LiDAR-MIMO: Efficient Uncertainty Estimation for LiDAR-based 3D Object Detection

TL;DR

LiDAR-MIMO introduces an efficient uncertainty estimation method for LiDAR-based 3D object detection, achieving comparable accuracy to existing methods while significantly reducing computational costs and runtime.

Contribution

This paper adapts the MIMO uncertainty estimation approach to LiDAR 3D detection, enabling faster and more efficient uncertainty estimation with minimal accuracy loss.

Findings

LiDAR-MIMO achieves similar uncertainty estimation accuracy as MC dropout and ensembles.

LiDAR-MIMO is twice as fast as MC dropout and ensembles.

LiDAR-MIMO attains higher mAP than MC dropout, approaching ensemble performance.

Abstract

The estimation of uncertainty in robotic vision, such as 3D object detection, is an essential component in developing safe autonomous systems aware of their own performance. However, the deployment of current uncertainty estimation methods in 3D object detection remains challenging due to timing and computational constraints. To tackle this issue, we propose LiDAR-MIMO, an adaptation of the multi-input multi-output (MIMO) uncertainty estimation method to the LiDAR-based 3D object detection task. Our method modifies the original MIMO by performing multi-input at the feature level to ensure the detection, uncertainty estimation, and runtime performance benefits are retained despite the limited capacity of the underlying detector and the large computational costs of point cloud processing. We compare LiDAR-MIMO with MC dropout and ensembles as baselines and show comparable uncertainty estimation results with only a small number of output heads. Further, LiDAR-MIMO can be configured to be twice as fast as MC dropout and ensembles, while achieving higher mAP than MC dropout and approaching that of ensembles.