Machine Learning for Soft Robotic Sensing and Control
Open accessThe DOI matches its Crossref record; 40 of the 42 references it cites were found in a registry or an index, and 2 are not checked yet.
Abstract
Herein, the progress of machine learning methods in the field of soft robotics, specifically in the applications of sensing and control, is outlined. Data‐driven methods such as machine learning are especially suited to systems with governing functions that are unknown, impractical or impossible to represent analytically, or computationally intractable to integrate into real‐world solutions. Function approximation with careful formulation of the machine learning architecture enables the encoding of dynamic behavior and nonlinearities, with the added potential to address hysteresis and nonstationary behavior. Supervised learning and reinforcement learning in simulation and on a wide variety of physical robotic systems have shown promising results for the use of empirical data‐driven methods as a solution to contemporary soft robotics problems.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“There have been many outstanding examples of exploiting machine learning in the field of sensors and actuators, such as extracting motion intent from electrophysiological signals,[287,610] using haptics to identify object categories,[160,611] decoupling multimodal signals from cross-reactive sensor arrays,[231,612] and controlling soft robots[613,614].”
From Flexible Electronics and Devices as Human–Machine Interfaces for Medical Robotics (2022) · cites this paper as [611]
Citations
Cites
Pattern Recognition and Machine Learning
(2006) · doi:10.1007/978-0-387-45528-0 · Cited by 9,824
Design, fabrication and control of soft robots
Rus, D., & Tolley, M. T. (2015) · Nature · doi:10.1038/nature14543 · Cited by 5,825
Soft Robotics: Biological Inspiration, State of the Art, and Future Research
Trivedi, D., Rahn, C. D., Kier, W. M., & Walker, I. D. (2008) · Applied Bionics and Biomechanics · doi:10.1080/11762320802557865 · Cited by 1,708
Soft Robotics: A Perspective—Current Trends and Prospects for the Future
Majidi, C. (2014) · Soft Robotics · doi:10.1089/soro.2013.0001 · Cited by 1,302
Self-citationWhitesides, G. M. (2018) · Angewandte Chemie International Edition · doi:10.1002/anie.201800907 · Cited by 850
Soft robot perception using embedded soft sensors and recurrent neural networks
Thuruthel, T. G., Shih, B., Laschi, C., & Tolley, M. T. (2019) · Science Robotics · doi:10.1126/scirobotics.aav1488 · Cited by 678
Control Strategies for Soft Robotic Manipulators: A Survey
George Thuruthel, T., Ansari, Y., Falotico, E., & Laschi, C. (2018) · Soft Robotics · doi:10.1089/soro.2017.0007 · Cited by 645
Lee, C., Kim, M., Kim, Y. J., Hong, N., Ryu, S., Kim, H. J., & Kim, S. (2017) · International Journal of Control, Automation and Systems · doi:10.1007/s12555-016-0462-3 · Cited by 616
Solving Rubik's Cube with a Robot Hand
OpenAI, Akkaya, I., Andrychowicz, M., Chociej, M., Litwin, M., McGrew, B., Petron, A., Paino, A., Plappert, M., Powell, G., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.07113 · Cited by 602 · cited 1×
“[47] The stochastic and nonlinear dynamics of soft systems is a major dif fi culty in their control.”
BackgroundSoft‐Matter Engineering for Soft Robotics
Majidi, C. (2019) · Advanced Materials Technologies · doi:10.1002/admt.201800477 · Cited by 358
Self-citation
Research works printed but not linked: 13
- Buondonno G., 2017, IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, 705
- Duriez C., 2013, Proc. IEEE Int. Conf. on Robotics and Automation, 3982
- Mitchell T. M., 1997, Machine Learning
- Baishya S. S., 2016, IEEE Int. Conf. on Intelligent Robots and Systems, 8
- Schmitz A., 2015, IEEE-RAS Int. Conf. on Humanoid Robots, 1044
- Schlagenhauf C., Control of Tendon-Driven Soft Foam Robot Hands, Tech. Rep.
- Trumic M., Kernel-Based Nonlinear Adaptive Control of Stiffness and Position for Soft Robots Actuators, Tech. Rep.
- T. G.Thuruthel E.Falotico M.Cianchetti F.Renda C.Laschi in13th Int. Conf. on Informatics in Control Automation and Robotics Doctoral Consortium Vol.2 Science and Technology Publications Setubal Portugal2016 p.303.
- H.Jiang Z.Wang X.Liu X.Chen Y.Jin X.You X.Chen inProc. IEEE Int. Conf. on Robotics and Automation.IEEE Piscataway NJ2017 p.6127.
