Field Of Robotics Research Articles

SolarBot: A Dual-Mode, Bluetooth-Enabled Two-Wheel Robot Powered by Renewable Energy

This research paper explores the development and deployment of a two-wheel drive robot car that leverages renewable solar energy stored in lithium-ion batteries. The system is designed with an L298N motor driver, an Arduino microcontroller, and an HC-05 Bluetooth module, providing the robot with both autonomous and manual control capabilities. The solar panel, integrated with a charging module and voltage regulator, is mounted on a zero PCB, ensuring a sustainable and uninterrupted power supply. The robot is equipped with ultrasonic sensors, enabling it to detect and navigate around obstacles automatically, ensuring a safe and efficient operation. In its autonomous mode, the robot can navigate predefined paths, making real-time adjustments based on sensor input to avoid collisions. This feature is particularly useful for applications such as automated plant watering, where the robot can move through a garden and irrigate plants while avoiding obstacles. Additionally, the robot can be utilized as a floor cleaning device, capable of maneuvering around furniture and other objects. The RC Bluetooth app facilitates manual control, allowing users to operate the robot remotely for various tasks. The project demonstrates a practical application of renewable energy in robotics, emphasizing the benefits of sustainable energy solutions and versatile operational modes. The use of a wooden platform provides a sturdy base for the robot's components, ensuring durability and reliability. This work contributes to the field of robotics by showcasing how solar power can be effectively harnessed to create energy-efficient, multifunctional robotic systems.

A Novel Terrain Segmentation Approach for Scene Understanding of Field Robots

A Novel Terrain Segmentation Approach for Scene Understanding of Field Robots

Policy Compression for Intelligent Continuous Control on Low-Power Edge Devices.

Interest in deploying deep reinforcement learning (DRL) models on low-power edge devices, such as Autonomous Mobile Robots (AMRs) and Internet of Things (IoT) devices, has seen a significant rise due to the potential of performing real-time inference by eliminating the latency and reliability issues incurred from wireless communication and the privacy benefits of processing data locally. Deploying such energy-intensive models on power-constrained devices is not always feasible, however, which has led to the development of model compression techniques that can reduce the size and computational complexity of DRL policies. Policy distillation, the most popular of these methods, can be used to first lower the number of network parameters by transferring the behavior of a large teacher network to a smaller student model before deploying these students at the edge. This works well with deterministic policies that operate using discrete actions. However, many real-world tasks that are power constrained, such as in the field of robotics, are formulated using continuous action spaces, which are not supported. In this work, we improve the policy distillation method to support the compression of DRL models designed to solve these continuous control tasks, with an emphasis on maintaining the stochastic nature of continuous DRL algorithms. Experiments show that our methods can be used effectively to compress such policies up to 750% while maintaining or even exceeding their teacher's performance by up to 41% in solving two popular continuous control tasks.

A method of dense point cloud SLAM based on improved YOLOV8 and fused with ORB-SLAM3 to cope with dynamic environments

With the development of society and the advancement of technology, intelligent robots have been widely used in various fields. At the same time, Simultaneous Localization and Mapping (SLAM) technology is a key technology in the research field of intelligent robots. However, in dynamic environments, achieving accurate and robust visual SLAM remains a major challenge. In this paper, we propose a method based on improved YOLOv8 fused with ORB-SLAM3 to address dense point cloud SLAM in dynamic environments. Our proposed method successfully integrates real-time object detection and image segmentation technologies of YOLOv8 into the ORB-SLAM3 framework, achieving high-precision and robust visual SLAM in dynamic environments. In the YOLOv8 framework, we use a balanced convolution method, GSConv, instead of some traditional convolution layers (Conv), which balances accuracy with computational load. Based on the GSConv convolution method, we adopt a new feature fusion module, VoVGSCSP, to replace traditional C2f feature fusion modules, thereby improving the Neck structure of YOLOv8 and achieving a lightweight network model. We compare our proposed method with ORB-SLAM3 and some computer vision algorithms on the TUM dataset. Experimental data confirms that our method outperforms existing visual SLAM algorithms in dynamic environments. In fast-moving dynamic environments, the RMSE of absolute pose estimation of our method is 96.28% lower than that of ORB-SLAM3, and the RMSE of relative pose estimation is 51.57% lower than that of ORB-SLAM3. The experimental results demonstrate that our method significantly improves the accuracy of pose estimation in dynamic environments and greatly enhances the performance compared to ORB-SLAM3.

