Journal of Field Robotics最新文献

{"title":"A Machine Learning–Based Ergonomic Assessment of Wireless Hand Control System for Lower-Limb Disabled Tractor Operators and Abled Female Agricultural Workers","authors":"Smrutilipi Hota,&nbsp;V. K. Tewari","doi":"10.1002/rob.22458","DOIUrl":"https://doi.org/10.1002/rob.22458","url":null,"abstract":"<div>\u0000 \u0000 <p>Tractor being the most used power source for agricultural operations needs hand control (HC) and foot control (FC) to maneuver it. FCs restrict lower-limb disabled agricultural workers from participating in tractor operation, and high requirement of actuation forces to operate FCs may create overexertion and early fatigue to female agricultural workers. Therefore, a sensor-based HC system has been developed to assist them in tractor operation with minimal actuating force. This study focuses on ergonomic assessment of the HC system to assess the suitability for the abled and disabled agricultural workers, including physiological, psychophysical, and muscle fatigue parameters. Heart rate (HR) of abled male and female, and disabled male and female was observed in the range of 83–118, 85–117, 93–118, and 92–114 beats/min, respectively, during tractor operation. Energy expenditure rate (EER) during tractor operation with FCs (9.7–17.4 kJ/min) was observed higher than with the HC system (7.3–16.5 kJ/min). Body parts discomfort was observed highest for the right hand of all the subjects (4.9–5.3) and maximum overall discomfort was experienced by abled females during the operation with FCs (5.4) as they have to exert higher force. The root mean square (RMS) value of the electromyography signal obtained for extensor digitorum muscle was found to be higher for all the subjects and with both HC and FC (abled male, 17.37–40.43 µV; abled female, 14.76–45.29 µV; disabled male, 15.49–40.23 µV; disabled female, 30.32–54.29 µV) than other upper arm muscles middle deltoid, flexor carpi radialis, and brachioradialis. Muscle workload for all the selected muscles of all the subjects was observed within the recommended limit during the tractor operation with a developed HC system (&lt; 30%). Categorization of overall discomfort rating (ODR) of the subjects using HR, EER, and RMS through machine learning algorithms such as <i>k</i>-nearest neighbor (KNN), random forest classifier, and support vector machine predicted the ODR with accuracies in the range of 77%–83%. KNN algorithm was found to be most accurate with prediction accuracy of 83%. The developed HC system provides assistantship to the lower-limb disabled agricultural workers (1%–100% disability of lower limbs) and allows female workers to operate the tractor with minimal physical exertion.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 4","pages":"1344-1360"},"PeriodicalIF":4.2,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143950232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Model Reference-Based Neural Controller for Transmission Line Inspection Robot","authors":"Zehra Karagöz,&nbsp;Nazmi Ekren,&nbsp;Uğur Demir,&nbsp;Ahmet Fevzi Baba,&nbsp;Mustafa Şahin","doi":"10.1002/rob.22448","DOIUrl":"https://doi.org/10.1002/rob.22448","url":null,"abstract":"<p>The regular inspection of the power transmission lines is essential for the uninterrupted transmission of electrical energy to demand points. This quickly requires actions with economically, efficiently, and safely. Therefore, the transmission line inspection robots are inevitable solution as an alternative to existing line inspection methods. This study present design and control of a transmission line inspection robot (I-Robot). Since the I-Robot exhibits nonlinear behavior and has multiple inputs and multiple outputs, a model reference-based neural controller is determined to achieve nonlinear control. The robot design process consists of four stages which are kinematic modelling, dynamic modelling, actuator modelling and controller design. To meet inspection requirements, the conceptual design of the I-Robot is performed, and the kinematic model are calculated in terms of the transformation matrices. According to the design requirements and system constraints, the dynamic model of the I-Robot is created. To provide desired motions and trajectory tracking, the actuator models are determined. Then, the I-Robot is prototyped. According to the dynamics of joint, robot and constraints, the system identification is performed to create reference model. During the system identification, the logged data are used the train the