1
|
Zhou Z, Lu Y, Tortós PE, Qin R, Kokubu S, Matsunaga F, Xie Q, Yu W. Addressing data imbalance in Sim2Real: ImbalSim2Real scheme and its application in finger joint stiffness self-sensing for soft robot-assisted rehabilitation. Front Bioeng Biotechnol 2024; 12:1334643. [PMID: 38948382 PMCID: PMC11212110 DOI: 10.3389/fbioe.2024.1334643] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2023] [Accepted: 05/10/2024] [Indexed: 07/02/2024] Open
Abstract
The simulation-to-reality (sim2real) problem is a common issue when deploying simulation-trained models to real-world scenarios, especially given the extremely high imbalance between simulation and real-world data (scarce real-world data). Although the cycle-consistent generative adversarial network (CycleGAN) has demonstrated promise in addressing some sim2real issues, it encounters limitations in situations of data imbalance due to the lower capacity of the discriminator and the indeterminacy of learned sim2real mapping. To overcome such problems, we proposed the imbalanced Sim2Real scheme (ImbalSim2Real). Differing from CycleGAN, the ImbalSim2Real scheme segments the dataset into paired and unpaired data for two-fold training. The unpaired data incorporated discriminator-enhanced samples to further squash the solution space of the discriminator, for enhancing the discriminator's ability. For paired data, a term targeted regression loss was integrated to ensure specific and quantitative mapping and further minimize the solution space of the generator. The ImbalSim2Real scheme was validated through numerical experiments, demonstrating its superiority over conventional sim2real methods. In addition, as an application of the proposed ImbalSim2Real scheme, we designed a finger joint stiffness self-sensing framework, where the validation loss for estimating real-world finger joint stiffness was reduced by roughly 41% compared to the supervised learning method that was trained with scarce real-world data and by 56% relative to the CycleGAN trained with the imbalanced dataset. Our proposed scheme and framework have potential applicability to bio-signal estimation when facing an imbalanced sim2real problem.
Collapse
Affiliation(s)
- Zhongchao Zhou
- Department of Medical System Engineering, Chiba University, Chiba, Japan
| | - Yuxi Lu
- Department of Medical System Engineering, Chiba University, Chiba, Japan
| | | | - Ruian Qin
- Department of Medical System Engineering, Chiba University, Chiba, Japan
| | - Shota Kokubu
- Department of Medical System Engineering, Chiba University, Chiba, Japan
| | - Fuko Matsunaga
- Department of Medical System Engineering, Chiba University, Chiba, Japan
| | - Qiaolian Xie
- Department of Medical System Engineering, Chiba University, Chiba, Japan
- Institute of Rehabilitation Engineering and Technology, University of Shanghai for Science and Technology, Shanghai, China
| | - Wenwei Yu
- Department of Medical System Engineering, Chiba University, Chiba, Japan
- Center for Frontier Medical Engineering, Chiba University, Chiba, Japan
| |
Collapse
|
2
|
García-Córdova F, Guerrero-González A, Hidalgo-Castelo F. Anthropomorphic Tendon-Based Hands Controlled by Agonist-Antagonist Corticospinal Neural Network. SENSORS (BASEL, SWITZERLAND) 2024; 24:2924. [PMID: 38733030 PMCID: PMC11086241 DOI: 10.3390/s24092924] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/02/2024] [Revised: 04/27/2024] [Accepted: 05/01/2024] [Indexed: 05/13/2024]
Abstract
This article presents a study on the neurobiological control of voluntary movements for anthropomorphic robotic systems. A corticospinal neural network model has been developed to control joint trajectories in multi-fingered robotic hands. The proposed neural network simulates cortical and spinal areas, as well as the connectivity between them, during the execution of voluntary movements similar to those performed by humans or monkeys. Furthermore, this neural connection allows for the interpretation of functional roles in the motor areas of the brain. The proposed neural control system is tested on the fingers of a robotic hand, which is driven by agonist-antagonist tendons and actuators designed to accurately emulate complex muscular functionality. The experimental results show that the corticospinal controller produces key properties of biological movement control, such as bell-shaped asymmetric velocity profiles and the ability to compensate for disturbances. Movements are dynamically compensated for through sensory feedback. Based on the experimental results, it is concluded that the proposed biologically inspired adaptive neural control system is robust, reliable, and adaptable to robotic platforms with diverse biomechanics and degrees of freedom. The corticospinal network successfully integrates biological concepts with engineering control theory for the generation of functional movement. This research significantly contributes to improving our understanding of neuromotor control in both animals and humans, thus paving the way towards a new frontier in the field of neurobiological control of anthropomorphic robotic systems.