Investigating the Influence of Counterflow Regions on the Hydrodynamic Performance of Biomimetic Robotic Fish.

Biomimetic robotic fish are a novel approach to studying quiet, highly agile, and efficient underwater propulsion systems, attracting significant interest from experts in robotics and engineering. These versatile robots showcase their ability to operate effectively in various water conditions. Nevertheless, the comprehension of the swimming mechanics and the evolution of the flow field of flexible robots in counterflow regions is still unknown. This paper presents a framework for the self-propulsion of robotic fish that imitates biological characteristics. The method utilizes computational fluid dynamics to analyze the hydrodynamic efficiency of the organisms at different frequencies of tail movement, under both still and opposing flow circumstances. Moreover, this study clarifies the mechanisms that explain how changes in the aquatic environment affect the speed and efficiency of propulsion. It also examines the most effective swimming tactics for places with counterflow. The results suggest that the propulsion effectiveness of robotic fish in counterflow locations does not consistently correspond to various tail-beat frequencies. By utilizing vorticity maps, a comparative analysis can identify situations when counterflow zones improve the efficiency of propulsion.

Human-robot interactions in autonomous hospital transports

The integration of robotics in nursing is a significant shift in healthcare, driven by the aging global population and the increasing demand for care. Robots in nursing can handle less technical tasks such as patient transport and rehabilitation activities. This support allows caregivers to focus on less strenuous nursing duties and more direct patient care. Human-Robot Interaction (HRI) plays an important role in this challenging context. In this research, we present an autonomous hospital transport system based on the ROS 2 framework, focusing on enhancing HRI in the healthcare environment. It encompasses the development of a control architecture for autonomous robot behavior, the implementation of machine learning for emergency detection, and the creation of a user-friendly interface for both patients and staff. The proposed concepts were validated in real-world scenarios in three different hospitals in Germany. This not only demonstrates the practical application of this system but also shares insights and methods, encouraging further advancement in the field of healthcare robotics.

Open-source design of low-cost sensorised elastic actuators for collaborative prosthetics and orthotics

Collaborative robots, or cobots, have become popular due to their ability to safely operate alongside humans in shared environments. These robots use compliant actuators as a key design element to prevent damage during unintended collisions. In prosthetic and orthotic applications, compliant actuators are crucial for ensuring user safety and comfort. However, most compliant cobots for these applications are excessively expensive and complex to construct. Our study introduces an innovative, cost-effective, and sensorised elastic actuator design tailored for prosthetics and orthotics. The design uses a modular approach and leverages 3D printing technology for rapid customisation, enabling efficient and affordable fabrication. Both hardware and software components are open-source, facilitating unrestricted access for students, researchers, and practitioners. Our design supports impedance and admittance control techniques, enhancing the system’s capabilities. Validation results show a standard deviation of 9.67 Nm between calculated and measured torque in impedance control and 0.2563 radians between calculated and measured angles in admittance control. This allows for improved adaptability to varying operational requirements in prosthetics and orthotics. By introducing this educational framework encompassing a low-cost, sensorised elastic actuator design, we aim to address the need for accessible solutions in the field of collaborative robotics for prosthetics and orthotics.

Ethics and responsibility in biohybrid robotics research

The industrial revolution of the 19th century marked the onset of an era of machines and robots that transformed societies. Since the beginning of the 21st century, a new generation of robots envisions similar societal transformation. These robots are biohybrid: part living and part engineered. They may self-assemble and emerge from complex interactions between living cells. While this new era of living robots presents unprecedented opportunities for positive societal impact, it also poses a host of ethical challenges. A systematic, nuanced examination of these ethical issues is of paramount importance to guide the evolution of this nascent field. Multidisciplinary fields face the challenge that inertia around collective action to address ethical boundaries may result in unexpected consequences for researchers and societies alike. In this Perspective, we i) clarify the ethical challenges associated with biohybrid robotics, ii) discuss the need for and elements of a potential governance framework tailored to this technology; and iii) propose tangible steps toward ethical compliance and policy formation in the field of biohybrid robotics.

