Pub Date : 2024-04-09DOI: 10.3390/robotics13040061
Ana Iglesias, Raquel Viciana, J. Pérez-Lorenzo, K. Ting, Alberto J. Tudela, Rebeca Marfil, Malak Qbilat, Antonio Hurtado, Antonio Jerez, J. P. Bandera
The use of new assistive technologies in general, and Socially Assistive Robots (SARs) in particular, is becoming increasingly common for supporting people’s health and well-being. However, it still faces many issues regarding long-term adherence, acceptability and utility. Most of these issues are due to design processes that insufficiently take into account the needs, preferences and values of intended users. Other issues are related to the currently very limited amount of long-term evaluations, performed in real-world settings, for SARs. This study presents the results of two regional projects that consider as a starting hypothesis that the assessment in controlled environments and/or with short exposures may not be enough in the design of an SAR deployed in a retirement home and the necessity of designing for and with users. Thus, the proposed methodology has focused on use-cases definitions that follow a human-centred and participatory design approach. The main goals have been facilitating system acceptance and attachment by involving stakeholders in the robots design and evaluation, overcoming usage barriers and considering user’s needs integration. The implementation of the first use-case deployed and the two-phase pilot test performed in a retirement home are presented. In particular, a detailed description of the interface redesign process based on improving a basic prototype with users’ feedback and recommendations is presented, together with the main results of a formal evaluation that has highlighted the impact of changes and improvements addressed in the first redesign loop of the system.
新辅助技术，特别是社会辅助机器人（SAR）的使用越来越普遍，为人们的健康和福祉提供支持。然而，在长期使用、可接受性和实用性方面仍面临许多问题。这些问题大多是由于设计过程没有充分考虑到预期用户的需求、偏好和价值观造成的。其他问题则与目前在真实世界环境中对 SAR 进行的长期评估数量非常有限有关。本研究介绍了两个地区性项目的成果，这两个项目的出发假设是，在受控环境和/或短时间暴露下进行的评估可能不足以设计出部署在养老院的合成孔径雷达，而且有必要为用户并与用户一起进行设计。因此，建议的方法侧重于使用案例的定义，遵循以人为本和参与式的设计方法。主要目标是通过让利益相关者参与机器人的设计和评估、克服使用障碍和考虑用户的需求整合，促进系统的接受和附着。本报告介绍了第一个使用案例的实施情况，以及在一家养老院进行的两个阶段的试点测试。特别是，详细介绍了根据用户反馈和建议改进基本原型的界面重新设计过程，以及正式评估的主要结果，该评估强调了系统第一次重新设计循环中的更改和改进所产生的影响。
{"title":"The Town Crier: A Use-Case Design and Implementation for a Socially Assistive Robot in Retirement Homes","authors":"Ana Iglesias, Raquel Viciana, J. Pérez-Lorenzo, K. Ting, Alberto J. Tudela, Rebeca Marfil, Malak Qbilat, Antonio Hurtado, Antonio Jerez, J. P. Bandera","doi":"10.3390/robotics13040061","DOIUrl":"https://doi.org/10.3390/robotics13040061","url":null,"abstract":"The use of new assistive technologies in general, and Socially Assistive Robots (SARs) in particular, is becoming increasingly common for supporting people’s health and well-being. However, it still faces many issues regarding long-term adherence, acceptability and utility. Most of these issues are due to design processes that insufficiently take into account the needs, preferences and values of intended users. Other issues are related to the currently very limited amount of long-term evaluations, performed in real-world settings, for SARs. This study presents the results of two regional projects that consider as a starting hypothesis that the assessment in controlled environments and/or with short exposures may not be enough in the design of an SAR deployed in a retirement home and the necessity of designing for and with users. Thus, the proposed methodology has focused on use-cases definitions that follow a human-centred and participatory design approach. The main goals have been facilitating system acceptance and attachment by involving stakeholders in the robots design and evaluation, overcoming usage barriers and considering user’s needs integration. The implementation of the first use-case deployed and the two-phase pilot test performed in a retirement home are presented. In particular, a detailed description of the interface redesign process based on improving a basic prototype with users’ feedback and recommendations is presented, together with the main results of a formal evaluation that has highlighted the impact of changes and improvements addressed in the first redesign loop of the system.","PeriodicalId":506759,"journal":{"name":"Robotics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140725446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-06DOI: 10.3390/robotics13040060
Ali KhalilianMotamed Bonab, D. Chiaradia, A. Frisoli, D. Leonardis