Collapse
Affiliation(s)
| | - Antonio Guerrero-González
- Department of Automation, Electrical Engineering, and Electronic Technology, Polytechnic University of Cartagena, 30203 Cartagena, Spain; (F.G.-C.); (F.H.-C.)
| | | |
Collapse
|
3
|
García-Samartín JF, Molina-Gómez R, Barrientos A. Model-Free Control of a Soft Pneumatic Segment. Biomimetics (Basel) 2024; 9:127. [PMID: 38534812 DOI: 10.3390/biomimetics9030127] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2024] [Revised: 02/08/2024] [Accepted: 02/19/2024] [Indexed: 03/28/2024] Open
Abstract
Soft robotics faces challenges in attaining control methods that ensure precision from hard-to-model actuators and sensors. This study focuses on closed-chain control of a segment of PAUL, a modular pneumatic soft arm, using elastomeric-based resistive sensors with negative piezoresistive behaviour irrespective of ambient temperature. PAUL's performance relies on bladder inflation and deflation times. The control approach employs two neural networks: the first translates position references into valve inflation times, and the second acts as a state observer to estimate bladder inflation times using sensor data. Following training, the system achieves position errors of 4.59 mm, surpassing the results of other soft robots presented in the literature. The study also explores system modularity by assessing performance under external loads from non-actuated segments.
Collapse
Affiliation(s)
- Jorge Francisco García-Samartín
- Centro de Automática y Robótica (UPM-CSIC), Universidad Politécnica de Madrid-Consejo Superior de Investigaciones Científicas, José Gutiérrez Abascal 2, 28006 Madrid, Spain
| | - Raúl Molina-Gómez
- Centro de Automática y Robótica (UPM-CSIC), Universidad Politécnica de Madrid-Consejo Superior de Investigaciones Científicas, José Gutiérrez Abascal 2, 28006 Madrid, Spain
| | - Antonio Barrientos
- Centro de Automática y Robótica (UPM-CSIC), Universidad Politécnica de Madrid-Consejo Superior de Investigaciones Científicas, José Gutiérrez Abascal 2, 28006 Madrid, Spain
| |
Collapse
|
4
|
Tang Z, Xin W, Wang P, Laschi C. Learning-Based Control for Soft Robot-Environment Interaction with Force/Position Tracking Capability. Soft Robot 2024. [PMID: 38386561 DOI: 10.1089/soro.2023.0116] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/24/2024] Open
Abstract
Soft robotics promises to achieve safe and efficient interactions with the environment by exploiting its inherent compliance and designing control strategies. However, effective control for the soft robot-environment interaction has been a challenging task. The challenges arise from the nonlinearity and complexity of soft robot dynamics, especially in situations where the environment is unknown and uncertainties exist, making it difficult to establish analytical models. In this study, we propose a learning-based optimal control approach as an attempt to address these challenges, which is an optimized combination of a feedforward controller based on probabilistic model predictive control and a feedback controller based on nonparametric learning methods. The approach is purely data-driven, without prior knowledge of soft robot dynamics and environment structures, and can be easily updated online to adapt to unknown environments. A theoretical analysis of the approach is provided to ensure its stability and convergence. The proposed approach enabled a soft robotic manipulator to track target positions and forces when interacting with a manikin in different cases. Moreover, comparisons with other data-driven control methods show a better performance of our approach. Overall, this work provides a viable learning-based control approach for soft robot-environment interactions with force/position tracking capability.
Collapse
Affiliation(s)
- Zhiqiang Tang
- Department of Mechanical Engineering, National University of Singapore, Singapore, Singapore
| | - Wenci Xin
- Department of Mechanical Engineering, National University of Singapore, Singapore, Singapore
| | - Peiyi Wang
- Robotics Research Center, Beijing Jiaotong University, Beijing, China
| | - Cecilia Laschi
- Department of Mechanical Engineering, National University of Singapore, Singapore, Singapore
| |
Collapse
|
5
|
Zhu M, Dai J, Feng Y. Robust Grasping of a Variable Stiffness Soft Gripper in High-Speed Motion Based on Reinforcement Learning. Soft Robot 2024; 11:95-104. [PMID: 37477655 DOI: 10.1089/soro.2022.0246] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/22/2023] Open
Abstract
Industrial robots are widely deployed to perform pick-and-place tasks at high speeds to minimize manufacturing time and boost productivity. When dealing with delicate or fragile goods, soft robotic grippers are better end effectors than rigid grippers due to their softness and safe interaction. However, high-speed motion causes the soft robotic gripper to vibrate, leading to damage of the objects or failed grasping. Soft grippers with variable stiffness are considered to be effective in suppressing vibrations by adding damping devices, but it is quite challenging to compromise between stiffness and compliance. In this article, a controller based on deep reinforcement learning is proposed to control the stiffness of the soft robotic gripper, which can accurately suppress the vibration with only a minor influence on its compliance and softness. The proposed controller is a real-time vibration control strategy, which estimates the output of the controller based on the current operating environment. To demonstrate the effectiveness of the proposed controller, experiments were done with a UR5 robotic arm. For different situations, experimental results show that the proposed controller responds quickly and reduces the amplitude of the oscillation substantially.