- Zhang H., 2017, Proc. 10th International Conference on Intelligent Robotics and Applications (ICIRA), 173
- Gillespie M. T., 2018, IEEE Int. Conf. on Soft Robotics, RoboSoft 2018, 39
- Deisenroth M. P., 2011, Robot. Sci. Syst., 57
- Lenz I., 2015, Robot. Sci. Syst., 11
Cited by
Electronic skins and machine learning for intelligent soft robots
Shih, B., Shah, D., Li, J., Thuruthel, T. G., Park, Y.-L., Iida, F., Bao, Z., Kramer-Bottiglio, R., & Tolley, M. T. (2020) · Science Robotics · doi:10.1126/scirobotics.aaz9239 · Cited by 715
Flexible Electronics and Devices as Human–Machine Interfaces for Medical Robotics
Heng, W., Solomon, S., & Gao, W. (2022) · Advanced Materials · doi:10.1002/adma.202107902 · Cited by 609
Xavier, M. S., Tawk, C. D., Zolfagharian, A., Pinskier, J., Howard, D., Young, T., Lai, J., Harrison, S. M., Yong, Y. K., Bodaghi, M., et al. (2022) · IEEE Access · doi:10.1109/access.2022.3179589 · Cited by 418
“model-based methods due to their significant degrees of freedom and highly nonlinear dynamics [285], [334].”
BackgroundFinite Element Modeling of Soft Fluidic Actuators: Overview and Recent Developments
Xavier, M. S., Fleming, A. J., & Yong, Y. K. (2021) · Advanced Intelligent Systems · doi:10.1002/aisy.202000187 · Cited by 313
Ying, B., Chen, R. Z., Zuo, R., Li, J., & Liu, X. (2021) · Advanced Functional Materials · doi:10.1002/adfm.202104665 · Cited by 273
Control Strategies for Soft Robot Systems
Wang, J., & Chortos, A. (2022) · Advanced Intelligent Systems · doi:10.1002/aisy.202100165 · Cited by 254
Applications of artificial intelligence in engineering and manufacturing: a systematic review
Nti, I. K., Adekoya, A. F., Weyori, B. A., & Nyarko-Boateng, O. (2022) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-021-01771-6 · Cited by 234
“…2018; Shastry & Sanjay, 2020), learning and teaching (Liang et al., 2016; Nti & Quarcoo, 2019), robotics and autonomous driving (Bi et al., 2020; Chin et al., 2020; Fong et al., 2020), earthing resistance prediction (Nti Adekoya et al., 2020; Nti Adekoya et al., 2020; Nti, Appiah, et al., 2020;…”
BackgroundElastica: A Compliant Mechanics Environment for Soft Robotic Control
Naughton, N. M., Sun, J., Tekinalp, A., Parthasarathy, T., Chowdhary, G. V., & Gazzola, M. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3063698 · Cited by 196
Data-Driven Methods Applied to Soft Robot Modeling and Control: A Review
Chen, Z., Renda, F., Gall, A. L., Mocellin, L., Bernabei, M., Dangel, T., Ciuti, G., Cianchetti, M., & Stefanini, C. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3377291 · Cited by 180
“Owing to the above characteristics, the modeling of soft robots is more complex than that of their rigid counterparts, which also leads to challenging control tasks [13], [14].”
BackgroundMachine learning (ML)-centric resource management in cloud computing: A review and future directions
Khan, T., Tian, W., Zhou, G., Ilager, S., Gong, M., & Buyya, R. (2022) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2022.103405 · Cited by 179
A survey of robot manipulation in contact
Suomalainen, M., Karayiannidis, Y., & Kyrki, V. (2022) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2022.104224 · Cited by 165
“Compliance can also be created with a mechanical device, such as a Variable Stiffness Actuator (VSA) or the relatively novel field of soft robotics [6]; in this survey, we will not go deeper into mechanical compliance, but present certain works where mechanical compliance is used.”
BackgroundIntelligent Soft Surgical Robots for Next‐Generation Minimally Invasive Surgery
Zhu, J., Lyu, L., Xu, Y., Liang, H., Zhang, X., Ding, H., & Wu, Z. (2021) · Advanced Intelligent Systems · doi:10.1002/aisy.202100011 · Cited by 165
Soft Tactile Sensing Skins for Robotics
Roberts, P. B., Zadan, M., & Majidi, C. (2021) · Current Robotics Reports · doi:10.1007/s43154-021-00065-2 · Cited by 152
“Advancements in this field also depend on further progress in the use of machine learning for mapping a soft sensor’s raw data into accurate measurements of pressure intensity and location [94–99].”
BackgroundSelf-citationRecent Advances on Underwater Soft Robots
Qu, J., Xu, Y., Li, Z., Yu, Z., Mao, B., Wang, Y., Wang, Z., Fan, Q., Qian, X., Zhang, M., et al. (2023) · Advanced Intelligent Systems · doi:10.1002/aisy.202300299 · Cited by 148
ReSkin: versatile, replaceable, lasting tactile skinsPreprint
Bhirangi, R., Hellebrekers, T., Majidi, C., & Gupta, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.00071 · Cited by 146
“Machine learning approaches have recently been shown to effectively parse soft sensor data for robotic grasping [7, 8, 9], proprioception [10], and object classification [11], among many others [12, 13, 14].”