The light weight and compliance of exosuits are valuable benefits not present rigid exoskeleton devices, yet these intriguing features make it challenging to properly model and simulate their interaction with the musculoskeletal system. Tendon-driven exosuits adopt an electrical motor combined with pulleys and cable transmission in the actuation stage. An important aspect of the design of these systems for the load transfer efficacy and comfort of the user is the anchor point positioning. In this paper, we propose a framework, whose first purpose is as a design methodology for the synthesis of an exosuit device, achieved by optimizing the anchor point location. The optimization procedure finds the best 3D position of the anchor points based on the interaction forces between the exosuit and the upper arm. The computation of the forces is based on the combination of a mathematical model of a wrist–elbow exosuit and a dynamic model of the upper arm. Its second purpose is the simulation of the kinematic and physiological effects of the interaction between the arm, the exosuit, and the complex upper limb musculoskeletal system. It offers insights into muscular and exoskeleton loading during operation. The presented experiments involve the development and validation of personalized musculoskeletal models, with kinematic, anthropometric, and electromyographic data measured in a load-lifting task. Simulation of the exosuit operation—coupled with the musculoskeletal model—showed the efficacy of the suit in assisting the wrist and elbow muscles and provided interesting highlights about the impact of the assistance on shoulder muscles. Finally, we provide a possible design of an elbow and wrist exosuit based on the optimized results.
{"title":"A Framework for Modeling, Optimization, and Musculoskeletal Simulation of an Elbow–Wrist Exosuit","authors":"Ali KhalilianMotamed Bonab, D. Chiaradia, A. Frisoli, D. Leonardis","doi":"10.3390/robotics13040060","DOIUrl":"https://doi.org/10.3390/robotics13040060","url":null,"abstract":"The light weight and compliance of exosuits are valuable benefits not present rigid exoskeleton devices, yet these intriguing features make it challenging to properly model and simulate their interaction with the musculoskeletal system. Tendon-driven exosuits adopt an electrical motor combined with pulleys and cable transmission in the actuation stage. An important aspect of the design of these systems for the load transfer efficacy and comfort of the user is the anchor point positioning. In this paper, we propose a framework, whose first purpose is as a design methodology for the synthesis of an exosuit device, achieved by optimizing the anchor point location. The optimization procedure finds the best 3D position of the anchor points based on the interaction forces between the exosuit and the upper arm. The computation of the forces is based on the combination of a mathematical model of a wrist–elbow exosuit and a dynamic model of the upper arm. Its second purpose is the simulation of the kinematic and physiological effects of the interaction between the arm, the exosuit, and the complex upper limb musculoskeletal system. It offers insights into muscular and exoskeleton loading during operation. The presented experiments involve the development and validation of personalized musculoskeletal models, with kinematic, anthropometric, and electromyographic data measured in a load-lifting task. Simulation of the exosuit operation—coupled with the musculoskeletal model—showed the efficacy of the suit in assisting the wrist and elbow muscles and provided interesting highlights about the impact of the assistance on shoulder muscles. Finally, we provide a possible design of an elbow and wrist exosuit based on the optimized results.","PeriodicalId":506759,"journal":{"name":"Robotics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140734470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-01DOI: 10.3390/robotics13040058
E. Stefanini, G. Lentini, G. Grioli, M. G. Catalano, A. Bicchi
The objective of this paper is to propose a framework for a robot to learn multiple Sensory-Motor Contingencies from human demonstrations and reproduce them. Sensory-Motor Contingencies are a concept that describes intelligent behavior of animals and humans in relation to their environment. They have been used to design control and planning algorithms for robots capable of interacting and adapting autonomously. However, enabling a robot to autonomously develop Sensory-Motor Contingencies is challenging due to the complexity of action and perception signals. This framework leverages tools from Learning from Demonstrations to have the robot memorize various sensory phases and corresponding motor actions through an attention mechanism. This generates a metric in the perception space, used by the robot to determine which sensory-motor memory is contingent to the current context. The robot generalizes the memorized actions to adapt them to the present perception. This process creates a discrete lattice of continuous Sensory-Motor Contingencies that can control a robot in loco-manipulation tasks. Experiments on a 7-dof collaborative robotic arm with a gripper, and on a mobile manipulator demonstrate the functionality and versatility of the framework.