Collapse
Affiliation(s)
- Mingzhu Zhu
- School of Astronautics, Northwestern Polytechnical University, Xi'an, China
| | - Junyue Dai
- Information Engineering College, Zhejiang University of Technology, Hangzhou, China
| | - Yu Feng
- Information Engineering College, Zhejiang University of Technology, Hangzhou, China
| |
Collapse
|
6
|
Nazeer MS, Laschi C, Falotico E. Soft DAgger: Sample-Efficient Imitation Learning for Control of Soft Robots. SENSORS (BASEL, SWITZERLAND) 2023; 23:8278. [PMID: 37837107 PMCID: PMC10574889 DOI: 10.3390/s23198278] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/08/2023] [Revised: 09/28/2023] [Accepted: 10/02/2023] [Indexed: 10/15/2023]
Abstract
This paper presents Soft DAgger, an efficient imitation learning-based approach for training control solutions for soft robots. To demonstrate the effectiveness of the proposed algorithm, we implement it on a two-module soft robotic arm involved in the task of writing letters in 3D space. Soft DAgger uses a dynamic behavioral map of the soft robot, which maps the robot's task space to its actuation space. The map acts as a teacher and is responsible for predicting the optimal actions for the soft robot based on its previous state action history, expert demonstrations, and current position. This algorithm achieves generalization ability without depending on costly exploration techniques or reinforcement learning-based synthetic agents. We propose two variants of the control algorithm and demonstrate that good generalization capabilities and improved task reproducibility can be achieved, along with a consistent decrease in the optimization time and samples. Overall, Soft DAgger provides a practical control solution to perform complex tasks in fewer samples with soft robots. To the best of our knowledge, our study is an initial exploration of imitation learning with online optimization for soft robot control.
Collapse
Affiliation(s)
- Muhammad Sunny Nazeer
- The BioRobotics Institute, Scuola Superiore Sant’Anna, 56025 Pontedera, Italy;
- Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna, 56125 Pisa, Italy
| | - Cecilia Laschi
- Department of Mechanical Engineering, National University of Singapore, Singapore 117575, Singapore;
| | - Egidio Falotico
- The BioRobotics Institute, Scuola Superiore Sant’Anna, 56025 Pontedera, Italy;
- Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna, 56125 Pisa, Italy
| |
Collapse
|
7
|
Kararsiz G, Duygu YC, Wang Z, Rogowski LW, Park SJ, Kim MJ. Navigation and Control of Motion Modes with Soft Microrobots at Low Reynolds Numbers. MICROMACHINES 2023; 14:1209. [PMID: 37374794 DOI: 10.3390/mi14061209] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/16/2023] [Revised: 05/30/2023] [Accepted: 06/05/2023] [Indexed: 06/29/2023]
Abstract
This study investigates the motion characteristics of soft alginate microrobots in complex fluidic environments utilizing wireless magnetic fields for actuation. The aim is to explore the diverse motion modes that arise due to shear forces in viscoelastic fluids by employing snowman-shaped microrobots. Polyacrylamide (PAA), a water-soluble polymer, is used to create a dynamic environment with non-Newtonian fluid properties. Microrobots are fabricated via an extrusion-based microcentrifugal droplet method, successfully demonstrating the feasibility of both wiggling and tumbling motions. Specifically, the wiggling motion primarily results from the interplay between the viscoelastic fluid environment and the microrobots' non-uniform magnetization. Furthermore, it is discovered that the viscoelasticity properties of the fluid influence the motion behavior of the microrobots, leading to non-uniform behavior in complex environments for microrobot swarms. Through velocity analysis, valuable insights into the relationship between applied magnetic fields and motion characteristics are obtained, facilitating a more realistic understanding of surface locomotion for targeted drug delivery purposes while accounting for swarm dynamics and non-uniform behavior.
Collapse
Affiliation(s)
- Gokhan Kararsiz
- Department of Mechanical Engineering, Southern Methodist University, Dallas, TX 75275, USA
| | - Yasin Cagatay Duygu
- Department of Mechanical Engineering, Southern Methodist University, Dallas, TX 75275, USA
| | - Zhengguang Wang
- Department of Mechanical Engineering, Southern Methodist University, Dallas, TX 75275, USA
| | - Louis William Rogowski
- Applied Research Associates, Inc. (ARA), 4300 San Mateo Blvd. NE, Suite A-220, Albuquerque, NM 87110, USA
| | - Sung Jea Park
- School of Mechanical Engineering, Korea University of Technology and Education, Cheonan 31253, Chungnam, Republic of Korea
| | - Min Jun Kim
- Department of Mechanical Engineering, Southern Methodist University, Dallas, TX 75275, USA
| |
Collapse
|
8
|
Xiang G, Dian S, Du S, Lv Z. Variational Information Bottleneck Regularized Deep Reinforcement Learning for Efficient Robotic Skill Adaptation. SENSORS (BASEL, SWITZERLAND) 2023; 23:762. [PMID: 36679561 PMCID: PMC9864208 DOI: 10.3390/s23020762] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/16/2022] [Revised: 01/03/2023] [Accepted: 01/05/2023] [Indexed: 06/17/2023]
Abstract
Deep Reinforcement Learning (DRL) algorithms have been widely studied for sequential decision-making problems, and substantial progress has been achieved, especially in autonomous robotic skill learning. However, it is always difficult to deploy DRL methods in practical safety-critical robot systems, since the training and deployment environment gap always exists, and this issue would become increasingly crucial due to the ever-changing environment. Aiming at efficiently robotic skill transferring in a dynamic environment, we present a meta-reinforcement learning algorithm based on a variational information bottleneck. More specifically, during the meta-training stage, the variational information bottleneck first has been applied to infer the complete basic tasks for the whole task space, then the maximum entropy regularized reinforcement learning framework has been used to learn the basic skills consistent with that of basic tasks. Once the training stage is completed, all of the tasks in the task space can be obtained by a nonlinear combination of the basic tasks, thus, the according skills to accomplish the tasks can also be obtained by some way of a combination of the basic skills. Empirical results on several highly nonlinear, high-dimensional robotic locomotion tasks show that the proposed variational information bottleneck regularized deep reinforcement learning algorithm can improve sample efficiency by 200-5000 times on new tasks. Furthermore, the proposed algorithm achieves substantial asymptotic performance improvement. The results indicate that the proposed meta-reinforcement learning framework makes a significant step forward to deploy the DRL-based algorithm to practical robot systems.