BackgroundSelf-citationSoft Materials and Devices Enabling Sensorimotor Functions in Soft Robots
Su, J., He, K., Li, Y., Tu, J., & Chen, X. (2025) · Chemical Reviews · doi:10.1021/acs.chemrev.4c00906 · Cited by 124
Magnetic Printing of Liquid Metal for Perceptive Soft Actuators with Embodied Intelligence
Ma, B., Xu, C., Cui, L., Chao, Z., & Liu, H. (2021) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.0c20418 · Cited by 105
Dong, X., Luo, X., Zhao, H., Qiao, C., Li, J., Yi, J., Yang, L., Oropeza, F. J., Hu, T. S., Xu, Q., et al. (2022) · Soft Matter · doi:10.1039/d2sm01067d · Cited by 99
Fang, J., Zhuang, Y., Liu, K., Chen, Z., Liu, Z., Kong, T., Xu, J., & Cheng, Q. (2022) · Advanced Science · doi:10.1002/advs.202104347 · Cited by 88
Static Shape Control of Soft Continuum Robots Using Deep Visual Inverse Kinematic Models
Almanzor, E., Ye, F., Shi, J., Thuruthel, T. G., Wurdemann, H. A., & Iida, F. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3275375 · Cited by 85
“soft robots, where they have been employed for learning an accurate forward dynamics model [55], [56], [57] or for directly learning a closed-loop control policy using reinforcement learn-”
MethodLearning-Based Control Strategies for Soft Robots: Theory, Achievements, and Future Challenges
Laschi, C., Thuruthel, T. G., Lida, F., Merzouki, R., & Falotico, E. (2023) · IEEE Control Systems · doi:10.1109/mcs.2023.3253421 · Cited by 84
“Hence, learning-based approaches have been ubiquitously preferred for modelling soft sensory systems [83], [84], [85].”
BackgroundA retrofit sensing strategy for soft fluidic robots
Zou, S., Picella, S., de Vries, J., Kortman, V. G., Sakes, A., & Overvelde, J. T. B. (2024) · Nature Communications · doi:10.1038/s41467-023-44517-z · Cited by 82
“Moving forward, machine learning can potentially be applied to readthehigher-orderdifferenceinthepressure-timecurvesofthesoft robot for various interactions with the environment to achieve more complex sensing applications 12,56 .”
BackgroundFluidic innervation sensorizes structures from a single build material
Truby, R. L., Chin, L., Zhang, A., & Rus, D. L. (2022) · Science Advances · doi:10.1126/sciadv.abq4385 · Cited by 80
“Despite an increasing focus on data-driven approaches for solving longstanding challenges in soft robot control (21, 23, 24, 37, 38), the robustness and reliability of current soft robotic actuation and sensing strategies limit the size of datasets that can be acquired for proprioceptively determining shape or kinemat…”
BackgroundAnthropomorphic Twisted String-Actuated Soft Robotic Gripper With Tendon-Based Stiffening
Konda, R., Bombara, D. J., Swanbeck, S., & Zhang, J. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3224774 · Cited by 79
“For this purpose, advanced motion planning and grasping algorithms that utilize machine learning techniques [72], [73] could be developed.”
MethodA highly stretchable hydrogel sensor for soft robot multi-modal perception
Wang, S., Sun, Z., Zhao, Y., & Zuo, L. (2021) · Sensors and Actuators A Physical · doi:10.1016/j.sna.2021.113006 · Cited by 76
Guiding the design of superresolution tactile skins with taxel value isolines theory
Sun, H., & Martius, G. (2022) · Science Robotics · doi:10.1126/scirobotics.abm0608 · Cited by 75
“For typical applications, a resolution is desirable that would imply numerous taxels ( 4 , 5 , 7 – 11 ); this is true both for small surface sensing, e.g., at the fingertips, and for large surfaces, e.g., around limbs.”
BackgroundPark, H., Gbadam, G. S., Niu, S., Ryu, H., & Lee, J. (2024) · International Journal of Extreme Manufacturing · doi:10.1088/2631-7990/ad88be · Cited by 72
Hydrogel and Machine Learning for Soft Robots’ Sensing and Signal Processing: A Review
Wang, S., & Sun, Z. (2022) · Journal of Bionic Engineering · doi:10.1007/s42235-022-00320-y · Cited by 71
“Machine learning (ML) is a promising approach to deal with the problem, since it is data-driven and can empirically approximate the unknown model [20, 21].”
