Enabling Physical AI at the Edge: Hardware-Accelerated Recovery of System Dynamics

• URL: http://arxiv.org/abs/2512.23767v1
• Date: Mon, 29 Dec 2025 04:51:51 GMT
• Title: Enabling Physical AI at the Edge: Hardware-Accelerated Recovery of System Dynamics
• Authors: Bin Xu, Ayan Banerjee, Sandeep Gupta,
• Abstract summary: textbfMERINDA (Model Recovery in Reconfigurable Dynamic Architecture) is an FPGA-accelerated MR framework designed to make physical AI practical on resource-constrained devices.<n>We show that MERINDA can bring accurate, explainable MR to the edge for real-time monitoring of autonomous systems.
• Score: 4.058950730052848
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Physical AI at the edge -- enabling autonomous systems to understand and predict real-world dynamics in real time -- requires hardware-efficient learning and inference. Model recovery (MR), which identifies governing equations from sensor data, is a key primitive for safe and explainable monitoring in mission-critical autonomous systems operating under strict latency, compute, and power constraints. However, state-of-the-art MR methods (e.g., EMILY and PINN+SR) rely on Neural ODE formulations that require iterative solvers and are difficult to accelerate efficiently on edge hardware. We present \textbf{MERINDA} (Model Recovery in Reconfigurable Dynamic Architecture), an FPGA-accelerated MR framework designed to make physical AI practical on resource-constrained devices. MERINDA replaces expensive Neural ODE components with a hardware-friendly formulation that combines (i) GRU-based discretized dynamics, (ii) dense inverse-ODE layers, (iii) sparsity-driven dropout, and (iv) lightweight ODE solvers. The resulting computation is structured for streaming parallelism, enabling critical kernels to be fully parallelized on the FPGA. Across four benchmark nonlinear dynamical systems, MERINDA delivers substantial gains over GPU implementations: \textbf{114$\times$ lower energy} (434~J vs.\ 49{,}375~J), \textbf{28$\times$ smaller memory footprint} (214~MB vs.\ 6{,}118~MB), and \textbf{1.68$\times$ faster training}, while matching state-of-the-art model-recovery accuracy. These results demonstrate that MERINDA can bring accurate, explainable MR to the edge for real-time monitoring of autonomous systems.

