robots due to changes in the body axis, leading to a decrease in map accuracy. In the future, the development of SLAM systems considering body axis changes is expected to be crucial for multi-legged robots like micro-hexapods. Therefore, we propose the implementation of a system that incorporates body axis changes during locomotion using inertial measurement units and similar sensors.

Multi-strategy ensemble Harris hawks optimization for smooth path planning of mobile robots

Efficient and safe path planning for autonomous navigation is paramount in advancing the motion control capabilities of mobile robots. To obtain the global optimal smooth path for mobile robots, a multi-strategy ensemble Harris hawks optimization algorithm (SDHHO) is proposed in this paper. The spiral search strategy is adopted to improve the early update method of the algorithm, which can improve the global exploration ability. To achieve better balance between global exploration and local exploitation, the Sine chaotic map is introduced to the escape energy, replacing random components. Furthermore, an elite differential mutation strategy combined with Gaussian mutation is designed to prevent the algorithm from falling into local optima. We compared the SDHHO algorithm with other classical and novel algorithms on 23 benchmark functions, and the results demonstrated the superiority of SDHHO. The proposed algorithm is applied to the smooth path planning for mobile robots, which is transformed into an optimization problem of control nodes of high-order Bezier curves. Empirical evaluations across diverse environments underscore the proficiency of the proposed method in generating paths characterized by reduced length and enhanced safety and continuity.

CGAN-Based Forest Scene 3D Reconstruction from a Single Image

Forest scene 3D reconstruction serves as the fundamental basis for crucial applications such as forest resource inventory, forestry 3D visualization, and the perceptual capabilities of intelligent forestry robots in operational environments. However, traditional 3D reconstruction methods like LiDAR present challenges primarily because of their lack of portability. Additionally, they encounter complexities related to feature point extraction and matching within multi-view stereo vision sensors. In this research, we propose a new method that not only reconstructs the forest environment but also performs a more detailed tree reconstruction in the scene using conditional generative adversarial networks (CGANs) based on a single RGB image. Firstly, we introduced a depth estimation network based on a CGAN. This network aims to reconstruct forest scenes from images and has demonstrated remarkable performance in accurately reconstructing intricate outdoor environments. Subsequently, we designed a new tree silhouette depth map to represent the tree’s shape as derived from the tree prediction network. This network aims to accomplish a detailed 3D reconstruction of individual trees masked by instance segmentation. Our approach underwent validation using the Cityscapes and Make3D outdoor datasets and exhibited exceptional performance compared with state-of-the-art methods, such as GCNDepth. It achieved a relative error as low as 8% (with an absolute error of 1.76 cm) in estimating diameter at breast height (DBH). Remarkably, our method outperforms existing approaches for single-image reconstruction. It stands as a cost-effective and user-friendly alternative to conventional forest survey methods like LiDAR and SFM techniques. The significance of our method lies in its contribution to technical support, enabling the efficient and detailed utilization of 3D forest scene reconstruction for various applications.

Unintended consequences of humanoid service robots: A case study of public service organizations

Robots guided by artificial intelligence (AI) are transforming service operations in for-profit companies. However, public and non-profit organizations have been slower to pursue these innovative new technologies. We conducted an in-depth single-case qualitative study of one public organization (a public library in Australia) to better understand the unintended consequences of humanoid service robots. Our findings theorize unintended consequences through dimensions of customer value and service interaction locus, yielding four types – service disparities, judgment-free communication, noise pollution and social touch. Our analysis reveals new insights into: 1) the unintended consequences of humanoid robots for customers; 2) the effects of these consequences on the service organization; and 3) the technology capabilities of humanoid robots as potential sources of the consequences. When public and non-profit organizations leverage these unintended consequences, they can use robots more effectively to improve the overall customer service experience.

Integration of Deep Learning and Collaborative Robot for Assembly Tasks

Human–robot collaboration has gained attention in the field of manufacturing and assembly tasks, necessitating the development of adaptable and user-friendly forms of interaction. To address this demand, collaborative robots (cobots) have emerged as a viable solution. Deep Learning has played a pivotal role in enhancing robot capabilities and facilitating their perception and understanding of the environment. This study proposes the integration of cobots and Deep Learning to assist users in assembly tasks such as part handover and storage. The proposed system includes an object classification system to categorize and store assembly elements, a voice recognition system to classify user commands, and a hand-tracking system for close interaction. Tests were conducted for each isolated system and for the complete application as used by different individuals, yielding an average accuracy of 91.25%. The integration of Deep Learning into cobot applications has significant potential for transforming industries, including manufacturing, healthcare, and assistive technologies. This work serves as a proof of concept for the use of several neural networks and a cobot in a collaborative task, demonstrating communication between the systems and proposing an evaluation approach for individual and integrated systems.

Into the ice: Exploration and data capturing in glacial moulins by a tethered robot

AbstractGlacial moulins (cylindrical meltwater drainage shafts) provide valuable insights into glacier dynamics, but are inaccessible and hazardous environments for humans to study. Exploring them using passive sensor probes has revealed their complex geometry, which has limited further exploration with passive sensor probes. To overcome these challenges, we propose a tethered robot capable of autonomously exploring and capturing data in glacial moulins. Our novel robot is equipped with a tether to support its motion. Combined with novel estimation and control algorithms, the tethered robot is able to safely and efficiently maneuver in confined, chimney‐like structures, such as moulins. Laboratory and field experiments confirm the feasibility of the proposed design, showing successful localization in environments with no access to positional measurements. Field trials on the Mer de Glace glacier demonstrate the robot's capabilities, descending into the largest moulin to depths of 25 m, capturing valuable scientific data. Onboard sensors are used to capture data to reconstruct the moulin's three‐dimensional geometry and two sampling mechanisms are presented and evaluated to extract samples from the icy surface of the moulin. Our results show promising potential for future exploration of moulins, demonstrating the effectiveness of our tethered robot for safely gathering data from these hazardous environments.

MTUW-GAN: A Multi-Teacher Knowledge Distillation Generative Adversarial Network for Underwater Image Enhancement

Underwater imagery is plagued by issues such as image blurring and color distortion, which significantly impede the detection and operational capabilities of underwater robots, specifically Autonomous Underwater Vehicles (AUVs). Previous approaches to image fusion or multi-scale feature fusion based on deep learning necessitated multi-branch image preprocessing prior to merging through fusion modules. However, these methods have intricate network structures and a high demand for computational resources, rendering them unsuitable for deployment on AUVs, which have limited resources at their disposal. To tackle these challenges, we propose a multi-teacher knowledge distillation GAN for underwater image enhancement (MTUW-GAN). Our approach entails multiple teacher networks instructing student networks simultaneously, enabling them to enhance color and detail in degraded images from various perspectives, thus achieving an image-fusion-level performance. Additionally, we employ middle layer channel distillation in conjunction with the attention mechanism to extract and transfer rich middle layer feature information from the teacher model to the student model. By eliminating multiplexed branching and fusion modules, our lightweight student model can directly generate enhanced underwater images through model compression. Furthermore, we introduce a multimodal objective enhancement function to refine the overall framework training, striking a balance between a low computational effort and high-quality image enhancement. Experimental results, obtained by comparing our method with existing approaches, demonstrate the clear advantages of our proposed method in terms of visual quality, model parameters, and real-time performance. Consequently, our method serves as an effective solution for real-time underwater image enhancement, specifically tailored for deployment on AUVs.