BackgroundA Perspective on Miniature Soft Robotics: Actuation, Fabrication, Control, and Applications
Chi, Y., Zhao, Y., Hong, Y., Li, Y., & Yin, J. (2023) · Advanced Intelligent Systems · doi:10.1002/aisy.202300063 · Cited by 68
Sim-to-Real of Soft Robots With Learned Residual Physics
Gao, J., Michelis, M. Y., Spielberg, A., & Katzschmann, R. K. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3446287 · Cited by 67
“Previous work, however, has only worked with low-dimensional state spaces, and it has yet to be scaled up to the high degree-of-freedom meshes used in soft-body simulations [28].”
BackgroundVariable stiffness soft robotic gripper: design, development, and prospects
Yu, S., Zhao, Y., Wang, H., Dong, L., Pei, C., Jin, Z., Sun, Y., & Liu, T. (2023) · Bioinspiration & Biomimetics · doi:10.1088/1748-3190/ad0b8c · Cited by 64
“The mandate in the domain of con-trol is to coordinate the integration of signals received from sensors and execute actions consistent with predefined objectives [307].”
BackgroundSoft Robot Design, Manufacturing, and Operation Challenges: A Review
Ambaye, G. A., Boldsaikhan, E., & Krishnan, K. (2024) · Journal of Manufacturing and Materials Processing · doi:10.3390/jmmp8020079 · Cited by 58
Giordano, G., Carlotti, M., & Mazzolai, B. (2021) · Advanced Materials Technologies · doi:10.1002/admt.202100437 · Cited by 58
Zhang, S., Suresh, L., Yang, J., Zhang, X., & Tan, S. C. (2022) · Advanced Intelligent Systems · doi:10.1002/aisy.202100194 · Cited by 57
Research Progress in Electroactive Polymers for Soft Robotics and Artificial Muscle Applications
Dewang, Y., Sharma, V., Baliyan, V. K., Soundappan, T., & Singla, Y. K. (2025) · Polymers · doi:10.3390/polym17060746 · Cited by 55
From Molecules to Machines: A Multiscale Roadmap to Intelligent, Multifunctional Soft Robotics
Li, Y., Schreiber, S., Yang, H., Liu, M., Little, J. M., Cao, W., Luo, Y., Bao, Y., Shih, C., Bai, H., et al. (2025) · Chemical Reviews · doi:10.1021/acs.chemrev.4c00972 · Cited by 55
A fabrication strategy for millimeter-scale, self-sensing soft-rigid hybrid robots
Lee, H. C., Elder, N., Leal, M., Stantial, S., Martinez, E. V., Jos, S., Cho, H., & Russo, S. (2024) · Nature Communications · doi:10.1038/s41467-024-51137-8 · Cited by 54
“Whereas the latter is a data-driven approach, which predictsandcontrolstherobotusingmachinelearningtechniques 48,49 .”
BackgroundProbabilistic Modeling and Bayesian Filtering for Improved State Estimation for Soft Robots
Kim, D., Park, M., & Park, Y. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3060335 · Cited by 54
A Sea-Anemone-Inspired, Multifunctional, Bistable Gripper
Qi, Q., Xiang, C., Ho, V. A., & Rossiter, J. M. (2021) · Soft Robotics · doi:10.1089/soro.2020.0176 · Cited by 53
Sun, Z., Wang, S., Zhao, Y., Zhong, Z., & Zuo, L. (2022) · Advanced Intelligent Systems · doi:10.1002/aisy.202200089 · Cited by 51
Jin, L., Zhai, X., Xue, W., Zhang, K., Jiang, J., Bodaghi, M., & Liao, W. (2025) · Smart Materials and Structures · doi:10.1088/1361-665x/adadcd · Cited by 50
Soft Optical Waveguides for Biomedical Applications, Wearable Devices, and Soft Robotics: A Review
Wang, X., Li, Z., & Su, L. (2023) · Advanced Intelligent Systems · doi:10.1002/aisy.202300482 · Cited by 48
Safety Guarantees for Neural Network Dynamic Systems Via Stochastic Barrier Functions
Mazouz, R., Muvvala, K., Babu, A. R., Laurenti, L., & Lahijanian, M. (2022) · neural information processing systems · doi:10.52202/068431-0703 · Cited by 45
A Vision-Based Sensing Approach for a Spherical Soft Robotic Arm
Hofer, M., Sferrazza, C., & D’Andrea, R. (2021) · Frontiers in Robotics and AI · doi:10.3389/frobt.2021.630935 · Cited by 45
“An overview of such applications for sensing and control is provided in Chin et al. (2020).”
