DFA-DRIVE: A Cross-layer Delay Fault Analysis and Optimization Framework for Robust Multi-Task Driving Perception

Autonomous driving systems increasingly rely on deep neural network (DNN) based multi-task perception models for reliable, real time scene understanding. At nanoscale technology nodes, these workloads are highly susceptible to timing errors arising from temperature fluctuations, voltage droop, and device aging. Among these, temperature poses a critical challenge. Prolonged high thermal stress exacerbates delay faults, degrading perception accuracy and endangering safety critical operation.

We present DFA-DRIVE, a cross-layer Delay Fault Analysis Framework for Autonomous Driving that bridges circuit-level timing analysis with system level resilience evaluation. DFA-DRIVE quantifies how temperature induced timing failures propagate through object detection, drivable area segmentation, and lane line segmentation, exposing task level reliability bottlenecks.

Building on DFA-DRIVE, we introduce DFA-OPT, an adaptive hardware mapping algorithm that dynamically reassigns systolic array (SA) resources based on DNN layer and application level thermal sensitivity. Targeting the automotive reliability envelopes of AEC-Q100 Grade~0 (–40 °C to 150 °C) and Grade~1 (–40 °C to 125 °C), DFA-OPT restores near baseline accuracy of small, high reliable SA (e.g., 4×4) even when large SA (e.g., 256×256) experience accuracy drops of upto 4% at 150 °C, achieving comparable accuracy with fewer computation cycles.