Taming Perception Jitter: Uncertainty-Aware LiDAR Object Detection for Reliable Motion Classification
2026-06-08 • Robotics
RoboticsComputer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of false movement predictions for objects that are actually still in autonomous driving. They improve a 3D object detector by adding uncertainty estimates and use a simple statistical test to tell real motion from random jitter in short time windows. Their method fits easily into existing systems and uses little extra computing power. Testing shows it works as well as traditional speed-based methods but makes fewer mistakes that lead to unnecessary stops. This suggests that accounting for uncertainty helps self-driving cars better handle noise in real-world data.
3D object detectionaleatoric uncertaintytwo-sample z-testmotion classificationdata associationvelocity estimationautonomous drivingbounding box jitternuScenes datasetreal-world testing
Authors
Cornelius Schröder, Žygimantas Marcinkus, Markus Lienkamp
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.