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
Items 201–238 of 238
Tanaka, K., Takahashi, T., & Hamaya, M. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11245913 · Cited by 1
“Many studies have investigated arms composed of soft materials (e.g., silicone rubbers) using embedded proprioceptive sensors to infer arm configuration, frequently applying machine learning techniques to relate sensor outputs to arm posture [15], [16], [17].”
Multi-Modal Sensing in Colonoscopy: A Data-Driven Approach
Bono, V. D., Capaldi, E., Kelshiker, A., Aktas, A., Aihara, H., & Russo, S. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3645700 · Cited by 1
Clearance size detection based on deep neural networks without feature extraction
Nguyen, T. V., Rodríguez, A. J., González, F., Mikkola, A., Kim, J., & Orzechowski, G. (2026) · Multibody System Dynamics · doi:10.1007/s11044-026-10163-8 · Cited by 1
“Furthermore, data-driven methods are particularly suited for systems with unknown, impractical, or computationally intractable governing functions, as shown by their use in soft robotics for modeling the complex, nonlinear behavior of compliant materials [18].”
Soft robotics gripper technology in medical surgery application: a systematic literature review
Saputra, I. G. N. P. W. E., Fajrin, A., Lubis, U. S., & Efendi, A. (2026) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-026-00538-7 · Cited by 1
“However, recent studies demonstrate that machine learning–based control frameworks can enhance adaptive behavior in response to tissue deformation and motion (Zhu et al. 2021; Shademan et al. 2016; Chin et al. 2020).”
InfluentialZhang, J., Yu, J., Chen, Y., Tian, Y., Zhang, Q., Sun, J., Yu, X., Li, S., & Gong, Y. (2026) · Journal of Zhejiang University. Science A · doi:10.1631/jzus.a2500507 · Cited by 1
Lightweight framework for time-varying error compensation in soft strain sensors
Phan, M. T., Dao, P. L., Ngo, S. T., Phan, N. A., Cao, P., Krishnan, G., Hsiao‐Wecksler, E. T., Pham, H., & Thai, M. T. (2026) · Sensors and Actuators Reports · doi:10.1016/j.snr.2026.100499 · Cited by 1
LEARNING SOFT ROBOT AND SOFT ACTUATOR DYNAMICS USING DEEP NEURAL NETWORK
Thanabalan, H. P. (2021) · International Journal of Engineering Applied Sciences and Technology · doi:10.33564/ijeast.2021.v05i09.003 · Cited by 1
“Paper proposed by (Chin, et al., 2020) where data from the physical environment was gathered using soft sensors and transducing these data into a signal that converts the information.”
MethodA Flexible 3D Force Sensor with In-Situ Tunable Sensitivity
Davies, J., Thai, M. T., Hoang, T. T., Nguyen, C. C., Phan, P. T., Zhu, K., Tran, D. B. N., Ho, V. A., La, H. M., Ha, Q. P., et al. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160637 · Cited by 1
“To achieve a higher accuracy in line with the repeatability of the force sensing device, a better NN model and more data sets should be used [44].”
MethodSoft Humanoid Finger with Magnetic Tactile Perception
Ding, X., Shan, J., Xia, Z., Sun, F., & Fang, B. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-6495-6_5 · Cited by 1
Length Modelling of Spiral Superficial Soft Strain Sensors Using Geodesics and Covering Spaces
Al-Azzawi, A., Stadler, P., Kong, H., & Sukkarieh, S. (2023) · Robotics · doi:10.3390/robotics12060164 · Cited by 1
Banerjee, H., Hammoumi, A., Baudino, C., Borot, M., Corcelle, J., Laperrousaz, S., & Sorin, F. (2025) · IEEE International Conference on Soft Robotics (RoboSoft) · doi:10.1109/robosoft63089.2025.11020888 · Cited by 1
Theory of Geometric Super-resolution for Haptic Sensor Design.Preprint
Sun, H., & Martius, G. (2021) · arXiv (Cornell University) · Cited by 1
Dynamic Modeling and MPC for Locomotion of Tendon-Driven Soft QuadrupedPreprint
Karan, S., Maram, N., Borate, S., & Vadali, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.16371 · Cited by 1
“Supervised learning can capture complex input-output mappings but demands large labeled datasets [13].”
Machine Learning and Optimization Applications for Soft Robotics
İlman, M. M., & Taşer, P. Y. (2022) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-6684-5381-0.ch002
Compressing Multiple Sensor Signals for Distributed Sensing by Autoencoder Preprocessing
Wang, J., Shu, J., Li, Z., Yu, H., & Tong, R. K. (2023) · International Conference on Control and Robotics (ICCR) · doi:10.1109/iccr60000.2023.10444858
“To overcome the issue of high non-linearity and hysteresis, long short-term memory (LSTM) neural networks have been utilized as a solution to the regression problem [12].”
