MERINDA: Real-Time Digital Twins for Physical AI and Autonomous Systems

Invention Description

The next generation of autonomous systems—from robots and drones to industrial platforms and intelligent vehicles—depends on Physical AI: systems that continuously learn, predict, and adapt to the physical world. These capabilities increasingly rely on digital twins, computational models that reconstruct and predict system behavior in real time. However, existing approaches often depend on cloud computing or computationally intensive algorithms that are too slow and energy-demanding for deployment on edge devices.

Researchers at Arizona State University have developed MERINDA, a novel framework that enables real-time digital twins and physics-guided AI models to run efficiently on resource-constrained hardware. MERINDA combines a highly parallel neural architecture with FPGA acceleration to replace traditional iterative solvers used in model recovery and neural differential equation methods.

By dramatically reducing runtime, memory usage, and energy consumption while maintaining state-of-the-art accuracy, MERINDA enables autonomous systems to continuously reconstruct and predict their dynamics directly on embedded platforms. The technology supports fast, adaptive, and trustworthy operation in mission-critical environments where cloud connectivity, latency, and power consumption are major constraints.

MERINDA provides the computational infrastructure needed to bring Physical AI from the cloud to the edge.
 
Potential Applications
  • Real-time digital twins for autonomous vehicles, robotics, and drones
  • Edge AI platforms requiring physics-guided predictive inference
  • Aerospace and defense systems operating in bandwidth- and power-constrained environments
  • Industrial automation and cyber-physical systems requiring online adaptation
  • Embedded and IoT devices performing real-time modeling and decision making
  • Hardware acceleration for physical AI workloads on FPGAs, NPUs, and heterogeneous SoCs
  • Predictive maintenance and intelligent control in industrial and manufacturing systems
Benefits and Advantages
  • Enables real-time execution of digital twins on embedded hardware
  • Significantly reduces memory footprint, DRAM bandwidth, and energy consumption
  • Accelerates physics-guided AI and model recovery using FPGA implementations
  • Supports deployment on resource-constrained edge platforms
  • Provides low-latency adaptation to changing physical environments
  • Parallelizable neural architecture improves scalability and performance
  • Maintains accuracy comparable to state-of-the-art model recovery techniques
For more information about this opportunity, please see
Patent Information: