Machine Learning Driven Prediction of the Behavior of Biohybrid Actuators
Authors: Michail-Antisthenis Tsompanas, Marco Perez Hernandez, Faisal Abdul-Fattah, Karim Elhakim, Mostafa Ibrahim, Judith Fuentes, Florencia Lezcano, Riccardo Collu, Massimo Barbaro, Stefano Lai, Samuel Sanchez, Andrew Adamatzky
Organizations: Unconventional Computing Laboratory & School of Computing & Creative Technologies, College of Arts, Technology and Environment, University of the West of England, Bristol, BS16 1QY, United Kingdom · School of Computing & Creative Technologies, College of Arts, Technology and Environment, University of the West of England, Bristol, BS16 1QY, United Kingdom · Institute for Bioengineering of Catalonia (IBEC), The Barcelona Institute for Science and Technology (BIST), Barcelona, Spain · Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy · Instituciò Catalana de Recerca i Estudis Avancats (ICREA) and Institute for Bioengineering of Catalonia (IBEC), The Barcelona Institute for Science and Technology (BIST), Barcelona, Spain · Unconventional Computing Laboratory, College of Arts, Technology and Environment, University of the West of England, Bristol, BS16 1QY, United Kingdom
Skeletal muscle-based biohybrid actuators have proved to be a promising component in soft robotics, offering efficient movement. However, their intrinsic biological variability and nonlinearity pose significant challenges for controllability and predictability. To address these issues, this study investigates the application of supervised learning, a form of machine learning, to model and predict the behavior of biohybrid machines (BHMs), focusing on a muscle ring anchored on flexible polymer pillars. First, static prediction models (i.e., random forest and neural network regressors) are trained to estimate the maximum exerted force achieved from input variables such as muscle sample, electrical stimulation parameters, and baseline exerted force. Second, a dynamic modeling framework, based on Long Short-Term Memory networks, is developed to serve as a digital twin, replicating the time series of exerted forces observed in response to electrical stimulation. Both modeling approaches demonstrate high predictive accuracy. The best performance of the static models is characterized by R2 of 0.9425, whereas the dynamic model achieves R2 of 0.9956. The static models can enable optimization of muscle actuator performance for targeted applications and required force outcomes, while the dynamic model provides a foundation for developing robustly adaptive control strategies in future biohybrid robotic systems.
Figures & tables
Stimulation Frequency
Amount of experiments
50
69
30
48
20
30
35
12
70
1
25
1
Table 1: Stimulation Frequency distribution on the dataset.
Stimulation Pulse Width
Amount of experiments
15
53
5
41
20
17
10
15
8
13
40
10
Table 2: Stimulation Pulse Width distribution on the dataset.
Figure 1: RFR model accuracy and residual analysis for predicted force, (A) scatter plot of actual versus predicted values and (B) residual distribution.
Figure 2: NN model accuracy and residual analysis for predicted force, (A) scatter plot of actual versus predicted values and (B) residual distribution.
Figure 3: Updated NN model accuracy and residual analysis for predicted force, (A) scatter plot of actual versus predicted values and (B) residual distribution.
Figure 4: Four examples of input windows of 10 data points, the true next value of force and the predicted one that LSTM provides after training.
Figure 5: The actual time series for biphasic asymmetric charge-balanced experiment with pulse modulation between [2ms,10ms] at 30Hz and the forecast time series provided by LSTM.
Figure 6: The first 100 time steps of the actual time series for the experiment presented in Fig 5 and the forecast time series provided by LSTM.
Figure 7: Electrical stimulation patterns and setup. (A) Stimulation was performed using four different waveforms. (B) Stimulation was performed using a portable stimulator [ 7 ] . (C) The biohybrid actuator was placed inside a Petri dish and mounted on two movable pillars. Electrical stimulation caused the muscle bioactuator to contract, inducing movement of the pillars. (D) The stimulation parameters were modulated using linear modulation following a ramp or staircase pattern.
Understanding human motion beyond surface kinematics is crucial for motion analysis, rehabilitation, and injury risk assessment. However, progress in this domain is limited by the lack of large-scale datasets with biomechanical annotations, and by existing approaches that cannot directly infer internal biomechanical states from visual observations. In this paper, we introduce a simulation-based framework for estimating muscle activations from existing motion capture datasets, resulting in BioHuman10M, a large-scale dataset with synchronized video, motion, and activations. Building on BioHuman10M, we propose BioHuman, an end-to-end model that takes monocular video as input and jointly predicts human motion and muscle activations, effectively bridging visual observations and internal biomechanical states. Extensive experiments demonstrate that BioHuman enables accurate reconstruction of both kinematic motion and muscle activity, and generalizes across diverse subjects and motions. We believe our approach establishes a new benchmark for video-based biomechanical understanding and opens up new possibilities for physically grounded human modeling.
Yujun Huo, He Zhang, Chentao Song +3
Beihang University, China · Tsinghua University, China
Human locomotion emerges from high-dimensional neuromuscular control, making predictive musculoskeletal simulation challenging. We present a physiology-informed reinforcement-learning framework that constrains control using muscle synergies. We extracted a low-dimensional synergy basis from inverse musculoskeletal analyses of a small set of overground walking trials and used it as the action space for a muscle-driven three-dimensional model trained across variable speeds, slopes and uneven terrain. The resulting controller generated stable gait from 0.7-1.8 m/s and on ± 6∘ grades and reproduced condition-dependent modulation of joint angles, joint moments and ground reaction forces. Compared with an unconstrained controller, synergy-constrained control reduced non-physiological knee kinematics and kept knee moment profiles within the experimental envelope. Across conditions, simulated vertical ground reaction forces correlated strongly with human measurements, and muscle-activation timing largely fell within inter-subject variability. These results show that embedding neurophysiological structure into reinforcement learning can improve biomechanical fidelity and generalization in predictive human locomotion simulation with limited experimental data.
Ilseung Park, Eunsik Choi, Jangwhan Ahn +1
Carnegie Mellon University · Department of Physical Education, Seoul National University, Seoul, Republic of Korea · Seoul National University +2
In this paper, we introduce a consistency-driven dual LSTM framework for accurately learning both the forward and inverse kinematics of a pneumatically actuated soft robotic arm integrated into a wearable device. This approach effectively captures the nonlinear and hysteretic behaviors of soft pneumatic actuators while addressing the one-to-many mapping challenge between actuation inputs and end-effector positions. By incorporating a cycle consistency loss, we enhance physical realism and improve the stability of inverse predictions. Extensive experiments-including trajectory tracking, ablation studies, and wearable demonstrations-confirm the effectiveness of our method. Results indicate that the inclusion of the consistency loss significantly boosts prediction accuracy and promotes physical consistency over conventional approaches. Moreover, the wearable soft robotic arm demonstrates strong human-robot collaboration capabilities and adaptability in everyday tasks such as object handover, obstacle-aware pick-and-place, and drawer operation. This work underscores the promising potential of learning-based kinematic models for human-centric, wearable robotic systems.
Xingyu Chen, Yi Xiong, Li Wen
School of Mechanical Engineering and Automation, Beihang University, Beijing 100191, China