Collapse
Affiliation(s)
- Guofei Xiang
- College of Electrical Engineering, Sichuan University, Chengdu 610065, China
- National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou 014031, China
| | - Songyi Dian
- College of Electrical Engineering, Sichuan University, Chengdu 610065, China
| | - Shaofeng Du
- National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou 014031, China
| | - Zhonghui Lv
- National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou 014031, China
| |
Collapse
|
9
|
Design and control of soft biomimetic pangasius fish robot using fin ray effect and reinforcement learning. Sci Rep 2022; 12:21861. [PMID: 36529776 PMCID: PMC9760642 DOI: 10.1038/s41598-022-26179-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Accepted: 12/12/2022] [Indexed: 12/23/2022] Open
Abstract
Soft robots provide a pathway to accurately mimic biological creatures and be integrated into their environment with minimal invasion or disruption to their ecosystem. These robots made from soft deforming materials possess structural properties and behaviors similar to the bodies and organs of living creatures. However, they are difficult to develop in terms of integrated actuation and sensing, accurate modeling, and precise control. This article presents a soft-rigid hybrid robotic fish inspired by the Pangasius fish. The robot employs a flexible fin ray tail structure driven by a servo motor, to act as the soft body of the robot and provide the undulatory motion to the caudal fin of the fish. To address the modeling and control challenges, reinforcement learning (RL) is proposed as a model-free control strategy for the robot fish to swim and reach a specified target goal. By training and investigating the RL through experiments on real hardware, we illustrate the capability of the fish to learn and achieve the required task.
Collapse
|
10
|
Schegg P, Ménager E, Khairallah E, Marchal D, Dequidt J, Preux P, Duriez C. SofaGym: An Open Platform for Reinforcement Learning Based on Soft Robot Simulations. Soft Robot 2022; 10:410-430. [PMID: 36476150 DOI: 10.1089/soro.2021.0123] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022] Open
Abstract
OpenAI Gym is one of the standard interfaces used to train Reinforcement Learning (RL) Algorithms. The Simulation Open Framework Architecture (SOFA) is a physics-based engine that is used for soft robotics simulation and control based on real-time models of deformation. The aim of this article is to present SofaGym, an open-source software to create OpenAI Gym interfaces, called environments, out of soft robot digital twins. The link between soft robotics and RL offers new challenges for both fields: representation of the soft robot in an RL context, complex interactions with the environment, use of specific mechanical tools to control soft robots, transfer of policies learned in simulation to the real world, etc. The article presents the large possible uses of SofaGym to tackle these challenges by using RL and planning algorithms. This publication contains neither new algorithms nor new models but proposes a new platform, open to the community, that offers non existing possibilities of coupling RL to physics-based simulation of soft robots. We present 11 environments, representing a wide variety of soft robots and applications; we highlight the challenges showcased by each environment. We propose methods of solving the task using traditional control, RL, and planning and point out research perspectives using the platform.
Collapse
Affiliation(s)
- Pierre Schegg
- Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, Univ. Lille, Lille, France
- Robocath, Rouen, France
| | - Etienne Ménager
- Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, Univ. Lille, Lille, France
| | - Elie Khairallah
- Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, Univ. Lille, Lille, France
| | - Damien Marchal
- Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, Univ. Lille, Lille, France
| | - Jérémie Dequidt
- Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, Univ. Lille, Lille, France
| | - Philippe Preux
- Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, Univ. Lille, Lille, France
| | - Christian Duriez
- Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, Univ. Lille, Lille, France
| |
Collapse
|
11
|
Morimoto R, Ikeda M, Niiyama R, Kuniyoshi Y. Characterization of continuum robot arms under reinforcement learning and derived improvements. Front Robot AI 2022; 9:895388. [PMID: 36119726 PMCID: PMC9475256 DOI: 10.3389/frobt.2022.895388] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2022] [Accepted: 08/04/2022] [Indexed: 11/13/2022] Open
Abstract
In robotics, soft continuum robot arms are a promising prospect owing to their redundancy and passivity; however, no comprehensive study exists that examines their characteristics compared to rigid manipulators. In this study, we examined the advantages of a continuum robot arm as compared to a typical and rigid seven-degree-of-freedom (7-DoF) robot manipulator in terms of performing various tasks through reinforcement learning. We conducted simulations for tasks with different characteristics that require control over position and force. Common tasks in robot manipulators, such as reaching, crank rotation, object throwing, and peg-in-hole were considered. The initial conditions of the robot and environment were randomized, aiming for evaluations including robustness. The results indicate that the continuum robot arm excels in the crank-rotation task, which is characterized by uncertainty in environmental conditions and cumulative rewards. However, the rigid robot arm learned better motions for the peg-in-hole task than the other tasks, which requires fine motion control of the end-effector. In the throwing task, the continuum robot arm scored well owing to its good handling of anisotropy. Moreover, we developed a reinforcement-learning method based on the comprehensive experimental results. The proposed method successfully improved the motion learning of a continuum robot arm by adding a technique to regulate the initial state of the robot. To the best of our knowledge, ours is the first reinforcement-learning experiment with multiple tasks on a single continuum robot arm and is the first report of a comparison between a single continuum robot arm and rigid manipulator on a wide range of tasks. This simulation study can make a significant contribution to the design of continuum arms and specification of their applications, and development of control and reinforcement learning methods.
