Data-Driven Precision Control of Soft Helicoid Robots
Authors: Roshan S. Kaundinya, Mark Leone, Roberto Sabella, Hugo Buurmeijer, Luis Pabon, John Irvin Alora, Marco Pavone, George Haller
Organizations: Institute for Mechanical Systems, ETH Zürich, Leonhardstrasse 21, 8092, Zürich, Switzerland. · Department of Aeronautics and Astronautics, Stanford University, 496 Lomita Mall, Stanford, 94305, CA, USA. · Department of Industrial Engineering, University of Naples Federico II, P.le V. Tecchio, 80, 80125, Naples, Italy.
A purely data-driven method grounded in the theory of adiabatic spectral submanifolds (aSSMs) was recently used to model and control nonlinear soft robotic simulators. Here, we extend the methodology to learn aSSM-reduced models from data collected from hardware soft robotic platforms. Specifically, we learn a five dimensional (5D) aSSM-reduced nonlinear ordinary differential equation (ODE) that accurately models the dynamics of a soft-helicoid trunk robot. We then use this ODE in a model predictive control scheme to demonstrate real-time precision control across various challenging closed-loop trajectory-tracking tasks, ranging from 2D to 3D trajectories with static and dynamic constraints. We find that our methodology enhances accuracy and precision across all control tasks compared to available data-driven linear methods and model-free reinforcement learning. While we focus here on a soft-helicoid trunk robot, our methodology relies solely on hardware data and is therefore applicable to a broader class of soft robotic systems.
Figures & tables
Method
Model
Data
Training
Maximum
Constraints
Controller
dim. d
collection time
time
error [cm]
handling
freq. [Hz]
aSSM (ours)
5
2 hours
5 minutes
5
Yes
50
Koopman-pregain ( Haggerty et al., 2023 )
6
2 hours
30 seconds
38
No
100
DMDc ( Proctor et al., 2016 )
6
2 hours
30 seconds
18
Yes
100
MZ-Koopman ( Catalasan and He, 2026 )
33
2 hours
15 minutes
17
Yes
20
RL (PPO) ( Schulman et al., 2017 )
NA
6 hours
6 hours
10
No
100
Table 1: Comparison of data-driven aSSM-based modeling and control against linear and learning-based baselines for closed-loop 3D target tracking. The maximum error represents the maximum relative pointwise error obtained across all closed-loop tasks presented in Section 1.4 .
Figure 1: (a) Final optimized geometric parameters of the Trimmed Helicoid module. (b) The three-module soft helicoid trunk robot is vertically mounted. The end-effector and midpoint positions are motion-tracked using OptiTrack markers (gray). (c) Design space: Helix thickness ( P1 ), Trimming ratio ( P2 ), Revolutions ( P3 ), Microstructures ( P4 ).
Figure 2: Schematic for (a) the frozen limit of the aSSM geometry and (b) the dynamic aSSM geometry for time-varying control inputs.
Figure 3: (a) Step and random input sequence responses in the soft trunk’s observable space. (b) Filtered decay plots after pre-processing the step input dataset Ystep . (c) Predictions on previously unseen decay data of the leading-order aSSM-reduced model for static inputs. (d) Prediction of the aSSM-reduced model for unseen random control inputs using various approximations of the critical manifold L0 .
Figure 4: Closed-loop tracking results for a Figure-8 target (black) with the uncertainty band of width 3 [cm] plotted in gray.
Figure 5: Pointwise relative error for closed-loop tracking of a Figure-8 track with speed 9 [cm/s].
Figure 6: Pointwise relative error for closed-loop tracking of a faster Figure-8 track.
Figure 7: Closed-loop tracking results for a 3D Random track (black) with the uncertainty tube of radius 3 [cm] plotted in gray.
Figure 8: Hardware snapshots during closed-loop tracking of the 3 D Random track. See Supplementary Movie for all closed-loop hardware demonstrations.
Figure 9: Pointwise relative error for closed-loop tracking of a 3D Random track.
Figure 10: Closed-loop tracking results for a 3D Pacman track (black) with the uncertainty tube of radius 3 [cm] plotted in gray. The left panel shows results for the average speed along the target track of 3 [cm/s], and the right panel shows results for a speed that is 2 times faster.
Figure 11: Pointwise relative error for closed-loop tracking of a 3D Pacman track with speed 3 [cm/s].
Figure 12: Pointwise relative error for closed-loop tracking of a faster 3D Pacman track.
Figure 13: Snapshots for closed-loop avoidance of static spherical obstacles while simultaneously tracking a 3D Random track for (a) a small-sized spherical obstacle, and (b) a medium-sized spherical obstacle. Each plot contains closed-loop results for the 5D aSSM-reduced (green solid line), the 6D DMDc model (purple), the 33D MZ-Koopman model (yellow), and the 5D aSSM-reduced with deactivated constraints (green dotted line). The uncertainty tube of radius 3 [cm] is plotted in gray around the target track. The dark red sphere is the obstacle, and the translucent sphere shell surrounding it is a safety buffer zone with a width of 2.5 [cm].
Figure 14: (a) Snapshot for avoiding a large spherical obstacle while tracking the 3D Random target. (b) Pointwise relative error plots for the large-sized spherical obstacle avoidance task. The tolerance line accounts for the sphere’s location in real time as the target track is traversed.
Figure 15: Snapshots of the trunk main body avoiding a moving cylindrical obstacle at (a) t=5 [s] as it approaches the rest state and (b) t=15 [s] as the obstacle rotates near the rest state via aSSM-based closed-loop control. The trunk body is green, and the cylindrical obstacle is yellow.
Figure 16: Snapshots at (a) t=1 [s] and (b) t=3 [s] for the same closed-loop avoidance task same as Fig. ( 15 ), with a faster moving cylindrical obstacle.
Figure 1: Closed-loop tracking results for an extremely fast 3D Pacman track (black) with the uncertainty tube of radius 3 [cm] plotted in gray. The average instantaneous speed along the target track is 12 [cm/s].
Figure 2: Pointwise relative error plots for closed-loop tracking for a 3D Pacman track with speed 12 [cm/s]
Figure 3: Pointwise relative error plots for (a) the small-sized spherical obstacle and (b) the medium-sized spherical obstacle avoidance task. The tolerance line accounts for the sphere’s location in real time as the target track is traversed.
Figure 4: Snapshots of the trunk main body avoiding a moving cylindrical obstacle at (a) t=15 [s] as it approaches the rest state and (b) t=30 [s] as the obstacle moves up in the vertical direction. The trunk body is green, and the cylindrical obstacle is yellow.
Figure 5: Training reward curve for proximal policy optimization (PPO) on hardware. The solid gray line indicates the allowed uncertainty of −17.5 , computed by summing the maximum allowed positional uncertainty (3 cm tube radius, measured on hardware) across the 10-second episode.
Soft robots are commonly sought for safety-critical interactions in delicate environments, where accurate position and orientation control is imperative. Model predictive control (MPC) offers a solution, but it requires a model of the robot's infinite-dimensional nonlinear dynamics that is at once accurate and computationally cheap. Recent theory on adiabatic spectral submanifolds (aSSMs) and their applications to soft robots provide data-driven model-reduction methods to construct such models. Here, we extend these methods to identify aSSMs from enlarged observable datasets and upgrade the currently available aSSM-MPC schemes. Evaluated on a high-fidelity finite-element simulation of a pressure-actuated soft arm, our controller reduces position and orientation tracking error by more than 60% compared to existing data-driven baselines.
Aron Karakai, Roshan S. Kaundinya, Mike Yan Michelis +2
Automatic Control Laboratory, ETH Zurich, Switzerland · Institute for Mechanical Systems, ETH Zurich, Switzerland · Soft Robotics Laboratory and the ETH AI Center, ETH Zurich, Switzerland
Controlling the shape profile of soft trunk robots extends their reach into complex regions of the workspace and enhances their use in practical applications. Recent advances in soft robot design have enabled soft trunk robots to achieve greater flexibility in conforming to complex shapes. Specifically, trunk robots whose geometries are designed as helicoids have been shown to enable extreme shape-changing capabilities. Their compliance makes them highly nonlinear, which in turn makes shape control difficult. On similar tendon-driven trunk robots, model-based controllers based on the theory of adiabatic spectral submanifolds (aSSMs) have achieved high accuracy in closed-loop end-effector tracking. We extend this approach by learning an aSSM model of the full body of a trimmed-helicoid soft trunk robot from data and use this in a model predictive control (MPC) scheme to demonstrate a range of shape control tasks on hardware. On closed-loop dynamic shape regulation, our method outperforms the available linear baselines by a factor of 10. In human-in-the-loop interactive demos, our method completes section-by-section shaping and balances a tennis ball for over 25 seconds, while the linear baselines fall short. A model-free reinforcement learning policy trained for 12 hours on hardware fails on the same balancing task. These results establish aSSM-based MPC as a practical route to full-body shape control on real soft hardware.
Hehui Zheng, Marc Stampanoni, Roshan S. Kaundinya +3
Soft Robotics Lab, ETH Zurich, Zurich, Switzerland · Institute for Mechanical Systems, ETH Zurich, Zurich, Switzerland
Precise control of soft manipulators remains challenging due to the difficulty of developing accurate yet computationally tractable models for model-based estimation and control. Reduced Cosserat-rod models provide a physics-based and control-oriented description of soft-robot dynamics, offering an explicit alternative to purely data-driven input-output representations. In this paper, we propose a moving-horizon estimation (MHE) and nonlinear model predictive control (NMPC) framework for cable-driven soft manipulators based on reduced Cosserat dynamics. A smooth cable-length-driven modeling formulation is developed by approximating the complementarity relationship between cable tension and cable slackness, enabling cable-length control without direct tension sensing. Based on this formulation, an MHE method is introduced to estimate the reduced state and reconstruct the manipulator configuration from end-effector pose measurements and cable-length information. An NMPC controller is then formulated to achieve task-space control under cable-length and cable-rate constraints. The proposed framework is validated through numerical simulations and experiments. Simulation results demonstrate the effectiveness of the estimator and controller for pose and strain-related regulation on a multi-cable soft manipulator. Experimental results on a four-cable prototype further show that the proposed MHE-NMPC scheme can be implemented in real time and enables accurate end-effector position tracking through cable-length control.