{"title":"Exploring Saliency for Learning Sensory-Motor Contingencies in Loco-Manipulation Tasks","authors":"E. Stefanini, G. Lentini, G. Grioli, M. G. Catalano, A. Bicchi","doi":"10.3390/robotics13040058","DOIUrl":"https://doi.org/10.3390/robotics13040058","url":null,"abstract":"The objective of this paper is to propose a framework for a robot to learn multiple Sensory-Motor Contingencies from human demonstrations and reproduce them. Sensory-Motor Contingencies are a concept that describes intelligent behavior of animals and humans in relation to their environment. They have been used to design control and planning algorithms for robots capable of interacting and adapting autonomously. However, enabling a robot to autonomously develop Sensory-Motor Contingencies is challenging due to the complexity of action and perception signals. This framework leverages tools from Learning from Demonstrations to have the robot memorize various sensory phases and corresponding motor actions through an attention mechanism. This generates a metric in the perception space, used by the robot to determine which sensory-motor memory is contingent to the current context. The robot generalizes the memorized actions to adapt them to the present perception. This process creates a discrete lattice of continuous Sensory-Motor Contingencies that can control a robot in loco-manipulation tasks. Experiments on a 7-dof collaborative robotic arm with a gripper, and on a mobile manipulator demonstrate the functionality and versatility of the framework.","PeriodicalId":506759,"journal":{"name":"Robotics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140786688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-01DOI: 10.3390/robotics13040059
C. Peers, Chengxu Zhou
Bimanual manipulation is valuable for its potential to provide robots in the field with increased capabilities when interacting with environments, as well as broadening the number of possible manipulation actions available. However, for a robot to perform bimanual manipulation, the system must have a capable control framework to localise and generate trajectories and commands for each sub-system to allow for successful cooperative manipulation as well as sufficient control over each individual sub-system. The proposed method suggests using multiple mobile manipulator platforms coupled through the use of an optical tracking localisation method to act as a single bimanual manipulation system. The framework’s performance relies on the accuracy of the localisation. As commands are primarily high-level, it is possible to use any number and combination of mobile manipulators and fixed manipulators within this framework. We demonstrate the functionality of this system through tests in a Pybullet simulation environment using two different omnidirectional mobile manipulators, as well a real-life experiment using two quadrupedal manipulators.