BackgroundAll the Feels: A Dexterous Hand With Large-Area Tactile Sensing
Bhirangi, R., DeFranco, A., Adkins, J., Majidi, C., Gupta, A., Hellebrekers, T., & Kumar, V. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3327619 · Cited by 45
“Collecting data from real-world interactions, on the other hand, is difficult due to the absence of an affordable, reliable hand that can handle the demands of large-scale data collection.”
BackgroundSelf-citationRod models in continuum and soft robot control: a reviewPreprint
Alessi, C., Agabiti, C., Caradonna, D., Laschi, C., Renda, F., & Falotico, E. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.05886 · Cited by 44
“Unlike analytical methods, which require explicit geometrical and physical descriptions of the robot mechanics, ML only requires training artificial neural networks (ANNs) on descriptive motion data to approximate the map between actuation and task space [23].”
Embodied AI for dexterity-capable construction Robots: DEXBOT framework
You, H., Zhou, T., Zhu, Q., Ye, Y., & Du, J. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102572 · Cited by 39
Pushing with Soft Robotic Arms via Deep Reinforcement Learning
Alessi, C., Bianchi, D., Stano, G., Cianchetti, M., & Falotico, E. (2024) · Advanced Intelligent Systems · doi:10.1002/aisy.202300899 · Cited by 39
Task space adaptation via the learning of gait controllers of magnetic soft millirobots
Demir, S. Ö., Çulha, U., Karacakol, A. C., Pena‐Francesch, A., Trimpe, S., & Sitti, M. (2021) · The International Journal of Robotics Research · doi:10.1177/02783649211021869 · Cited by 39
“Our approach is not only limited to walking gait learning and it can further be applied to different locomotion and manipulation controllers for soft robots (Chin et al., 2020).”
BackgroundUsing Redundant and Disjoint Time-Variant Soft Robotic Sensors for Accurate Static State Estimation
Thuruthel, T. G., Hughes, J., Georgopoulou, A., Clemens, F. J., & Iida, F. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3061399 · Cited by 38
“Recent advancements in machine learning can be an alternate solution to handling the nonlinear time-variant dynamics of these soft sensors [15], [16].”
BackgroundControlling diverse robots by inferring Jacobian fields with deep networks
Li, S., Zhang, A., Chen, B., Matusik, H., Liu, C., Rus, D. L., & Sitzmann, V. (2025) · Nature · doi:10.1038/s41586-025-09170-0 · Cited by 37
“Prior work has leveraged machine learning [17, 18, 19, 20, 21] and marker-based visual servoing [22, 23, 24, 25, 26] to overcome these challenges, but requires extensive expert-guided customization to be applied to a particular robot architecture.”
A Learning-Based Approach to Sensorize Soft Robots
Ang, B. W. K., & Yeow, C. (2022) · Soft Robotics · doi:10.1089/soro.2020.0172 · Cited by 35
“42 Machine learning can also act as function ap-proximators toward the learning of soft robotic kinematics and dynamics, 42,43 which are difficult problems that analytical methods cannot solve.”
Learning Controllers for Continuum Soft Manipulators: Impact of Modeling and Looming Challenges
Falotico, E., Donato, E., Alessi, C., Setti, E., Nazeer, M. S., Agabiti, C., Caradonna, D., Bianchi, D., Piqué, F., Ansari, Y. T., et al. (2024) · Advanced Intelligent Systems · doi:10.1002/aisy.202400344 · Cited by 34
Deep Learning Methods in Soft Robotics: Architectures and Applications
Čakurda, T., Trojanová, M., Pomin, P., & Hošovský, A. (2024) · Advanced Intelligent Systems · doi:10.1002/aisy.202400576 · Cited by 34
Vision-Based Sensing for Electrically-Driven Soft Actuators
Zhang, A., Truby, R. L., Chin, L., Li, S., & Rus, D. L. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3201604 · Cited by 34
“and fabricating soft sensorized robots with high spatiotemporal resolution sensing [1], [5].”
BackgroundContinuum-Body-Pose Estimation From Partial Sensor Information Using Recurrent Neural Networks
Tanaka, K., Minami, Y., Tokudome, Y., Inoue, K., Kuniyoshi, Y., & Nakajima, K. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3199034 · Cited by 33
“This forms a type of indirect sensing task and learning from these relationships from the data has often been done using machine learning approaches [12], [13], [14].”
MethodDielectric Elastomer-Based Actuators: A Modeling and Control Review for Non-Experts
Medina, H., Farmer, C., & Liu, I. (2024) · Actuators · doi:10.3390/act13040151 · Cited by 33
Data‐Driven Navigation of Ferromagnetic Soft Continuum Robots Based on Machine Learning
Ni, Y., Sun, Y., Zhang, H., Li, X., Zhang, S., & Li, M. (2023) · Advanced Intelligent Systems · doi:10.1002/aisy.202200167 · Cited by 32
A review on self-healing featured soft robotics
Islam, M. A., Talukder, L., Al, M. F., Sarker, S. K., Muyeen, S. M., Das, P., Hasan, M. M., Das, S. K., Islam, M. M., Islam, M. R., et al. (2023) · Frontiers in Robotics and AI · doi:10.3389/frobt.2023.1202584 · Cited by 31
“Carnegie Mellon University’s Morphing Matter Lab has found promising robot applications in this sector (Chin et al., 2020).”