Evolution of Industrial Robots from the Perspective of the Metaverse: Integration of Virtual and Physical Realities and Human–Robot Collaboration

During the transition from Industry 4.0 to Industry 5.0, industrial robotics technology faces the need for intelligent and highly integrated development. Metaverse technology creates immersive and interactive virtual environments, allowing technicians to perform simulations and experiments in the virtual world, and overcoming the limitations of traditional industrial operations. This paper explores the application and evolution of metaverse technology in the field of industrial robotics, focusing on the realization of virtual–real integration and human–machine collaboration. It proposes a design framework for a virtual–real interaction system based on the ROS and WEB technologies, supporting robot connectivity, posture display, coordinate axis conversion, and cross-platform multi-robot loading. This paper emphasizes the study of two key technologies for the system: virtual–real model communication and virtual–real model transformation. A general communication mechanism is designed and implemented based on the ROS, using the ROS topic subscription to achieve connection and real-time data communication between physical robots and virtual models, and utilizing URDF model transformation technology for model invocation and display. Compared with traditional simulation software, i.e., KUKA Sim PRO (version 1.1) and RobotStudio (version 6.08), the system improves model loading by 45.58% and 24.72%, and the drive response by 41.50% and 28.75%. This system not only supports virtual simulation and training but also enables the operation of physical industrial robots, provides persistent data storage, and supports action reproduction and offline data analysis and decision making.

Core–Shell Nanostructured Assemblies Enable Ultrarobust, Notch‐Resistant and Self‐Healing Materials

AbstractActuators based on stimulus‐responsive soft materials have attracted widespread attention due to their significant advantages in flexibility and structural adaptability over traditional rigid actuators. However, the development of fast‐actuating, mechanical robust and self‐healing actuators without compromising flexibility remains an ongoing challenge. Here, this study presents a photo‐responsive flexible actuator by incorporating core–shell liquid metal nano‐assemblies into a polyurethane matrix to construct a dynamic supramolecular interface. The nano‐assemblies are endowed with adaptive characteristics to external loading, being expected to dissipate energy via the reversible reconstruction of hydrogen bonding and deformation of nano‐assemblies. The obtained composites exhibit excellent mechanical strength (31 MPa), low modulus (2.02 MPa), high stretchability (1563.95%), autonomous self‐healing (92.5%), and NIR‐responsive actuation properties. Furthermore, the combination of high cohesive energy but fluxible nano‐liquid metal core, and strong dynamic interface not only achieves the balance of high tensile strength and high flexibility but also endows the actuators with outstanding notch‐resistant performance (fracture energy≈58.8 kJ m−2) through multiphase energy dissipation. This work provides a promising strategy for developing soft yet tough self‐healing materials in the fields of flexible robotics and artificial muscles.

Bi-HS-RRTX\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^\ ext {X}$$\\end{document}: an efficient sampling-based motion planning algorithm for unknown dynamic environments

In the field of autonomous mobile robots, sampling-based motion planning methods have demonstrated their efficiency in complex environments. Although the Rapidly-exploring Random Tree (RRT) algorithm and its variants have achieved significant success in known static environment, it is still challenging in achieving optimal motion planning in unknown dynamic environments. To address this issue, this paper proposes a novel motion planning algorithm Bi-HS-RRTX\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^\ ext {X}$$\\end{document}, which facilitates asymptotically optimal real-time planning in continuously changing unknown environments. The algorithm swiftly determines an initial feasible path by employing the bidirectional search. When dynamic obstacles render the planned path infeasible, the bidirectional search is reactivated promptly to reconstruct the search tree in a local area, thereby significantly reducing the search planning time. Additionally, this paper adopts a hybrid heuristic sampling strategy to optimize the planned path quality and search efficiency. The convergence of the proposed algorithm is accelerated by merging local biased sampling with nominal path and global heuristic sampling in hyper-ellipsoid region. To verify the effectiveness and efficiency of the proposed algorithm in unknown dynamic environments, numerous comparative experiments with existing algorithms were conducted. The experimental results indicate that the proposed planning algorithm has significant advantages in planned path length and planning time.

Highly stretchable dynamic hydrogels for soft multilayer electronics.

Recent progress in the development of synthetic polymer networks has enabled the next generation of hydrogel-based machines and devices. The ability to mimic the mechanical and electrical properties of human tissue gives great potential toward the fields of bioelectronics and soft robotics. However, fabricating hydrogel devices that display high ionic conductivity while maintaining high stretchability and softness remains unmet. Here, we synthesize supramolecular poly(ionic) networks, which display high stretchability (>1500%), compressibility (>90%), and rapid self-recovery (<30 s), while achieving ionic conductivities of up to 0.1 S cm -1. Dynamic cross-links give rise to inter-layer adhesion and a stable interface is formed on account of ultrahigh binding affinities (>1013 M-2). Superior adherence between layers enabled the fabrication of an intrinsically stretchable hydrogel power source, paving the way for the next generation of multi-layer tissue mimetic devices.

