Search papers, labs, and topics across Lattice.
This paper introduces a near-sensor computing framework that integrates a spectral Poisson solver for efficient visuotactile perception, significantly reducing power consumption and latency compared to traditional host-based processing. By operating at 166 MHz, the system achieves a deterministic latency of just 0.211 ms for depth reconstruction, enabling rapid robotic responses to tactile stimuli. The results show that the proposed method reconstructs contact geometries with high accuracy, differing only 0.17% from a double-precision reference, while closing protective reflex loops in 28.3 ms, a substantial improvement over the 169.9 ms of host-based systems.
Near-sensor computing slashes tactile response times from 170 ms to just 28 ms, revolutionizing robotic reflexes.
Visuotactile sensors reconstruct dense contact geometry from measured surface gradients, but host-based processing increases power consumption and introduces data-transfer delays and variable scheduling latency, limiting the sensing and response speed of robotic systems. To address these limitations, we implement a near-sensor computing framework that includes a spectral Poisson solver as a fully streaming hardware pipeline. The computational core logic has an estimated power consumption of 347 mW and achieves high throughput without data-dependent branching or iterative convergence, thereby providing deterministic latency. Operating at 166 MHz, the pipeline produces the first depth value of each 128x128 frame 35,107 cycles after receiving the first input pixel, corresponding to a fixed latency of 0.211 ms. Across 15 contact geometries, the reconstructed depths differ from a double-precision reference by 0.17 % of the peak contact depth. On-chip decisions based on these reconstructions close a robot protective reflex loop in 28.3 +/- 4.9 ms, compared with 169.9 +/- 27.8 ms for an equivalent host-based loop using the same actuator. These results demonstrate that near-sensor reconstruction can provide accurate, energy-efficient, and deterministic tactile geometry on timescales suitable for rapid robotic contact responses.