BackgroundTang, Z. Q., Xin, W., Wang, P., & Laschi, C. (2024) · Soft Robotics · doi:10.1089/soro.2023.0116 · Cited by 31
Soft Robot Proprioception Using Unified Soft Body Encoding and Recurrent Neural Network
Wang, L., Lam, J., Chen, X., Li, J., Zhang, R., Su, Y., & Wang, Z. (2023) · Soft Robotics · doi:10.1089/soro.2021.0056 · Cited by 31
“37 For examples, Kim et al. handled the noise of the sensor output with probabilistic modeling and characterized the hysteresisusingaBayesiannetwork.”
Yao, S., Tang, R., Bai, L., Yan, H., Ren, H., & Liu, L. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3288245 · Cited by 30
Cyber-physical systems in water management and governance
Alexandra, C., Daniell, K. A., Guillaume, J., Saraswat, C., & Feldman, H. R. (2023) · Current Opinion in Environmental Sustainability · doi:10.1016/j.cosust.2023.101290 · Cited by 29
Anthropomorphic Soft Hand: Dexterity, Sensing, and Machine Learning
Wang, Y., Hao, T., Liu, Y., Xiao, H., Liu, S., & Zhu, H. (2024) · Actuators · doi:10.3390/act13030084 · Cited by 29
“Second, the control systems of soft hands are relatively complex, potentially requiring advanced algorithms and sensing technologies to achieve fine manipulation similar to human hands [21,22].”
BackgroundIntelligent sensory systems toward soft robotics
Luo, Z., Cheng, W., Zhao, T., & Xiang, N. (2024) · Applied Materials Today · doi:10.1016/j.apmt.2024.102122 · Cited by 29
Gaining a Sense of Touch Object Stiffness Estimation Using a Soft Gripper and Neural Networks
Bednarek, M., Kicki, P., Bednarek, J., & Walas, K. (2021) · Electronics · doi:10.3390/electronics10010096 · Cited by 28
“The extensive overview of machine learning methods in the soft robotics aspect is described in [22].”
MethodShu, J., Wang, J., Lau, S. C. Y., Su, Y., Heung, H. L., Shi, X., Li, Z., & Tong, R. K. (2022) · Sensors · doi:10.3390/s22207705 · Cited by 26
“This neural network can calibrate the sensor in one step when there is a reliable training dataset [4] while solving the problem with the kirigami-inspired sensors of nonlinearity, hysteresis and stress relaxation properties [35].”
MethodModel Learning With Backlash Compensation for a Tendon-Driven Surgical Robot
Cursi, F., Bai, W., Yeatman, E. M., & Kormushev, P. S. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3187519 · Cited by 26
“Thus far these nonlinearities have generally been neglected or treated as unmodelled noise [23].”
BackgroundStudier‐Fischer, A., Bressan, M., Qasim, A. B., Özdemir, B., Sellner, J., Seidlitz, S., Haney, C. M., Egen, L., Michel, M. S., Dietrich, M., et al. (2024) · Scientific Reports · doi:10.1038/s41598-024-68280-3 · Cited by 25
Paleoinspired robotics as an experimental approach to the history of life
Ishida, M., Berio, F., Santo, V. D., Shubin, N. H., & Iida, F. (2024) · Science Robotics · doi:10.1126/scirobotics.adn1125 · Cited by 25
“Control engineering and machine learning techniques can also be used to understand how adaptive actuator con-trol can evolve along with morphological evolution ( 108 ).”
BackgroundAner, E. A., Shehata, O. M., Awad, M. I., & ElHady, N. E. (2025) · Journal of Bionic Engineering · doi:10.1007/s42235-025-00819-0 · Cited by 24
Online Pressure Map Reconstruction in a Multitouch Soft Optical Waveguide Skin
Preti, M. L., Totaro, M., Falotico, E., Crepaldi, M., & Beccai, L. (2022) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2022.3158979 · Cited by 23
“For example, how to deal with spatiotemporal nonlinearities of soft systems and how to properly train general machine learning models [40].”
BackgroundComposite Soft Pneumatic Actuators Using 3D Printed Skins
Bhat, A., Ambrose, J. W., & Yeow, C. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3246841 · Cited by 23
“Some potential methods of achieving this in the future include using integrated sensing [50], [51], or mathematical modeling [52], or learning-based methods [53].”