BackgroundMethodInfluentialCollaborative Human and Computer Controls of Smart Machines: Literature Review
Hussein, B., Bi, Z., Younis, N., & Abu-Mulaweh, H. I. (2024) · International Conference on Reconfigurable Mechanisms and Robots (ReMAR) · doi:10.1109/remar61031.2024.10617622
Wang, J., Shu, J., Li, Z., & Tong, R. K. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3444813
“Most soft robots are predominantly composed of viscoelastic materials, characterized by time-dependent properties such as hysteresis and drift [8].”
BackgroundDevelopment and Characterization of Tactile Capacitive Sensor for Soft Robotics Application
Srinivas, G. L. (2024) · International Conference on Control, Mechatronics and Automation (ICCMA) · doi:10.1109/iccma63715.2024.10843942
Motion control of soft actuators and robots
Liang, W., Cao, J., Zhu, W., & Ren, Q. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-314018-1.00011-0
Multimodal Deformation Estimation of Soft Pneumatic Gripper During Operation
Cai, C. S. S., Xiao, F., Vanza, M., Wang, T., Zhou, F., Xu, X., Zhu, J., & Gao, Y. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246764
“In response, researchers have started to leverage advances in deep learning to capture the complex and often nonlinear relationships between sensor observations and the soft robot’s state, achieving some success [17].”
Learning-based control and localization of magnetic soft millirobots
Demir, S. Ö. (2024) · OPUS Publication Server of the University of Stuttgart (University of Stuttgart) · doi:10.18419/opus-14687
OPTICAL SENSING FOR CONTROL OF SOFT ACTUATORS
Xu, A. (2023) · eCommons (Cornell University) · doi:10.7298/1znt-tm23
Development of A Vision-Based Foot Massage Robot
Ammer, D. (2023) · reposiTUm (TU Wien) · doi:10.34726/hss.2023.97160
Design of a pneumatic soft robotic actuator using model-based optimization
Raeisinezhad, M. (2021) · Rowan Digitals Works (Rowan University)
Development and Study of 3D Printed Compliant Sensors for Robot Proprioception
Chuen Hau, P. (2023) · DiVA (Digitala Vetenskapliga Arkivet)
Stiffness-Modulation of Multi-DoF Pneumatic Soft Actuator for Minimally Invasive Surgery
Yuxi, L. U. (2024) · Institutional Repositories DataBase (IRDB) · doi:10.20776/doctor-k7688
Probe-to-Grasp Manipulation Using Self-Sensing Pneumatic Variable-Stiffness JointsPreprint
Trần, N. D., Fan, Y., Dai, F., Nguyen, K., Nguyen, A., Ly, H. H., Ta, T. D., & Chiba, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.27808
“Estimating object stiffness is an important problem in robotics and haptics [7].”
Artificial intelligence in robotics, automation, and predictive maintenance for mechanical systems
Pourrahmani, H. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-45526-1.00010-6
Mata, E. S. O., Pylypovskyi, O. V., Raimondo, E., Illing, R., Zabila, Y., Guo, L., Mu, G., López, M. N., Wang, X., Tzortzinis, G., et al. (2026) · Advanced Intelligent Systems · doi:10.1002/aisy.70432
Comparison of Different Data-Driven Methods for Modeling Soft Robotic Sensors
Garg (2025) · IEEE MIT Undergraduate Research Technology Conference (URTC) · doi:10.1109/urtc68753.2025.11533082
“Researchers have explored ways to make soft sensing more efficient, such as by using embedded soft resistive sensors [7].”
Sankar, K., Sheeba, A. G., & Rajeev, G. K. M. (2026) · Research Square · doi:10.21203/rs.3.rs-9391711/v1
Module Number Adaptive Visual Shape Control for Serial Modular Soft RobotsPreprint
AKAMINE, K., Horii, T., Sakaue, Y., & Ishizuka, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.29547
“As an alternative, data-driven control methods based on deep learning and reinforcement learning have attracted increasing attention [11], [12].”
Low-cost soft robotic gripper – combining textile sensors and a lightweight hybrid CNN–LSTM model
Nguyen, D. T., Vu, C. C., Tran, T. Q. N., & Ca Van, P. H. A. N. (2026) · Materials & Design · doi:10.1016/j.matdes.2026.117008
Yin, R., Liu, C., Sun, Z., Sun, S., Liu, S., & Xiao, H. (2026) · Robotica · doi:10.1017/s0263574726103907
Machine Learning‐Assisted Soft Sensors: From Material Design to Motion Recognition
Sun, H., Fu, S., Hou, Y., Liu, J., Yang, Y., Tao, C., Cheng, X., Huang, Y., & Wang, J. (2026) · Advanced Functional Materials · doi:10.1002/adfm.78483
Jeong, D. (2023) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)
Act4R: Action-conditioned 4D reconstruction for kinematics-free controlPreprint
Zhang, Z., Yu, C., Shao, Z., Liu, X., & Peng, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.17462
“Subsequent machine learning approaches attempted to bypass these physical constraints by training end-to-end regressors to map pixels directly to actuator commands (Chin et al., 2020; Toshimitsu et al., 2022).”
Chimuka, B. A., & Li, H. (2026) · Proceedings of the Institution of Mechanical Engineers Part E Journal of Process Mechanical Engineering · doi:10.1177/09544089261497750
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.