{"title":"Bimanual Telemanipulation Framework Utilising Multiple Optically Localised Cooperative Mobile Manipulators","authors":"C. Peers, Chengxu Zhou","doi":"10.3390/robotics13040059","DOIUrl":"https://doi.org/10.3390/robotics13040059","url":null,"abstract":"Bimanual manipulation is valuable for its potential to provide robots in the field with increased capabilities when interacting with environments, as well as broadening the number of possible manipulation actions available. However, for a robot to perform bimanual manipulation, the system must have a capable control framework to localise and generate trajectories and commands for each sub-system to allow for successful cooperative manipulation as well as sufficient control over each individual sub-system. The proposed method suggests using multiple mobile manipulator platforms coupled through the use of an optical tracking localisation method to act as a single bimanual manipulation system. The framework’s performance relies on the accuracy of the localisation. As commands are primarily high-level, it is possible to use any number and combination of mobile manipulators and fixed manipulators within this framework. We demonstrate the functionality of this system through tests in a Pybullet simulation environment using two different omnidirectional mobile manipulators, as well a real-life experiment using two quadrupedal manipulators.","PeriodicalId":506759,"journal":{"name":"Robotics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140757816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-05DOI: 10.3390/robotics13030044
Szilvia Kóra, Adrienn Bíró, Nándor Prontvai, Mónika Androsics, István Drotár, Péter Prukner, T. Haidegger, Klaudia Széphelyi, J. Tollár
Medical robotics nowadays can prevent, treat, or alleviate numerous severe conditions, including the dire consequences of stroke. Our objective was to determine the effect of employing a robotic soft exoskeleton in therapy on the development of the early mobilization, gait, and coordination in stroke patients. The ReStore™ Soft Exo-Suit, a wearable exosuit developed by a leading company with exoskeleton technology, was utilized. It is a powered, lightweight device intended for use in stroke rehabilitation for people with lower limb disability. We performed a randomized clinical intervention, using a before–after trial design in a university hospital setting. A total of 48 patients with a history of stroke were included, of whom 39 were randomized and 30 completed the study. Interventions: Barthel Index and modified Rankin scale (mRS) patients were randomly assigned to a non-physical intervention control (n = 9 of 39 completed, 30 withdrew before baseline testing), or to a high-intensity agility program (15 sessions, 5 weeks, n = 30 completed). The main focus of assessment was on the Modified Rankin Scale. Additionally, we evaluated secondary factors including daily life functionality, five dimensions of health-related quality of life, the Beck depression inventory, the 6 min walk test (6MWT), the Berg Balance Scale (BBS), and static balance (center of pressure). The Robot-Assisted Gait Therapy (ROB/RAGT) program led to significant improvements across various measures, including a 37% improvement in Barthel Index scores, a 56% increase in 10 m walking speed, and a 68% improvement in 6 min walking distance, as well as notable enhancements in balance and stability. Additionally, the intervention group demonstrated significant gains in all these aspects compared to the control group. In conclusion, the use of robotic therapy can be beneficial in stroke rehabilitation. These devices support the restoration and improvement of movement in various ways and contribute to restoring balance and stability.
{"title":"Investigation of the Effectiveness of the Robotic ReStore Soft Exoskeleton in the Development of Early Mobilization, Walking, and Coordination of Stroke Patients: A Randomized Clinical Trial","authors":"Szilvia Kóra, Adrienn Bíró, Nándor Prontvai, Mónika Androsics, István Drotár, Péter Prukner, T. Haidegger, Klaudia Széphelyi, J. Tollár","doi":"10.3390/robotics13030044","DOIUrl":"https://doi.org/10.3390/robotics13030044","url":null,"abstract":"Medical robotics nowadays can prevent, treat, or alleviate numerous severe conditions, including the dire consequences of stroke. Our objective was to determine the effect of employing a robotic soft exoskeleton in therapy on the development of the early mobilization, gait, and coordination in stroke patients. The ReStore™ Soft Exo-Suit, a wearable exosuit developed by a leading company with exoskeleton technology, was utilized. It is a powered, lightweight device intended for use in stroke rehabilitation for people with lower limb disability. We performed a randomized clinical intervention, using a before–after trial design in a university hospital setting. A total of 48 patients with a history of stroke were included, of whom 39 were randomized and 30 completed the study. Interventions: Barthel Index and modified