MethodPreechayasomboon, P., & Rombokas, E. (2021) · Actuators · doi:10.3390/act10020030 · Cited by 23
“Our method is only one of a class of methods for using machine learning to make the most of complex soft robotic sensors [30,31].”
MethodAblation Study of a Dynamic Model for a 3D-Printed Pneumatic Soft Robotic Arm
Alessi, C., Falotico, E., & Lucantonio, A. (2023) · IEEE Access · doi:10.1109/access.2023.3266282 · Cited by 22
“Then, artificial neural networks trained with machine learning algorithms map actuation to task space [6].”
MethodGeorgopoulou, A., Hardman, D., Thuruthel, T. G., Iida, F., & Clemens, F. J. (2023) · Advanced Science · doi:10.1002/advs.202301590 · Cited by 22
Soft touchless sensors and touchless sensing for soft robots
Sirithunge, C., Wang, H., & Iida, F. (2024) · Frontiers in Robotics and AI · doi:10.3389/frobt.2024.1224216 · Cited by 22
“To interpret sensor information, machine learning techniques have been utilized to decode the physical deformation of the mechanical structure (Chin et al., 2020).”
MethodEyvazian, A., Song, Y., Chibukhchyan, H. S., Savari, A., & Singh, N. S. S. (2025) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2025.102264 · Cited by 21
Machine Learning Best Practices for Soft Robot Proprioception
Zhang, A., Wang, T.-H. J., Truby, R. L., Chin, L., & Rus, D. L. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342379 · Cited by 21
“Specifically, key challenges in learning-based approaches to soft robotics include dealing with history-dependent time series data, choosing an appropriate way to represent and sample the data, and picking a suitable model architecture and training configuration [3].”
BackgroundVariable Stiffness Object Recognition with a CNN-Bayes Classifier on a Soft Gripper
Huang, J., & Rosendo, A. (2022) · Soft Robotics · doi:10.1089/soro.2021.0105 · Cited by 21
Multi-modal Sensor Fusion for Learning Rich Models for Interacting Soft Robots
Thuruthel, T. G., & Iida, F. (2023) · IEEE International Conference on Soft Robotics (RoboSoft) · doi:10.1109/robosoft55895.2023.10121992 · Cited by 21
Model-Based Robust Position Control of an Underactuated Dielectric Elastomer Soft Robot
Soleti, G., Massenio, P. R., Kunze, J., & Rizzello, G. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3539184 · Cited by 20
Xu, B., Li, M., Li, M., Fang, H., Wang, Y., Sun, X., Guo, Q., Wang, Z., Liu, Y., & Chen, D. (2022) · Micromachines · doi:10.3390/mi13030404 · Cited by 20
Automatically-Tuned Model Predictive Control for an Underwater Soft Robot
Null, W. D., Edwards, W., Jeong, D., Tchalakov, T., Menezes, J., Hauser, K. K., & Zhang, Y. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3333662 · Cited by 20
“Data-driven methods show promise in meeting these challenges because of their ability to capture nuanced characteristics of dynamics that are difficult to model analytically [3], [4], [10].”
MethodSafe Supervisory Control of Soft Robot Actuators
Sabelhaus, A. P., Patterson, Z. J., Wertz, A., & Majidi, C. (2024) · Soft Robotics · doi:10.1089/soro.2022.0131 · Cited by 20
“In addition to physical safety, SMA actuators in particular are known to suffer from degradation due to thermal and mechanical cycling, 17,37–39 which when viewed as a temperature constraint 40 can also be formulated as a safe control problem.”
Self-citationSoft Wearable Haptic Display and Flexible 3D Force Sensor for Teleoperated Surgical Systems
Thai, M. T., Davies, J., Nguyen, C. C., Phan, P. T., Hoang, T. T., Ji, A., Zhu, K., Sharma, B., Nicotra, E., Vo‐Doan, T. T., et al. (2023) · Advanced Sensor Research · doi:10.1002/adsr.202300105 · Cited by 18
Drift‐Aware Feature Learning Based on Autoencoder Preprocessing for Soft Sensors
Wang, J., Shu, J., Alam, M. M., Gao, Z., Li, Z., & Tong, R. K. (2024) · Advanced Intelligent Systems · doi:10.1002/aisy.202300486 · Cited by 18
Large‐Scale Surface Shape Sensing with Learning‐Based Computational Mechanics
Wang, K., Mak, C., Ho, J., Liu, Z., Sze, K. Y., Wong, K. K. Y., Althoefer, K. A., Liu, Y., Fukuda, T., & Kwok, K. (2021) · Advanced Intelligent Systems · doi:10.1002/aisy.202100089 · Cited by 18
Sarkar, S., Gundecha, V., Ghorbanpour, S., Shmakov, A., Babu, A. R., Pichard, A., & Cocho, M. (2022) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case49997.2022.9926561 · Cited by 17
“Recent advancement in AI has enabled controllers in various domains to model and learn the complex representation of data and can efficiently model the movements of the structure and adjust themselves to stabilize [31][32].”
