OpenPRC: A Unified Open-Source Framework for Physics-to-Task Evaluation in Physical Reservoir Computing

Yogesh Phalak; Wen Sin Lor; Apoorva Khairnar; Benjamin Jantzen; Noel Naughton; Suyi Li

cs.ROApr 8, 2026

OpenPRC: A Unified Open-Source Framework for Physics-to-Task Evaluation in Physical Reservoir Computing

Authors: Yogesh Phalak, Wen Sin Lor, Apoorva Khairnar, Benjamin Jantzen, Noel Naughton, Suyi Li

Organizations: Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA · Department of Philosophy, Virginia Tech, Blacksburg, VA, USA · Department of Computer Science, Virginia Tech, Blacksburg, VA, USA

Abstract

Physical Reservoir Computing (PRC) leverages the intrinsic nonlinear dynamics of physical substrates, mechanical, optical, spintronic, and beyond, as fixed computational reservoirs, offering a compelling paradigm for energy-efficient and embodied machine learning. However, the practical workflow for developing and evaluating PRC systems remains fragmented: existing tools typically address only isolated parts of the pipeline, such as substrate-specific simulation, digital reservoir benchmarking, or readout training. What is missing is a unified framework that can represent both high-fidelity simulated trajectories and real experimental measurements through the same data interface, enabling reproducible evaluation, analysis, and physics-aware optimization across substrates and data sources. We present OpenPRC, an open-source Python framework that fills this gap through a schema-driven physics-to-task pipeline built around five modules: a GPU-accelerated hybrid RK4-PBD physics engine (demlat), a video-based experimental ingestion layer (openprc.vision), a modular learning layer (reservoir), information-theoretic analysis and benchmarking tools (analysis), and physics-aware optimization (optimize). A universal HDF5 schema enforces reproducibility and interoperability, allowing GPU-simulated and experimentally acquired trajectories to enter the same downstream workflow without modification. Demonstrated capabilities include simulations of Origami tessellations, video-based trajectory extraction from a physical reservoir, and a common interface for standardized PRC benchmarking, correlation diagnostics, and capacity analysis. The longer-term vision is to serve as a standardizing layer for the PRC community, compatible with external physics engines including PyBullet, PyElastica, and MERLIN.

Figures & tables

Tool	Primary scope	Physics sim.	Experimental data	RC analysis	Optimization
MERLIN/MERLIN2	Non-rigid origami mechanics	$\checkmark$	$\times$	$\times$	limited
PyElastica	Cosserat rod simulation	$\checkmark$	$\times$	$\times$	limited
ReservoirPy	Digital RC benchmarking	$\times$	$\times$	$\checkmark$	limited
ORC	Digital RC in JAX	$\times$	$\times$	$\checkmark$	limited
PRCpy	PRC-oriented data workflow	$\times$	$\checkmark$	$\checkmark$	$\times$
OpenPRC	Unified physical PRC workflow	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$

Table 1: Representative software tools related to PRC and their scope.

Panel of Figure 1 — Figure 1: The OpenPRC pipeline. Both demlat and openprc.vision produce simulation.h5 , making simulated and experimental trajectories interchangeable to all downstream modules. The optimize module closes the loop back to demlat for iterative design optimization.

File	Producer	Consumers	Key content
geometry.h5	User / optimize	demlat	Node coordinates $[N\times 3]$ , masses $[N]$ , bar connectivity $[M\times 2]$ , hinge connectivity $[K\times 4]$ , stiffness, rest lengths, damping
signals.h5	User / optimize	demlat	Named time series $[T_{u}]$ or $[T_{u}\times d]$ ; signal timestep
config.json	User / optimize	demlat	Simulation duration, integrator settings, actuator wiring, export options
simulation.h5	demlat / openprc.vision	reservoir , analysis	Node positions $[T_{s}\times N\times 3]$ , velocities, bar strains $[T_{s}\times M]$ , hinge angles $[T_{s}\times K]$ , energies
readout.h5	reservoir	analysis , optimize	Readout weights $[D\times O]$ , predictions $[T_{s}\times O]$ , NMSE, NRMSE
metrics.h5	analysis	optimize , User	Memory-capacity profiles, IPC matrix, PCA variance, kernel rank

Table 2: Universal HDF5 file schema in OpenPRC.

Figure 2: Bar-hinge element showing the four-node hinge configuration. Node $\mathbf{P}_{i}$ interacts with its neighbours through axial bar forces and dihedral hinge torques, with angle gradients computed from the normals of the two adjacent faces.