reference model. Finally, the desired trajectory for the driving cycles is created by manual excitation of the I-Robot. During the manual excitation, the logged data are used to train the neural network (NN)-based controller. Eventually, the I-Robot is assessed under the test scenarios in term of the trajectory tracking performance as regression value and mean squared errors. According to the experiments, the neuron numbers and the training algorithm of the NN controller are determined. It was observed that the controller is quickly optimized with the adapting algorithm designed for the NN reference model. As a result, the performance of the model reference-based neural controller was determined as 99%.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 4","pages":"1314-1332"},"PeriodicalIF":4.2,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22448","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143950272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Utilizing Photovoltaic Solar Panels for Real-Time Localization and Speed Detection of Approaching Illuminated Objects in Humanoid Robots","authors":"Amir R. Ali,&nbsp;Abdelhameed Mubarak","doi":"10.1002/rob.22449","DOIUrl":"https://doi.org/10.1002/rob.22449","url":null,"abstract":"<div>\u0000 \u0000 <p>In the field of humanoid robotics, this paper showcases a promising method of integrating the photovoltaic (PV) solar panels into the “GUCnoid 1.0” humanoid robot model. Instead of the conventional power generation, solar cells are used to supply electrical energy to various sensors to create a system capable of real-time sensing and perception. The main focus of the study will be the use of PV panels as receptors that are capable of detecting the light, enabling an adaptive system which perceives environmental changes. The behavior of the PV cell is superbly studied when various light sources are approached or depart. They finally reveal unique patterns in the voltage output signal amplitude. Interestingly, these patterns figure out the same symmetric structure, which reflects on a vertical axis by their mirroring. Using this simplicity, the method involves using an artificial neural network that is able to distinguish the light sources coming towards the detector and the ones running away and the rate at which they approach/recede. Outdoor experiment was organized for verification of methods. GUCnoid 1.0— humanoid robot was placed in front of a moving vehicle with different speeds of approach. To be able to identify the vehicle's position and velocity, a PV sensing technique has to be applied. This innovative technology will have wide applications, with much attention paid to improving the speed of finding nearby objects or vehicles in the scenarios where quick detection is a serious life safety issue. Through the process of PV solar panels' smart sensing, we directly connect the areas of high-tech robotics and renewable energy. This discovery creates an opportunity for companies to build more responsive and flexible humanoid robots that can effectively collaborate with humans to achieve greater outcomes through more secure and efficient interactions between humans and robots.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 4","pages":"1298-1313"},"PeriodicalIF":4.2,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143950557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robot Grasping Detection Method Based on Keypoints","authors":"Song Yan,&nbsp;Lei Zhang","doi":"10.1002/rob.22447","DOIUrl":"https://doi.org/10.1002/rob.22447","url":null,"abstract":"<div>\u0000 \u0000 <p>This study introduces a novel keypoint-based grasp detection network, denoted as GKSCConv-Net, which operates on n-channel input images. The network architecture comprises three SCConv2D layers and three SCConvT2D layers. The SCConvT2D layers facilitate upsampling to maintain consistent dimensions between the output and input images. The resultant output consists of maps indicating left grasp points, right grasp points, and grasp center keypoints. The accuracy of predictions is enhanced through the incorporation of the keypoint refinement module and feature fusion module. To validate the model's generalization and applicability, comprehensive training, testing, and evaluation are conducted on diverse data sets, including the Cornell data set, Jacquard data set, and others representing real-world scenarios. Furthermore, ablation experiments are employed to substantiate the efficacy of the spatial reconstruction unit (SRU) and channel reconstruction unit (CRU) within the SCConv, exploring their impact on grasp keypoint detection outcomes. Real robotic grasping experiments ultimately affirm the model's outstanding performance in practical settings.