Embodying Intelligence into Mechanical Metamaterials via Reservoir Computing
For researchers in intelligent materials and physical computing, this work introduces a novel approach to embedding computation into mechanical structures, enabling sense-assess-response systems with reduced digital overhead.
This work uses mechanical metamaterials as physical reservoir computers to process environmental vibrations with minimal digital computation, achieving high performance on benchmark and embodied tasks by leveraging nonlinear dynamics. The metamaterial reservoir, with contact nonlinearities acting as leaky ReLU activations, demonstrates robust task performance and a memory-nonlinearity trade-off that can guide design.
This study harnesses the embodied intelligence of mechanical metamaterials to sense and process environmental vibrations with minimal digital computation. Using physical reservoir computing (PRC), we turn the metamaterial and its nonlinear dynamics into a physical neural network that nonlinearly transforms the input vibrations and uses a simple linear training to compute a range of tasks. We introduce a novel metamaterial reservoir composed of a network of unit cells with contact nonlinearities that are the physical equivalent of leaky rectified linear unit (ReLU) activation functions. We experimentally show that the metamaterial reservoir can compute two classes of tasks: independent tasks, such as benchmark functions, and embodied tasks, such as proprioception, which we introduce to describe tasks coupled to the structure's dynamics. By comparing against a linear metamaterial, we demonstrate that nonlinearity is critical for high task performance, and we show that the metamaterial is robust to inputs of varying complexity. Through dimensionality reduction, we uncover the governing information separation mechanism and show that the metamaterial separates the input vibrations into new frequency content spatially distributed across the sensor readouts. We then confirm that frequency content is a key indicator of task performance by conducting an optimal sensor selection study using a frequency-based greedy algorithm. Finally, we demonstrate that a metamaterial's generalized performance for different tasks can be quantified using the memory vs. nonlinearity subspace, providing a design tool for other reservoir abstractions. These results establish the embodied intelligence of mechanical metamaterials and provide a path for sense-assess-response in intelligent systems.