Figure 3: Versatile applications of the bar-hinge model in demlat : soft reservoir network (mass-spring lattice under dynamic actuation), Miura-ori tessellation, kirigami structure with geometric cuts, k-cone origami, bistable slab, and tapered spring. Strain is visualized using a cool–warm colormap.

Figure 4: DEMLAT Player visualizing a Miura-ori simulation. Faces are colored by axial bar strain (cool–warm colormap), nodes and bars are overlaid, and node trajectory trails show the dynamic response under base excitation. The player is built on PiViz [ 28 ] , a high-performance GPU-accelerated visualization library developed alongside OpenPRC.

Figure 5: Output of the openprc.vision pipeline applied to a physical Miura-ori reservoir [ 11 ] . Left: SIFT keypoints detected on the reference frame, with feature indices and response circles overlaid. Right: KLT tracking in progress, showing per-feature trajectory trails and forward-backward status indicators. The status bar at the bottom encodes per-feature tracking health across the frame window.

Figure 6: Representative NARMA2 benchmark result for the Miura-ori reservoir. The target is generated from the normalized base-excitation signal and the prediction is obtained from the trained readout over the evaluation window.

Figure 7: Memory-benchmark result for the Miura-ori reservoir under the truncated Dambre-style IPC analysis. Linear and nonlinear capacity contributions are resolved across delayed input components.

Reservoir Computing

Reservoir computing uses recurrent dynamical systems to transform temporal inputs into features that support efficient learning with simple readouts.

See all 107 papers

From Digital to Physical Reservoir Computing: Co-Optimizing Soft Robotic Reservoirs via Dynamics Matching
Aug 1, 2026Nicola Visentin, Maximilian Stölzle, Mariano Ramírez Montero +3Reservoir Computing Soft Robotics
Department of Cognitive Robotics, Delft University of Technology, Delft, The Netherlands · Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA · Department of Mechanical Engineering, Politecnico di Milano, Milan, Italy
OpenReservoirComputing: GPU-Accelerated Reservoir Computing in JAX
Mar 16, 2026Jan Williams, Dima Tretiak, Steven L. Brunton +2Reservoir Computing
Department of Mechanical Engineering, University of Washington, USA · Department of Applied Mathematics, University of Washington, USA · Department of Electrical and Computer Engineering, University of Washington, USA +1
Vestibular reservoir computing
Apr 10, 2026Smita Deb, Shirin Panahi, Mulugeta Haile +1Reservoir Computing
School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, AZ 85287, USA · Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO 80523, USA · DEVCOM Army Research Office, 6340 Rodman Road, Aberdeen Proving Ground, MD 21005-5069, USA +1

Aug 1, 2026J/K move · Enter open · S save

From Digital to Physical Reservoir Computing: Co-Optimizing Soft Robotic Reservoirs via Dynamics Matching

Nicola Visentin, Maximilian Stölzle, Mariano Ramírez Montero, Francesco Braghin+2

Department of Cognitive Robotics, Delft University of Technology, Delft, The Netherlands · Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA · Department of Mechanical Engineering, Politecnico di Milano, Milan, Italy

Reservoir Computing Soft Robotics

Open paper AskPDF arXiv

Soft robotic substrates are promising for Physical Reservoir Computing (PRC) because their compliant nonlinear dynamics can provide temporal memory, high-dimensional state transformations, and efficient inference. However, physical reservoirs are often adopted as-is rather than pretrained or co-optimized, potentially limiting soft robotic PRC performance relative to digital reservoirs. We investigate whether a physical reservoir can instead be pretrained against high-performing digital reference dynamics. Our formulation jointly optimizes physical parameters, a diffeomorphic physical-reference state map, and feedforward-feedback control using a differentiable physical model and an acceleration-level equation-error objective that avoids temporal integration. As a proof of concept, we instantiate the formulation with simulated soft robots, a Random Oscillators Network (RON) reference, and parallel multi-start gradient descent. We evaluate the optimized reservoirs on classification (sMNIST and ADIAC) and forecasting (Mackey-Glass and Lorenz96) tasks across four reservoir dimensions. Compared with unoptimized soft robot reservoirs, the optimized reservoirs achieve a mean relative improvement of 33.7% across all tasks and datasets, while remaining close to the digital reference. These results demonstrate the feasibility of dynamics-level co-optimization for the simulated soft robotic reservoirs considered here.

Abstract

Reservoir Computing

Explore similar work

From Digital to Physical Reservoir Computing: Co-Optimizing Soft Robotic Reservoirs via Dynamics Matching

OpenReservoirComputing: GPU-Accelerated Reservoir Computing in JAX

Vestibular reservoir computing