Large-area magnetic skin for multi-point and multi-scale tactile sensing with super-resolution

The advancements in tactile sensor technology have found wide-ranging applications in robotic fields, resulting in remarkable achievements in object manipulation and overall human-machine interactions. However, the widespread availability of high-resolution tactile skins remains limited, due to the challenges of incorporating large-sized, robust sensing units and increased wiring complexity. One approach to achieve high-resolution and robust tactile skins is to integrate a limited number of sensor units (taxels) into a flexible surface material and leverage signal processing techniques to achieve super-resolution sensing. Here, we present a magnetic skin consisting of multi-direction magnetized flexible films and a contactless Hall sensor array. The key features of the proposed sensor include the specific magnetization arrangement, K-Nearest Neighbors (KNN) clustering algorithm and convolutional neural network (CNN) model for signal processing. Using only an array of 4*4 taxels, our magnetic skin is capable of achieving super-resolution perception over an area of 48400 mm2, with an average localization error of 1.2 mm. By employing neural network algorithms to decouple the multi-dimensional signals, the skin can achieve multi-point and multi-scale perception. We also demonstrate the promising potentials of the proposed sensor in intelligent control, by simultaneously controlling two vehicles with trajectory mapping on the magnetic skin.

Enhancing 3D object detection by using neural network with self-adaptive thresholding

Robust 3D object detection remains a pivotal concern in the domain of autonomous field robotics. Despite notable enhancements in detection accuracy across standard datasets, real-world urban environments, characterized by their unstructured and dynamic nature, frequently precipitate an elevated incidence of false positives, thereby undermining the reliability of existing detection paradigms. In this context, our study introduces an advanced post-processing algorithm that modulates detection thresholds dynamically relative to the distance from the ego object. Traditional perception systems typically utilize a uniform threshold, which often leads to decreased efficacy in detecting distant objects. In contrast, our proposed methodology employs a Neural Network with a self-adaptive thresholding mechanism that significantly attenuates false negatives while concurrently diminishing false positives, particularly in complex urban settings. Empirical results substantiate that our algorithm not only augments the performance of 3D object detection models in diverse urban and adverse weather scenarios but also establishes a new benchmark for adaptive thresholding techniques in field robotics.

Enhancing 3D object detection by using neural network with self-adaptive thresholding

Robust 3D object detection remains a pivotal concern in the domain of autonomous field robotics. Despite notable enhancements in detection accuracy across standard datasets, real-world urban environments, characterized by their unstructured and dynamic nature, frequently precipitate an elevated incidence of false positives, thereby undermining the reliability of existing detection paradigms. In this context, our study introduces an advanced post-processing algorithm that modulates detection thresholds dynamically relative to the distance from the ego object. Traditional perception systems typically utilize a uniform threshold, which often leads to decreased efficacy in detecting distant objects. In contrast, our proposed methodology employs a Neural Network with a self-adaptive thresholding mechanism that significantly attenuates false negatives while concurrently diminishing false positives, particularly in complex urban settings. Empirical results substantiate that our algorithm not only augments the performance of 3D object detection models in diverse urban and adverse weather scenarios but also establishes a new benchmark for adaptive thresholding techniques in field robotics.

Towards Implantable Artificial Muscles: Epoxy Based Bilayer Thermal Actuators with Ambient Activation Temperatures

AbstractThe development of soft and biocompatible actuators is a current challenge in the fast‐growing field of soft robotics. A variety of shape‐memory and thermal actuators are currently being explored for application in these areas, especially to produce actuators that can operate at biocompatible temperatures for in vivo applications. Here we detail the synthesis of epoxy based materials, a class of materials not fully explored for soft actuators. By careful tuning of polymer composition by variation of monomer feed ratios, we show tuneable glass transition temperatures (Tgs) of these materials. Ambient temperature (30–60 °C) thermal actuators were then realised by casting of bilayers of epoxy resins with varying Tgs. Differences in thermal expansion when the Tg was reached lead to actuation in a specific direction. With optimisation, actuation in both the external‐heated and joule‐heated NiChrome‐epoxy actuators were able to occur at physiological temperatures (36–40 °C), previously unreported in the literature. For the joule‐heated NiChrome–epoxy actuators surface temperatures remained under 40 °C during actuation at low operating voltages (&lt;2 V). Higher force and power output could be achieved in a repeatable fashion at higher driving voltages without loss of displacement, but also leading to higher surface temperatures. These materials and the actuation approach present an exciting opportunity to develop future implantable actuators to solve significant challenges related to quality of life and an ageing population.