Rankin scale (mRS) patients were randomly assigned to a non-physical intervention control (n = 9 of 39 completed, 30 withdrew before baseline testing), or to a high-intensity agility program (15 sessions, 5 weeks, n = 30 completed). The main focus of assessment was on the Modified Rankin Scale. Additionally, we evaluated secondary factors including daily life functionality, five dimensions of health-related quality of life, the Beck depression inventory, the 6 min walk test (6MWT), the Berg Balance Scale (BBS), and static balance (center of pressure). The Robot-Assisted Gait Therapy (ROB/RAGT) program led to significant improvements across various measures, including a 37% improvement in Barthel Index scores, a 56% increase in 10 m walking speed, and a 68% improvement in 6 min walking distance, as well as notable enhancements in balance and stability. Additionally, the intervention group demonstrated significant gains in all these aspects compared to the control group. In conclusion, the use of robotic therapy can be beneficial in stroke rehabilitation. These devices support the restoration and improvement of movement in various ways and contribute to restoring balance and stability.","PeriodicalId":506759,"journal":{"name":"Robotics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140079408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.3390/robotics13030041
Hamada Esmaiel, Guolin Zhao, Zeyad A. H. Qasem, Jie Qi, Haixin Sun
This paper proposes a double-layer structure RRT* algorithm based on objective bias called DOB-RRT*. The algorithm adopts an initial path with an online optimization structure for motion planning. The first layer of RRT* introduces a feedback-based objective bias strategy with segment forward pruning processing to quickly obtain a smooth initial path. The second layer of RRT* uses the heuristics of the initial tree structure to optimize the path by using reverse maintenance strategies. Compared with conventional RRT and RRT* algorithms, the proposed algorithm can obtain the initial path with high quality, and it can quickly converge to the progressive optimal path during the optimization process. The performance of the proposed algorithm is effectively evaluated and tested in real experiments on an actual wheeled robotic vehicle running ROS Kinetic in a real environment.
{"title":"Double-Layer RRT* Objective Bias Anytime Motion Planning Algorithm","authors":"Hamada Esmaiel, Guolin Zhao, Zeyad A. H. Qasem, Jie Qi, Haixin Sun","doi":"10.3390/robotics13030041","DOIUrl":"https://doi.org/10.3390/robotics13030041","url":null,"abstract":"This paper proposes a double-layer structure RRT* algorithm based on objective bias called DOB-RRT*. The algorithm adopts an initial path with an online optimization structure for motion planning. The first layer of RRT* introduces a feedback-based objective bias strategy with segment forward pruning processing to quickly obtain a smooth initial path. The second layer of RRT* uses the heuristics of the initial tree structure to optimize the path by using reverse maintenance strategies. Compared with conventional RRT and RRT* algorithms, the proposed algorithm can obtain the initial path with high quality, and it can quickly converge to the progressive optimal path during the optimization process. The performance of the proposed algorithm is effectively evaluated and tested in real experiments on an actual wheeled robotic vehicle running ROS Kinetic in a real environment.","PeriodicalId":506759,"journal":{"name":"Robotics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140089787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-10DOI: 10.3390/robotics13010013
Tianze Xu, D. Myszka, Andrew P. Murray
This paper presents a planar four-bar approximate motion synthesis technique that uses only pole locations. Synthesis for rigid-body guidance determines the linkage dimensions that guide a body in a desired manner. The desired motion is specified with task positions including a location and orientation angle. Approximation motion synthesis is necessary when an exact match to the task positions cannot be obtained. A linkage that achieves the task positions as closely as possible becomes desired. Structural error refers to the deviations between the task positions and the linkage’s generated positions. A challenge in approximate motion synthesis is that structural error involves metrics that include location and orientation. A best-fit solution is not evident because the structural error is based on an objective function that combines the location and orientation. Such solutions lack bi-invariance because a change in reference for the motion changes the values of the metric. This work uses only displacement poles, described solely by their coordinates, as they sufficiently characterize the relative task positions. The optimization seeks to minimize the distance between the poles of the task positions and the poles of the generated positions. The use of poles results in a bi-invariant statement of the problem.