BackgroundIntegrated and Intelligent Soft Robots
Hao, T., Xiao, H., Ji, M., Liu, Y., & Liu, S. (2023) · IEEE Access · doi:10.1109/access.2023.3314513 · Cited by 17
“It is crucial to note that machine learning is a suitable technique for extracting nonlinear control models [110], [111].”
MethodHigh-sensitivity omnidirectional recognition strain sensor based on two-dimensional materials
Fu, C., Rong, C., Zhang, B., & Xuan, F. (2024) · Nano Research · doi:10.26599/nr.2025.94907411 · Cited by 17
Soft Robotics for Parkinson’s Disease Supported by Functional Materials and Artificial Intelligence
Mazumdar, H., Khondakar, K. R., Das, S., & Kaushik, A. K. (2025) · BME Frontiers · doi:10.34133/bmef.0143 · Cited by 17
Use of Finite Elements in the Training of a Neural Network for the Modeling of a Soft Robot
Terrile, S., López, A., & Barrientos, A. (2023) · Biomimetics · doi:10.3390/biomimetics8010056 · Cited by 17
“In this context, machine learning (ML) is postulated as a promising option for modeling the robot, actuator, and control [8,9].”
BackgroundA Deep Learning Framework for Soft Robots with Synthetic Data
Sapai, S., Loo, J. Y., Ding, Z. Y., Tan, C. P., Baskaran, V. M., & Nurzaman, S. G. (2023) · Soft Robotics · doi:10.1089/soro.2022.0188 · Cited by 17
“21,22 Furthermore, for some potential soft robot applications such as underwater exploration or surgical robotics, data collection processes can be expensive and limited.”
Composites of functional polymers: Toward physical intelligence using flexible and soft materials
Ford, M. J., Ohm, Y., Chin, K., & Majidi, C. (2021) · Journal of materials research/Pratt's guide to venture capital sources · doi:10.1557/s43578-021-00381-5 · Cited by 17
Self-citationDeep Learning for Strain Field Customization in Bioreactor with Dielectric Elastomer Actuator Array
Wang, J., Sarkar, D., Mohan, A., Lee, M., Ma, Z., & Chortos, A. (2024) · Cyborg and Bionic Systems · doi:10.34133/cbsystems.0155 · Cited by 16
“In recent years, the emergence of machine learning technology has revolutionized control and sensing within the soft robotics domain [32,33].”
BackgroundSelf-Healing Soft Robots: Materials, Sensors and Integrated Systems
Jeong, Y., Majidi, C., & Ko, S. H. (2025) · International Journal of Precision Engineering and Manufacturing · doi:10.1007/s12541-025-01272-z · Cited by 16
“Chin et al. proposed a machine learning-based approach for sensor and system characterization to overcome soft robots’ time-dependent and non-linear characteristics [96].”
Self-citationExploiting mechanical sensing in deformed surface and interface towards soft robots
Jin, H., Zhu, Z., Li, H., Kang, N., Mansori, M. E., & Zhang, W. (2025) · Advances in Colloid and Interface Science · doi:10.1016/j.cis.2025.103600 · Cited by 15
Intelligent Shape Decoding of a Soft Optical Waveguide Sensor
Mak, C.-H., Li, Y., Wang, K., Wu, M., Ho, J., Dou, Q., Sze, K. Y., Althoefer, K. A., & Kwok, K. (2023) · Advanced Intelligent Systems · doi:10.1002/aisy.202300082 · Cited by 15
Materializing Autonomy in Soft Robots across Scales
Berrueta, T. A., Murphey, T. D., & Truby, R. L. (2023) · Advanced Intelligent Systems · doi:10.1002/aisy.202300111 · Cited by 15
Metadata
- Authors
- Chin, K., Hellebrekers, T., & Majidi, C.
- Affiliations
- Carnegie Mellon University (US)
- Corresponding author
- Majidi, Carmel
- Venue
- Advanced Intelligent Systems
- Publisher
- Wiley
- Published
- 2020-03-03
- Volume
- 2
- Issue
- 6
- ISSN
- 2640-4567 (ISSN-L)
- OpenAlex
- W3002768791
- Cited by
- 215
- References
- 41
- Citations by year
- 2026: 17 · 2025: 43 · 2024: 44 · 2023: 40 · 2022: 34 · 2021: 32 · 2020: 5
- FWCI
- 8.71
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Advanced Intelligent Systems (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Science Foundation (1252522)
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Soft Robotics and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Mechanical Engineering › Advanced Materials and Mechanics
- Keywords
- soft robotics, machine learning, data-driven modeling, function approximation, hysteresis, supervised learning, reinforcement learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.