Collapse
|
12
|
|
13
|
Graule MA, McCarthy TP, Teeple CB, Werfel J, Wood RJ. SoMoGym: A Toolkit for Developing and Evaluating Controllers and Reinforcement Learning Algorithms for Soft Robots. IEEE Robot Autom Lett 2022. [DOI: 10.1109/lra.2022.3149580] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
|
14
|
Li G, Stalin T, Truong VT, Alvarado PVY. DNN-Based Predictive Model for a Batoid-Inspired Soft Robot. IEEE Robot Autom Lett 2022. [DOI: 10.1109/lra.2021.3135573] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
|
15
|
Rajendran SK, Zhang F. Design, Modeling, and Visual Learning-Based Control of Soft Robotic Fish Driven by Super-Coiled Polymers. Front Robot AI 2022; 8:809427. [PMID: 35309723 PMCID: PMC8931759 DOI: 10.3389/frobt.2021.809427] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/05/2021] [Accepted: 12/17/2021] [Indexed: 11/13/2022] Open
Abstract
A rapidly growing field of aquatic bio-inspired soft robotics takes advantage of the underwater animals’ bio-mechanisms, where its applications are foreseen in a vast domain such as underwater exploration, environmental monitoring, search and rescue, oil-spill detection, etc. Improved maneuverability and locomotion of such robots call for designs with higher level of biomimicry, reduced order of complex modeling due to continuum elastic dynamics, and challenging robust nonlinear controllers. This paper presents a novel design of a soft robotic fish actively actuated by a newly developed kind of artificial muscles—super-coiled polymers (SCP) and passively propelled by a caudal fin. Besides SCP exhibiting several advantages in terms of flexibility, cost and fabrication duration, this design benefits from the SCP’s significantly quicker recovery due to water-based cooling. The soft robotic fish is approximated as a 3-link representation and mathematically modeled from its geometric and dynamic perspectives to constitute the combined system dynamics of the SCP actuators and hydrodynamics of the fish, thus realizing two-dimensional fish-swimming motion. The nonlinear dynamic model of the SCP driven soft robotic fish, ignoring uncertainties and unmodeled dynamics, necessitates the development of robust/intelligent control which serves as the motivation to not only mimic the bio-mechanisms, but also mimic the cognitive abilities of a real fish. Therefore, a learning-based control design is proposed to meet the yaw control objective and study its performance in path following via various swimming patterns. The proposed learning-based control design employs the use of deep-deterministic policy gradient (DDPG) reinforcement learning algorithm to train the agent. To overcome the limitations of sensing the soft robotic fish’s states by designing complex embedded sensors, overhead image-based observations are generated and input to convolutional neural networks (CNNs) to deduce the curvature dynamics of the soft robot. A linear quadratic regulator (LQR) based multi-objective reward is proposed to reinforce the learning feedback of the agent during training. The DDPG-based control design is simulated and the corresponding results are presented.
Collapse
Affiliation(s)
- Sunil Kumar Rajendran
- Department of Electrical and Computer Engineering, Volgenau School of Engineering, George Mason University, Fairfax, VA, United States
| | - Feitian Zhang
- Department of Advanced Manufacturing and Robotics, Peking University, Beijing, China
- *Correspondence: Feitian Zhang,
| |
Collapse
|
16
|
Abstract
In this review paper, we are interested in the models and algorithms that allow generic simulation and control of a soft robot. First, we start with a quick overview of modeling approaches for soft robots and available methods for calculating the mechanical compliance, and in particular numerical methods, like real-time Finite Element Method (FEM). We also show how these models can be updated based on sensor data. Then, we are interested in the problem of inverse kinematics, under constraints, with generic solutions without assumption on the robot shape, the type, the placement or the redundancy of the actuators, the material behavior… We are also interested by the use of these models and algorithms in case of contact with the environment. Moreover, we refer to dynamic control algorithms based on mechanical models, allowing for robust control of the positioning of the robot. For each of these aspects, this paper gives a quick overview of the existing methods and a focus on the use of FEM. Finally, we discuss the implementation and our contribution in the field for an open soft robotics research.