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 4","pages":"1271-1286"},"PeriodicalIF":4.2,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143950180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"In-Pipe Maintenance Robot Using Spray-In-Place Pipe Technique for Long-Distance and Complex Pipe Environment","authors":"Colin Pak Yu Chan,&nbsp;Zijia Qu,&nbsp;Kin Hei Shiu,&nbsp;Chun Ho So,&nbsp;Keng Huat Koh,&nbsp;Musthafa Farhan,&nbsp;Chun Yiu Ho,&nbsp;Tsz Hei Wong,&nbsp;King Wai Chiu Lai","doi":"10.1002/rob.22440","DOIUrl":"https://doi.org/10.1002/rob.22440","url":null,"abstract":"<div>\u0000 \u0000 <p>Conventional pipe rehabilitation technologies are not the most sustainable solution for the utility industry because of various drawbacks, such as time consumption, disturbance to operations, society, and traffic, and the production of waste material. However, aged underground metal pipes are affected by natural forces. Trenchless rehabilitation technologies have been introduced for the treatment and renovation of aged pipes to ensure that utilities are safe and durable from an economic perspective. This paper proposes a portable and automatic robotic solution for a trenchless spray-in-place pipe approach for small underground pipelines. This approach shortens the duration of the rehabilitation operation from approximately a week to &lt; 5 h. The robot delivered and monitored a protective well-mixed urethane coating with plural components accurately using rotary mixing and spraying with a low-pressure and safer configuration (&lt; 0.8 MPa). The robot exhibited superior capacities in complicated pipe environments for turning into 90° elbows and 6-in. (150 mm), 8-in. (200 mm), and 10-in. (250 mm) pipelines. An automated robot was deployed and rehabilitated at various underground and on-ground pipe sites. The spray performance was validated using tensile tests. This robot can be applied to any pipeline system and can be developed for other in-pipe robotic construction and renovation approaches.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 4","pages":"1226-1243"},"PeriodicalIF":4.2,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143950093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-Time Heading Correction Control for Mars Rovers Considering Travel Terrain Differences Between Two Sides of the Suspension","authors":"Zhicheng Jia,&nbsp;Jingfu Jin,&nbsp;Xinju Dong,&nbsp;Meng Zou,&nbsp;Lianbin He","doi":"10.1002/rob.22446","DOIUrl":"https://doi.org/10.1002/rob.22446","url":null,"abstract":"<div>\u0000 \u0000 <p>Existing Mars rovers usually adopt a split suspension with a rocker-bogie on each side of the body to improve terrain adaptability. However, when exploring the Martian surface with complex terrain distribution, differential traveling conditions of the wheel sets on both sides can cause the Mars rover to deviate from its desired heading. This paper presents a coordinated wheel speed control method for Mars rovers that combines fuzzy control with active disturbance rejection control. This method can realize real-time heading correction while compensating for the effects of differences in terrain shape and terrain type on both sides. Another advantage of the proposed method is that the control system does not rely on the motion model of the Mars rover's suspension and avoids real-time acquisition of suspension attitude data, which improves the algorithm efficiency and portability. Finally, a series of experimental tests of multiterrain travel were conducted on a six-wheeled Mars rover prototype deploying the control system. The experimental results show that the control system can effectively guarantee that the Mars rover tracks the desired heading while traveling, and can obtain beneficial effects in reducing the internal force between the wheels and facing some special driving scenes.