Related papers

• From Complex Dynamics to DynFormer: Rethinking Transformers for PDEs [6.873342825786888]
  Transformer-based neural operators have emerged as powerful data-driven alternatives.<n>We propose DynFormer, a novel dynamics-informed neural operator.<n>We show that DynFormer achieves up to a 95% reduction in relative error compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-03T15:45:09Z)
• PhyG-MoE: A Physics-Guided Mixture-of-Experts Framework for Energy-Efficient GNSS Interference Recognition [49.955269674859004]
  This paper introduces PhyG-MoE (Physics-Guided Mixture-of-Experts), a framework designed to align model capacity with signal complexity.<n>Unlike static architectures, the proposed system employs a spectrum-based gating mechanism that routes signals based on their spectral feature entanglement.<n>A high-capacity TransNeXt expert is activated on-demand to disentangle complex features in saturated scenarios, while lightweight experts handle fundamental signals to minimize latency.
  arXiv  Detail & Related papers  (2026-01-19T07:57:52Z)
• Hardware Software Optimizations for Fast Model Recovery on Reconfigurable Architectures [4.058950730052848]
  We present MERINDA, an FPGA-accelerated MR framework that restructures computation as a streaming dataflow pipeline.<n>On representative MR workloads, MERINDA delivers up to 6.3x fewer cycles than an FPGA-based LTC baseline.
  arXiv  Detail & Related papers  (2025-12-05T19:38:34Z)
• Model Recovery at the Edge under Resource Constraints for Physical AI [4.415937510184061]
  We propose a novel FPGA-accelerated Model Recovery framework that replaces iterative solvers with a parallelizable neural architecture equivalent to NODEs.<n> MERINDA achieves nearly 11x lower DRAM usage and 2.2x faster runtime compared to mobile GPUs.
  arXiv  Detail & Related papers  (2025-12-01T23:54:23Z)
• Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics [71.53370807809296]
  Recent Graph Neural Simulators (GNSs) accelerate simulations by learning dynamics on graph-structured data.<n>We propose Information-preserving Graph Neural Simulators (IGNS), a graph-based neural simulator built on the principles of Hamiltonian dynamics.<n>IGNS consistently outperforms state-of-the-art GNSs, achieving higher accuracy and stability under challenging and complex dynamical systems.
  arXiv  Detail & Related papers  (2025-11-11T12:53:56Z)
• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition [95.54406667705999]
  Pangu Embedded is an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs)<n>It addresses the significant computational costs and inference latency challenges prevalent in existing reasoning-optimized LLMs.<n>It delivers rapid responses and state-of-the-art reasoning quality within a single, unified model architecture.
  arXiv  Detail & Related papers  (2025-05-28T14:03:02Z)
• Efficient Transformed Gaussian Process State-Space Models for Non-Stationary High-Dimensional Dynamical Systems [49.819436680336786]
  We propose an efficient transformed Gaussian process state-space model (ETGPSSM) for scalable and flexible modeling of high-dimensional, non-stationary dynamical systems.<n>Specifically, our ETGPSSM integrates a single shared GP with input-dependent normalizing flows, yielding an expressive implicit process prior that captures complex, non-stationary transition dynamics.<n>Our ETGPSSM outperforms existing GPSSMs and neural network-based SSMs in terms of computational efficiency and accuracy.
  arXiv  Detail & Related papers  (2025-03-24T03:19:45Z)
• Efficient and accurate neural field reconstruction using resistive memory [52.68088466453264]
  Traditional signal reconstruction methods on digital computers face both software and hardware challenges. We propose a systematic approach with software-hardware co-optimizations for signal reconstruction from sparse inputs. This work advances the AI-driven signal restoration technology and paves the way for future efficient and robust medical AI and 3D vision applications.
  arXiv  Detail & Related papers  (2024-04-15T09:33:09Z)
• SymbolNet: Neural Symbolic Regression with Adaptive Dynamic Pruning for Compression [1.0356366043809717]
  We propose $ttSymbolNet$, a neural network approach to symbolic regression specifically designed as a model compression technique.<n>This framework allows dynamic pruning of model weights, input features, and mathematical operators in a single training process.
  arXiv  Detail & Related papers  (2024-01-18T12:51:38Z)
• Symbolic Regression on FPGAs for Fast Machine Learning Inference [2.0920303420933273]
  High-energy physics community is investigating the potential of deploying machine-learning-based solutions on Field-Programmable Gate Arrays (FPGAs) We introduce a novel end-to-end procedure that utilizes a machine learning technique called symbolic regression (SR) We show that our approach can approximate a 3-layer neural network using an inference model that achieves up to a 13-fold decrease in execution time, down to 5 ns, while still preserving more than 90% approximation accuracy.
  arXiv  Detail & Related papers  (2023-05-06T17:04:02Z)
• RAMP-Net: A Robust Adaptive MPC for Quadrotors via Physics-informed Neural Network [6.309365332210523]
  We propose a Robust Adaptive MPC framework via PINNs (RAMP-Net), which uses a neural network trained partly from simple ODEs and partly from data. We report 7.8% to 43.2% and 8.04% to 61.5% reduction in tracking errors for speeds ranging from 0.5 to 1.75 m/s compared to two SOTA regression based MPC methods.
  arXiv  Detail & Related papers  (2022-09-19T16:11:51Z)
• Real-time Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platforms [59.03426963238452]
  We present Real-time Neural MPC, a framework to efficiently integrate large, complex neural network architectures as dynamics models within a model-predictive control pipeline. We show the feasibility of our framework on real-world problems by reducing the positional tracking error by up to 82% when compared to state-of-the-art MPC approaches without neural network dynamics.
  arXiv  Detail & Related papers  (2022-03-15T09:38:15Z)
• DySMHO: Data-Driven Discovery of Governing Equations for Dynamical Systems via Moving Horizon Optimization [77.34726150561087]
  We introduce Discovery of Dynamical Systems via Moving Horizon Optimization (DySMHO), a scalable machine learning framework. DySMHO sequentially learns the underlying governing equations from a large dictionary of basis functions. Canonical nonlinear dynamical system examples are used to demonstrate that DySMHO can accurately recover the governing laws.
  arXiv  Detail & Related papers  (2021-07-30T20:35:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.