Collapse
Affiliation(s)
- Pierre Schegg
- Robocath, Rouen, France
- Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, University of Lille, Lille, France
| | - Christian Duriez
- Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, University of Lille, Lille, France
| |
Collapse
|
17
|
Youssef SM, Soliman M, Saleh MA, Mousa MA, Elsamanty M, Radwan AG. Underwater Soft Robotics: A Review of Bioinspiration in Design, Actuation, Modeling, and Control. MICROMACHINES 2022; 13:mi13010110. [PMID: 35056275 PMCID: PMC8778375 DOI: 10.3390/mi13010110] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/04/2021] [Revised: 12/31/2021] [Accepted: 01/02/2022] [Indexed: 12/27/2022]
Abstract
Nature and biological creatures are some of the main sources of inspiration for humans. Engineers have aspired to emulate these natural systems. As rigid systems become increasingly limited in their capabilities to perform complex tasks and adapt to their environment like living creatures, the need for soft systems has become more prominent due to the similar complex, compliant, and flexible characteristics they share with intelligent natural systems. This review provides an overview of the recent developments in the soft robotics field, with a focus on the underwater application frontier.
Collapse
Affiliation(s)
- Samuel M. Youssef
- Smart Engineering Systems Research Center (SESC), Nile University, Sheikh Zayed City 12588, Egypt;
- Correspondence:
| | - MennaAllah Soliman
- School of Engineering and Applied Sciences, Nile University, Sheikh Zayed City 12588, Egypt; (M.S.); (M.A.S.); (A.G.R.)
| | - Mahmood A. Saleh
- School of Engineering and Applied Sciences, Nile University, Sheikh Zayed City 12588, Egypt; (M.S.); (M.A.S.); (A.G.R.)
| | - Mostafa A. Mousa
- Nile University’s Innovation Hub, Nile University, Sheikh Zayed City 12588, Egypt;
| | - Mahmoud Elsamanty
- Smart Engineering Systems Research Center (SESC), Nile University, Sheikh Zayed City 12588, Egypt;
- Mechanical Department, Faculty of Engineering at Shoubra, Benha University, Cairo 11672, Egypt
| | - Ahmed G. Radwan
- School of Engineering and Applied Sciences, Nile University, Sheikh Zayed City 12588, Egypt; (M.S.); (M.A.S.); (A.G.R.)
- Department of Engineering Mathematics and Physics, Cairo University, Giza 12613, Egypt
| |
Collapse
|
18
|
A Novel Training and Collaboration Integrated Framework for Human-Agent Teleoperation. SENSORS 2021; 21:s21248341. [PMID: 34960435 PMCID: PMC8708703 DOI: 10.3390/s21248341] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/11/2021] [Revised: 12/03/2021] [Accepted: 12/11/2021] [Indexed: 12/21/2022]
Abstract
Human operators have the trend of increasing physical and mental workloads when performing teleoperation tasks in uncertain and dynamic environments. In addition, their performances are influenced by subjective factors, potentially leading to operational errors or task failure. Although agent-based methods offer a promising solution to the above problems, the human experience and intelligence are necessary for teleoperation scenarios. In this paper, a truncated quantile critics reinforcement learning-based integrated framework is proposed for human–agent teleoperation that encompasses training, assessment and agent-based arbitration. The proposed framework allows for an expert training agent, a bilateral training and cooperation process to realize the co-optimization of agent and human. It can provide efficient and quantifiable training feedback. Experiments have been conducted to train subjects with the developed algorithm. The performances of human–human and human–agent cooperation modes are also compared. The results have shown that subjects can complete the tasks of reaching and picking and placing with the assistance of an agent in a shorter operational time, with a higher success rate and less workload than human–human cooperation.
Collapse
|
19
|
Liu XY, Wang JX. Physics-informed Dyna-style model-based deep reinforcement learning for dynamic control. Proc Math Phys Eng Sci 2021. [DOI: 10.1098/rspa.2021.0618] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022] Open
Abstract
Model-based reinforcement learning (MBRL) is believed to have much higher sample efficiency compared with model-free algorithms by learning a predictive model of the environment. However, the performance of MBRL highly relies on the quality of the learned model, which is usually built in a black-box manner and may have poor predictive accuracy outside of the data distribution. The deficiencies of the learned model may prevent the policy from being fully optimized. Although some uncertainty analysis-based remedies have been proposed to alleviate this issue, model bias still poses a great challenge for MBRL. In this work, we propose to leverage the prior knowledge of underlying physics of the environment, where the governing laws are (partially) known. In particular, we developed a physics-informed MBRL framework, where governing equations and physical constraints are used to inform the model learning and policy search. By incorporating the prior information of the environment, the quality of the learned model can be notably improved, while the required interactions with the environment are significantly reduced, leading to better sample efficiency and learning performance. The effectiveness and merit have been demonstrated over a handful of classic control problems, where the environments are governed by canonical ordinary/partial differential equations.