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 4","pages":"1209-1225"},"PeriodicalIF":4.2,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143949799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Active Sensing Strategy: Multi-Modal, Multi-Robot Source Localization and Mapping in Real-World Settings With Fixed One-Way Switching","authors":"Vu Phi Tran,&nbsp;Asanka G. Perera,&nbsp;Matthew A. Garratt,&nbsp;Kathryn Kasmarik,&nbsp;Sreenatha G. Anavatti","doi":"10.1002/rob.22441","DOIUrl":"https://doi.org/10.1002/rob.22441","url":null,"abstract":"<p>This paper introduces a state-machine model designed for a multi-modal, multi-robot environmental sensing algorithm tailored to dynamic real-world settings. The multi-modal algorithm uniquely combines two distinct exploration strategies for gas source localization and mapping tasks: (1) an initial exploration phase using multi-robot coverage path planning with variable formations, providing early gas field indication; and (2) a subsequent active sensing phase employing multi-robot swarms for precise field estimation. The state machine provides the logic for the transition between these two sensing algorithms. In the exploration phase, a coverage path is generated, maximizing the visited area while measuring gas concentration and estimating the initial gas field at pre-defined sample times. Subsequently, in the active sensing phase, mobile robots moving in a swarm collaborate to select the next measurement point by broadcasting potential positions and reward values, ensuring coordinated and efficient sensing for a multi-robot swarm system. System validation involves hardware-in-the-loop experiments and real-time experiments with a radio source emulating a gas field. The proposed approach is rigorously benchmarked against state-of-the-art single-mode active sensing and gas source localization techniques. The comprehensive evaluation highlights the multi-modal switching approach's capacity to expedite convergence, adeptly navigate obstacles in dynamic environments, and significantly enhance the accuracy of gas source location predictions. These findings highlight the effectiveness of our approach, showing significant improvements: a 43% reduction in turnaround time, a 50% increase in estimation accuracy, and enhanced robustness of multi-robot environmental sensing in cluttered scenarios without collisions. These advancements surpass the performance of conventional active sensing strategies, the partial differential equation model, and geometrical localization approaches, underscoring the efficacy of our method.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 4","pages":"1166-1190"},"PeriodicalIF":4.2,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22441","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143949877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Toward a Track-Fin Hybrid Driven Bionic Amphibious Robot: Design, Development, and Experiments","authors":"Minghai Xia,&nbsp;Qian Yin,&nbsp;Qunwei Zhu,&nbsp;Haisen Zeng,&nbsp;Zhongyue Lu,&nbsp;Zirong Luo","doi":"10.1002/rob.22443","DOIUrl":"https://doi.org/10.1002/rob.22443","url":null,"abstract":"<div>\u0000 \u0000 <p>Amphibious robots offer promising applications in field scenarios such as search and rescue, exploration and reconnaissance, and environment monitoring. However, achieving high locomotion performance in terrestrial, aquatic, and soft muddy transition areas remains challenging. This study presents a novel amphibious robot based on the hybrid drive of tracks and bionic fins. The robot is driven by a pair of tracks on land and by a pair of undulating fins underwater, without the need for switching operating modes due to the simultaneous drive of the two components. The structure design is introduced and the united operating strategies are derived for propulsion in multiple environments propulsion. A land–water united controller for the heading angle and track/fin frequency is designed based on a mathematical model. In field experiments, the robot achieved the maximum linear velocities of 2 m/s on land and 0.51 m/s underwater, with maximum yaw rates of 225 <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 \u0000 <mrow>\u0000 <mmultiscripts>\u0000 <mo>/</mo>\u0000 <none></none>\u0000 <none></none>\u0000 <mprescripts></mprescripts>\u0000 <none></none>\u0000 \u0000 <mo>∘</mo>\u0000 </mmultiscripts>\u0000 \u0000 <mi>s</mi>\u0000 </mrow>\u0000 </mrow>\u0000 </semantics></math> and 100 <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 \u0000 <mrow>\u0000 <mmultiscripts>\u0000 <mo>/</mo>\u0000 <none></none>\u0000 <none></none>\u0000 <mprescripts></mprescripts>\u0000 <none></none>\u0000 \u0000 <mo>∘</mo>\u0000 </mmultiscripts>\u0000 \u0000 <mi>s</mi>\u0000 </mrow>\u0000 </mrow>\u0000 </semantics></math>, respectively. The robot could transition seamlessly between land and water in less than 2 s. The closed-loop control experiments demonstrated that the robot could quickly follow the desired angle with minimal error in both media using the same controller and parameters. The proposed simultaneous drive method enhances the multi-terrain motion capacity and cross-medium performance while reducing control complexity of amphibious robot, providing a new perspective for the development of self-adaptive and high-performance amphibious robots for practical application.