Transformable Gaussian Reward Function for Socially Aware Navigation Using Deep Reinforcement Learning.

Robot navigation has transitioned from avoiding static obstacles to adopting socially aware navigation strategies for coexisting with humans. Consequently, socially aware navigation in dynamic, human-centric environments has gained prominence in the field of robotics. One of the methods for socially aware navigation, the reinforcement learning technique, has fostered its advancement. However, defining appropriate reward functions, particularly in congested environments, holds a significant challenge. These reward functions, crucial for guiding robot actions, necessitate intricate human-crafted design due to their complex nature and inability to be set automatically. The multitude of manually designed reward functions contains issues such as hyperparameter redundancy, imbalance, and inadequate representation of unique object characteristics. To address these challenges, we introduce a transformable Gaussian reward function (TGRF). The TGRF possesses two main features. First, it reduces the burden of tuning by utilizing a small number of hyperparameters that function independently. Second, it enables the application of various reward functions through its transformability. Consequently, it exhibits high performance and accelerated learning rates within the deep reinforcement learning (DRL) framework. We also validated the performance of TGRF through simulations and experiments.

Comparative Study of Mechanical Scaling Effects of Origami-Inspired Motion Generation Mechanisms with Multi-Degree Vertices

Origami exhibits the remarkable ability to transform into diverse shapes, including quadrilaterals, triangles, and more complex polygons. This unique property has inspired the integration of origami principles into engineering design, particularly in the development of foldable mechanisms. In the field of robotics, when combined with actuators, these foldable mechanisms are referred to as active origami. Origami-based mechanisms play a pivotal role as versatile end effectors or grippers, enabling them to accurately trace desired trajectories. The performance of these mechanisms heavily relies on their specific fold patterns. To shed light on their capabilities, this study focuses on five representative structures using spherical mechanisms: oriceps, Miura ori, MACIOR, and two hexagonal structures. To assess their potential, a comparative analysis is conducted, evaluating their kinematic and scaling performances. The analysis employs the “scaling factor” as a metric, which quantifies the mechanical advantage of these mechanisms. This metric aids in the selection of appropriate structures for various applications.

Neural network-based algorithm for door handle recognition using RGBD cameras

The ability to recognize and interact with a variety of doorknob designs is an important component on the path to true robot adaptability, allowing robotic systems to effectively interact with a variety of environments and objects The problem addressed in this paper is to develop and implement a method for recognizing the position of a door handle by a robot using data from an RGBD camera. To achieve this goal, we propose a revolutionary approach designed for autonomous robots that allows them to identify and manipulate door handles in different environments using data obtained from RGBD cameras. This was achieved by creating and annotating a complete dataset consisting of 5000 images of door handles from different angles, with the coordinates of the vertices of the bounding rectangles labeled. The architectural basis of the proposed approach is based on MobileNetV2, combined with a special decoder that optimally increases the resolution to 448 pixels. A new activation function specially designed for this neural network is implemented to ensure increased accuracy and efficiency of raw data processing. The most important achievement of this study is the model's ability to work in real-time, processing up to 16 images per second. This research paves the way for new advancements in the fields of robotics and computer vision, making a substantial contribution to the practical deployment of autonomous robots in a myriad of life's spheres.

Amplification of photothermally induced reversible actuation in non-woven fabrics compared to bulk films

The burgeoning field of soft robotics has witnessed a surge in interest, driven by the pursuit of creating precise machines with soft actuators capable of surpassing or aiding human manufacturing capabilities. This work explores light-responsive shape memory actuators derived from electrospun fibers, integrating a "push-pull" azo compound into a poly(ε-caprolactone) matrix. Driven by photothermal conversion, the resulting system exhibits reversible actuation under UV light, demonstrating rapid responses and superior performance compared to film counterparts. More specifically, the significant impact of morphology on both the photothermal behavior and the actuation performance is highlighted by comparing non-woven and bulk shape memory material. The temperature variation induced by UV light in the non-woven was notably affected by scattering effects, leading to the formation of temperature gradients throughout the material. Notably, the study establishes a unique stress-responsive range for fibrous actuators, demonstrating that their porous structure contributes to higher actuation magnitudes at lower stresses compared to conventional films. This innovation holds promise for applications in micro-robotics and biomedical fields, showcasing the potential of fibrous actuators in augmenting human-friendly robotics through their lightweight, flexible, and remotely actuated features.