Collapse
Affiliation(s)
- Xin-Yang Liu
- Department of Aerospace and Mechanical Engineering, College of Engineering, University of Notre Dame, Notre Dame, IN, USA
| | - Jian-Xun Wang
- Department of Aerospace and Mechanical Engineering, College of Engineering, University of Notre Dame, Notre Dame, IN, USA
| |
Collapse
|
20
|
Naughton N, Sun J, Tekinalp A, Parthasarathy T, Chowdhary G, Gazzola M. Elastica: A Compliant Mechanics Environment for Soft Robotic Control. IEEE Robot Autom Lett 2021. [DOI: 10.1109/lra.2021.3063698] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
|
21
|
Abstract
Abstract
Deep learning is transforming most areas of science and technology, including electron microscopy. This review paper offers a practical perspective aimed at developers with limited familiarity. For context, we review popular applications of deep learning in electron microscopy. Following, we discuss hardware and software needed to get started with deep learning and interface with electron microscopes. We then review neural network components, popular architectures, and their optimization. Finally, we discuss future directions of deep learning in electron microscopy.
Collapse
|
22
|
A Collaborative Control Method of Dual-Arm Robots Based on Deep Reinforcement Learning. APPLIED SCIENCES-BASEL 2021. [DOI: 10.3390/app11041816] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Collaborative control of a dual-arm robot refers to collision avoidance and working together to accomplish a task. To prevent the collision of two arms, the control strategy of a robot arm needs to avoid competition and to cooperate with the other one during motion planning. In this paper, a dual-arm deep deterministic policy gradient (DADDPG) algorithm is proposed based on deep reinforcement learning of multi-agent cooperation. Firstly, the construction method of a replay buffer in a hindsight experience replay algorithm is introduced. The modeling and training method of the multi-agent deep deterministic policy gradient algorithm is explained. Secondly, a control strategy is assigned to each robotic arm. The arms share their observations and actions. The dual-arm robot is trained based on a mechanism of “rewarding cooperation and punishing competition”. Finally, the effectiveness of the algorithm is verified in the Reach, Push, and Pick up simulation environment built in this study. The experiment results show that the robot trained by the DADDPG algorithm can achieve cooperative tasks. The algorithm can make the robots explore the action space autonomously and reduce the level of competition with each other. The collaborative robots have better adaptability to coordination tasks.
Collapse
|
23
|
Akalin N, Loutfi A. Reinforcement Learning Approaches in Social Robotics. SENSORS 2021; 21:s21041292. [PMID: 33670257 PMCID: PMC7918897 DOI: 10.3390/s21041292] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/17/2020] [Revised: 01/26/2021] [Accepted: 02/04/2021] [Indexed: 11/16/2022]
Abstract
This article surveys reinforcement learning approaches in social robotics. Reinforcement learning is a framework for decision-making problems in which an agent interacts through trial-and-error with its environment to discover an optimal behavior. Since interaction is a key component in both reinforcement learning and social robotics, it can be a well-suited approach for real-world interactions with physically embodied social robots. The scope of the paper is focused particularly on studies that include social physical robots and real-world human-robot interactions with users. We present a thorough analysis of reinforcement learning approaches in social robotics. In addition to a survey, we categorize existent reinforcement learning approaches based on the used method and the design of the reward mechanisms. Moreover, since communication capability is a prominent feature of social robots, we discuss and group the papers based on the communication medium used for reward formulation. Considering the importance of designing the reward function, we also provide a categorization of the papers based on the nature of the reward. This categorization includes three major themes: interactive reinforcement learning, intrinsically motivated methods, and task performance-driven methods. The benefits and challenges of reinforcement learning in social robotics, evaluation methods of the papers regarding whether or not they use subjective and algorithmic measures, a discussion in the view of real-world reinforcement learning challenges and proposed solutions, the points that remain to be explored, including the approaches that have thus far received less attention is also given in the paper. Thus, this paper aims to become a starting point for researchers interested in using and applying reinforcement learning methods in this particular research field.
Collapse
|
24
|
Abstract
SUMMARYInteraction between a robot and its environment requires perception about the environment, which helps the robot in making a clear decision about the object type and its location. After that, the end effector will be brought to the object’s location for grasping. There are many research studies on the reaching and grasping of objects using different techniques and mechanisms for increasing accuracy and robustness during grasping and reaching tasks. Thus, this paper presents an extensive review of research directions and topics of different approaches such as sensing, learning and gripping, which have been implemented within the current five years.
Collapse
|
25
|
Wang J, Zheng T, Gao Y, Wang D, Cui W, Fan J, You Z, Zhang J, Du X, Qiao Z, Wang X, Wang S, Xu Z, Wang C. Preparation and properties characterization of a novel soft robots partially made of silicone/W-based composites for gamma ray shielding. PROGRESS IN NUCLEAR ENERGY 2020. [DOI: 10.1016/j.pnucene.2020.103531] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
26
|
Kan L, Lei F, Song B, Su B, Shi Y. Flexible electromagnetic capturer with a rapid ejection feature inspired by a biological ballistic tongue. BIOINSPIRATION & BIOMIMETICS 2020; 15:066002. [PMID: 32647093 DOI: 10.1088/1748-3190/aba444] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/02/2020] [Accepted: 07/09/2020] [Indexed: 06/11/2023]
Abstract
Bionics is the inspiration resource of state-of-the-art science and technology. The chameleon can capture prey at great distances with the assistance of its highly stretchable and ballistic tongue. Inspired by this biological structure, here we demonstrate the fabrication of flexible electromagnetic manipulators. The as-prepared flexible electromagnetic manipulator can reach a maximum velocity of 8.1 m s-1and acceleration of 627 m s-2at an applied voltage of 360 V. The working mechanism of this flexible electromagnetic manipulator has been studied based on Maxwell and Abaqus simulations. Diverse parameters, including the lengths of the magnetic tube (the cylindrical magnet) and the whole manipulator and the applied voltage values, have been considered to tune the ejecting performance of the manipulator. Furthermore, flexible electromagnetic manipulators can be upgraded to capture various objects by attaching a mechanical force triggered gripper to their top pads. With this design, the velocity of the gripper can be significantly improved (the maximum is 8.1 m s-1, whereas soft grippers in previous research do not have the characteristic of fast movement), thus making it possible to get objects without approaching them; in other words, we can catch objects even though they are far away from us, which provides the possibility of long-distance capture. We believe this kind of bio-inspired fabrication is a powerful strategy to design and synthesize flexible even stretchable manipulators, extending the boundaries of conventional manipulators for soft robots.