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 4","pages":"1143-1165"},"PeriodicalIF":4.2,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143950271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effectiveness of an Expendable Unmanned Ground Vehicle Stalling a Mechanized Infantry Company's Primary Combat Units—A Virtual Simulation Experiment","authors":"Christian A. Andersson,&nbsp;Kasper Halme,&nbsp;Mia Laine,&nbsp;Ville Hulkko,&nbsp;Kai Virtanen","doi":"10.1002/rob.22442","DOIUrl":"https://doi.org/10.1002/rob.22442","url":null,"abstract":"<p>Technological advancements have spurred the development of unmanned ground vehicles (UGVs) and their innovative military applications and strategies. Such applications include expendable UGVs. However, public research concerning expendable military UGVs remains sparse. Particularly, the unclassified literature does not contain studies regarding their capabilities and effectiveness in combat. This study introduces a new low-cost expendable UGV called Laykka. Moreover, the study presents a virtual simulation experiment to evaluate Laykkas' operational capabilities and their impact on advancing mechanized infantry units. The experiment involved armored reserve officer students assuming the roles of infantry troops forming an attacking opposing force while staff officers controlled simulated infantry troops operating the UGVs. A total of 16 battle simulations were fought. The simulated UGVs operated by a single soldier were able to stall the advancement of the mechanized infantry company's primary combat units three times out of four and a smaller force 11 out of 12 times. The best stalling effect was observed using a mix of UGVs with different module types. These modules allowed reconnaissance, loitering mine, and anti-tank operations. The simulation experiment revealed that the UGV was an effective defensive tool due to its self-destructive capability, causing marked battle damage, disruption, and confusion to the opposing forces.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 4","pages":"1125-1142"},"PeriodicalIF":4.2,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22442","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143950224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Locomotion for Insect-Scale Robots With Bionic Strategies: A Review","authors":"Wenjing Zou,&nbsp;Erqi Ma,&nbsp;Haolin Chen,&nbsp;Feng Lin,&nbsp;Ziting Xiao,&nbsp;Zezhan Zhang,&nbsp;Jing Jiang,&nbsp;Yi Niu,&nbsp;Peifeng Yu,&nbsp;Chao Wang","doi":"10.1002/rob.22427","DOIUrl":"https://doi.org/10.1002/rob.22427","url":null,"abstract":"<div>\u0000 \u0000 <p>Insect-scale robots possess the advantageous traits of small size, lightweight, and high flexibility. These features make them suitable for complex, narrow, or higher-than-the-ground environments, allowing these insect-scale robots to become highly sought-after research topics. However, the miniaturization of robots has brought challenges to improving their environmental adaptability, such as climbing and obstacle-crossing abilities. Mainstream strategies inspired by natural creatures to address these challenges can be classified into two types: adhesion for climbing robots and multi-motion modes for obstacle-crossing robots. Adhesion is preferred for occasions requiring climbing slopes, walls, or ceilings. In contrast, multi-motion modes are suitable for occasions with limited obstacle heights or complex terrains to enable miniaturization and cable-free operation. This paper summarizes the current research on environment-adaptable insect-scale robots (EAISRs) with adhesion or multi-motion modes. Then, the paper discusses the advantages, disadvantages, and application scenarios of EAISRs, including climbing robots with different adhesion strategies and obstacle-crossing robots with various driving methods in detail. Finally, this paper proposes the future challenges and possible solutions for EAISRs, providing ideas for future interactions between insect-scale robots and the environment.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 5","pages":"1586-1616"},"PeriodicalIF":4.2,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}