Taming Perception Jitter: Uncertainty-Aware LiDAR Object Detection for Reliable Motion Classification

2026-06-08

AI Summary

Autonomous driving systems often misclassify static objects as dynamic due to perception jitter, leading to unnecessary planning interventions. This work proposes a lightweight jitter suppression method that integrates aleatoric uncertainty estimation into a 3D object detector and employs a two-sample z-test over a short observation window to distinguish true motion from perceptual noise. By leveraging existing data association modules, the approach incurs minimal additional computational overhead and is readily deployable. Experimental results demonstrate that, on the nuScenes dataset, its motion classification performance matches that of conventional velocity-thresholding methods, while real-world vehicle tests show a significant reduction in false dynamic classifications and unnecessary stops, thereby enhancing system robustness.

Abstract

Reliable motion classification is critical for autonomous driving, as false dynamic predictions of static objects can cascade into unnecessary planner interventions. Unstable bounding box predictions can lead to spurious velocity estimates in tracking and falsely predicted trajectories. We present a deployment-friendly mitigation strategy that augments a 3D object detector with aleatoric uncertainty estimates and applies a two-sample z-test over short observation windows to separate true motion from jitter. Integrated into Autoware with minimal changes, the approach reuses existing data association for minimal compute overhead. Empirical results show parity with velocity thresholding on nuScenes, but substantially fewer false dynamic predictions and unnecessary stops in real-world test drives, explained by the presence of an intermediate jitter band in the recorded data that speed-only rules misclassify. This demonstrates that uncertainty-aware detection and lightweight statistical testing can deliver practical performance gains for autonomous driving in noisier real-world settings.

Problem

• perception jitter
• motion classification
• LiDAR object detection
• autonomous driving
• false dynamic prediction

Innovation

• uncertainty-aware detection
• LiDAR object detection
• motion classification
• perception jitter
• two-sample z-test