Collapse
Affiliation(s)
- Longxin Kan
- State Key Laboratory of Material Processing and Die & Mould Technology, School of Materials Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, People's Republic of China
| | - Fengxiao Lei
- State Key Laboratory of Material Processing and Die & Mould Technology, School of Materials Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, People's Republic of China
| | - Bo Song
- State Key Laboratory of Material Processing and Die & Mould Technology, School of Materials Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, People's Republic of China
| | - Bin Su
- State Key Laboratory of Material Processing and Die & Mould Technology, School of Materials Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, People's Republic of China
| | - Yusheng Shi
- State Key Laboratory of Material Processing and Die & Mould Technology, School of Materials Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, People's Republic of China
| |
Collapse
|
27
|
Application of Deep Reinforcement Learning in Traffic Signal Control: An Overview and Impact of Open Traffic Data. APPLIED SCIENCES-BASEL 2020. [DOI: 10.3390/app10114011] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Persistent congestions which are varying in strength and duration in the dense traffic networks are the most prominent obstacle towards sustainable mobility. Those types of congestions cannot be adequately resolved by the traditional Adaptive Traffic Signal Control (ATSC). The introduction of Reinforcement Learning (RL) in ATSC as tackled those types of congestions by using on-line learning, which is based on the trial and error approach. Furthermore, RL is prone to the dimensionality curse related to the state–action space size based on which a non-linear quality function is derived. The Deep Reinforcement Learning (DRL) framework uses Deep Neural Networks (DNN) to digest raw traffic data to approximate the quality function of RL. This paper provides a comprehensive analysis of the most recent DRL approaches used for the ATSC algorithm design. Special emphasis is set to overview of the traffic state representation and multi-agent DRL frameworks applied for the large traffic networks. Best practices are provided for choosing the adequate DRL model, hyper-parameters tuning, and model architecture design. Finally, this paper provides a discussion about the importance of the open traffic data concept for the extensive application of DRL in the real world ATSC.
Collapse
|
28
|
Abstract
Building on the recent progress of four-dimensional (4D) printing to produce dynamic structures, this study aimed to bring this technology to the next level by introducing control-based 4D printing to develop adaptive 4D-printed systems with highly versatile multi-disciplinary applications, including medicine, in the form of assisted soft robots, smart textiles as wearable electronics and other industries such as agriculture and microfluidics. This study introduced and analysed adaptive 4D-printed systems with an advanced manufacturing approach for developing stimuli-responsive constructs that organically adapted to environmental dynamic situations and uncertainties as nature does. The adaptive 4D-printed systems incorporated synergic integration of three-dimensional (3D)-printed sensors into 4D-printing and control units, which could be assembled and programmed to transform their shapes based on the assigned tasks and environmental stimuli. This paper demonstrates the adaptivity of these systems via a combination of proprioceptive sensory feedback, modeling and controllers, as well as the challenges and future opportunities they present.
Collapse
|
29
|
Adaptive Real-Time Offloading Decision-Making for Mobile Edges: Deep Reinforcement Learning Framework and Simulation Results. APPLIED SCIENCES-BASEL 2020. [DOI: 10.3390/app10051663] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
This paper proposes a novel dynamic offloading decision method which is inspired by deep reinforcement learning (DRL). In order to realize real-time communications in mobile edge computing systems, an efficient task offloading algorithm is required. When the decision of actions (offloading enabled, i.e., computing in clouds or offloading disabled, i.e., computing in local edges) is made by the proposed DRL-based dynamic algorithm in each unit time, it is required to consider real-time/seamless data transmission and energy-efficiency in mobile edge devices. Therefore, our proposed dynamic offloading decision algorithm is designed for the joint optimization of delay and energy-efficient communications based on DRL framework. According to the performance evaluation via data-intensive simulations, this paper verifies that the proposed dynamic algorithm achieves desired performance.
Collapse
|
30
|
Correction: Bhagat, S.; et al. Deep Reinforcement Learning for Soft, Flexible Robots: Brief Review with Impending Challenges. Robotics 2019, 8, 4. ROBOTICS 2019. [DOI: 10.3390/robotics8040093] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
The authors wish to make the following corrections to this paper [1]: In Figure 1 of this paper [...]
Collapse
|