Sensing Intelligence as a Trainable Metamaterial Property
This work introduces a new paradigm for integrating mechanical sensing into the design of physical systems, potentially reducing reliance on electronics and computation for sensing tasks.
The authors present a method to make the geometry of a metamaterial trainable for sensing, where the body's deformation reshapes external stimuli into signals easier for a neural network to interpret. This approach improves sensing accuracy by up to fivefold or reduces the number of required electronic sensors by nearly an order of magnitude.
In biological systems, sensing is not performed by the brain alone: the body deforms, vibrates, and filters external stimuli before they are transduced into neural signals. In engineered systems, this processing burden is placed largely on electronics and computation, while the mechanical body is usually designed only for strength and stability. Here, we present sensing intelligence as a trainable property of the body. We show that the geometry of a metamaterial can be optimized to reshape external stimuli into internal signals that are easier for a neural network to interpret. Rather than hand-designing this physical preprocessing, we let the neural network train its own body for sensing by backpropagating the sensing loss to the body's design parameters through differentiable simulation. Across numerical and experimental sensing scenarios, the optimized body improves sensing accuracy by up to fivefold or reduces the number of required electronic sensors by nearly an order of magnitude.