{"title":"A Bi-Invariant Approach to Approximate Motion Synthesis of Planar Four-Bar Linkage","authors":"Tianze Xu, D. Myszka, Andrew P. Murray","doi":"10.3390/robotics13010013","DOIUrl":"https://doi.org/10.3390/robotics13010013","url":null,"abstract":"This paper presents a planar four-bar approximate motion synthesis technique that uses only pole locations. Synthesis for rigid-body guidance determines the linkage dimensions that guide a body in a desired manner. The desired motion is specified with task positions including a location and orientation angle. Approximation motion synthesis is necessary when an exact match to the task positions cannot be obtained. A linkage that achieves the task positions as closely as possible becomes desired. Structural error refers to the deviations between the task positions and the linkage’s generated positions. A challenge in approximate motion synthesis is that structural error involves metrics that include location and orientation. A best-fit solution is not evident because the structural error is based on an objective function that combines the location and orientation. Such solutions lack bi-invariance because a change in reference for the motion changes the values of the metric. This work uses only displacement poles, described solely by their coordinates, as they sufficiently characterize the relative task positions. The optimization seeks to minimize the distance between the poles of the task positions and the poles of the generated positions. The use of poles results in a bi-invariant statement of the problem.","PeriodicalId":506759,"journal":{"name":"Robotics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139439358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-09DOI: 10.3390/robotics13010012
M. Rybczak, Natalia Popowniak, A. Lazarowska
Machine learning (ML) is a branch of artificial intelligence that has been developing at a dynamic pace in recent years. ML is also linked with Big Data, which are huge datasets that need special tools and approaches to process them. ML algorithms make use of data to learn how to perform specific tasks or make appropriate decisions. This paper presents a comprehensive survey of recent ML approaches that have been applied to the task of mobile robot control, and they are divided into the following: supervised learning, unsupervised learning, and reinforcement learning. The distinction of ML methods applied to wheeled mobile robots and to walking robots is also presented in the paper. The strengths and weaknesses of the compared methods are formulated, and future prospects are proposed. The results of the carried out literature review enable one to state the ML methods that have been applied to different tasks, such as the following: position estimation, environment mapping, SLAM, terrain classification, obstacle avoidance, path following, learning to walk, and multirobot coordination. The survey allowed us to associate the most commonly used ML algorithms with mobile robotic tasks. There still exist many open questions and challenges such as the following: complex ML algorithms and limited computational resources on board a mobile robot; decision making and motion control in real time; the adaptability of the algorithms to changing environments; the acquisition of large volumes of valuable data; and the assurance of safety and reliability of a robot’s operation. The development of ML algorithms for nature-inspired walking robots also seems to be a challenging research issue as there exists a very limited amount of such solutions in the recent literature.
机器学习（ML）是人工智能的一个分支，近年来发展迅猛。机器学习也与大数据有关，大数据是需要特殊工具和方法来处理的巨大数据集。ML 算法利用数据来学习如何执行特定任务或做出适当决策。本文对最近应用于移动机器人控制任务的 ML 方法进行了全面调查，这些方法分为以下几种：监督学习、无监督学习和强化学习。文中还介绍了应用于轮式移动机器人和步行机器人的 ML 方法的区别。文中阐述了比较方法的优缺点，并提出了未来展望。根据文献综述的结果，我们可以指出应用于不同任务的 ML 方法，例如：位置估计、环境映射、SLAM、地形分类、避障、路径跟踪、步行学习和多机器人协调。通过调查，我们将最常用的 ML 算法与移动机器人任务联系起来。目前仍有许多悬而未决的问题和挑战，例如：移动机器人上复杂的 ML 算法和有限的计算资源；实时决策和运动控制；算法对不断变化的环境的适应性；获取大量有价值的数据；以及确保机器人运行的安全性和可靠性。为受自然启发的行走机器人开发 ML 算法似乎也是一个具有挑战性的研究课题，因为近期文献中此类解决方案的数量非常有限。
