MotiMem: Motion-Aware Approximate Memory for Energy-Efficient Neural Perception in Autonomous Vehicles

TL;DR

MotiMem is a hardware-software co-designed interface that reduces energy consumption in autonomous vehicle perception systems by dynamically identifying regions of interest and inducing sparsity, while maintaining high detection accuracy.

Contribution

It introduces a novel motion-aware memory interface with lightweight region detection and adaptive coding, significantly improving energy efficiency over standard codecs.

Findings

Reduces memory-interface dynamic energy by ~43%

Retains ~93% of object detection accuracy

Outperforms JPEG and WebP codecs in experiments

Abstract

High-resolution sensors are critical for robust autonomous perception but impose a severe memory wall on battery-constrained electric vehicles. In these systems, data movement energy often outweighs computation. Traditional image compression is ill-suited as it is semantically blind and optimizes for storage rather than bus switching activity. We propose MotiMem, a hardware-software co-designed interface. Exploiting temporal coherence,MotiMem uses lightweight 2D Motion Propagation to dynamically identify Regions of Interest (RoI). Complementing this, a Hybrid Sparsity-Aware Coding scheme leverages adaptive inversion and truncation to induce bitlevel sparsity. Extensive experiments across nuScenes, Waymo, and KITTI with 16 detection models demonstrate that MotiMem reduces memory-interface dynamic energy by approximately 43 percent while retaining approximately 93 percent of the object detection accuracy, establishing a new Pareto frontier significantly superior to standard codecs like JPEG and WebP.