{"title":"A Survey of Machine Learning Approaches for Mobile Robot Control","authors":"M. Rybczak, Natalia Popowniak, A. Lazarowska","doi":"10.3390/robotics13010012","DOIUrl":"https://doi.org/10.3390/robotics13010012","url":null,"abstract":"Machine learning (ML) is a branch of artificial intelligence that has been developing at a dynamic pace in recent years. ML is also linked with Big Data, which are huge datasets that need special tools and approaches to process them. ML algorithms make use of data to learn how to perform specific tasks or make appropriate decisions. This paper presents a comprehensive survey of recent ML approaches that have been applied to the task of mobile robot control, and they are divided into the following: supervised learning, unsupervised learning, and reinforcement learning. The distinction of ML methods applied to wheeled mobile robots and to walking robots is also presented in the paper. The strengths and weaknesses of the compared methods are formulated, and future prospects are proposed. The results of the carried out literature review enable one to state the ML methods that have been applied to different tasks, such as the following: position estimation, environment mapping, SLAM, terrain classification, obstacle avoidance, path following, learning to walk, and multirobot coordination. The survey allowed us to associate the most commonly used ML algorithms with mobile robotic tasks. There still exist many open questions and challenges such as the following: complex ML algorithms and limited computational resources on board a mobile robot; decision making and motion control in real time; the adaptability of the algorithms to changing environments; the acquisition of large volumes of valuable data; and the assurance of safety and reliability of a robot’s operation. The development of ML algorithms for nature-inspired walking robots also seems to be a challenging research issue as there exists a very limited amount of such solutions in the recent literature.","PeriodicalId":506759,"journal":{"name":"Robotics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139441855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-03DOI: 10.3390/robotics13010011
Thiago Sá de Paiva, R. S. Gonçalves, Giuseppe Carbone
This study aims to provide a comprehensive critical review of the existing body of evidence pertaining to gait rehabilitation. It also seeks to introduce a systematic approach for the development of innovative design solutions in this domain. The field of gait rehabilitation has witnessed a surge in the development of novel robotic devices. This trend has emerged in response to limitations observed in most commercial solutions, particularly regarding their high costs. Consequently, there is a growing need to explore more cost-effective alternatives and create opportunities for greater accessibility. Within the realm of cost-effective options, linkage-based gait trainers have emerged as viable alternatives, prompting a thorough examination of this category, which is carried out in this work. Notably, there is a wide heterogeneity in research approaches and presentation methods. This divergence has prompted discourse regarding the standardization of key elements relevant to the proposals of new linkage-based devices. As a result, this study proposes a comprehensive and standardized design process and offers a brief illustration of the application of this design process through the presentation of a potential new design.
{"title":"A Critical Review and Systematic Design Approach for Linkage-Based Gait Rehabilitation Devices","authors":"Thiago Sá de Paiva, R. S. Gonçalves, Giuseppe Carbone","doi":"10.3390/robotics13010011","DOIUrl":"https://doi.org/10.3390/robotics13010011","url":null,"abstract":"This study aims to provide a comprehensive critical review of the existing body of evidence pertaining to gait rehabilitation. It also seeks to introduce a systematic approach for the development of innovative design solutions in this domain. The field of gait rehabilitation has witnessed a surge in the development of novel robotic devices. This trend has emerged in response to limitations observed in most commercial solutions, particularly regarding their high costs. Consequently, there is a growing need to explore more cost-effective alternatives and create opportunities for greater accessibility. Within the realm of cost-effective options, linkage-based gait trainers have emerged as viable alternatives, prompting a thorough examination of this category, which is carried out in this work. Notably, there is a wide heterogeneity in research approaches and presentation methods. This divergence has prompted discourse regarding the standardization of key elements relevant to the proposals of new linkage-based devices. As a result, this study proposes a comprehensive and standardized design process and offers a brief illustration of the application of this design process through the presentation of a potential new design.","PeriodicalId":506759,"journal":{"name":"Robotics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139389351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：