Safety-Aware Hardening of 3D Object Detection Neural Network Systems

TL;DR

This paper proposes a safety-aware framework for 3D object detection neural networks, incorporating safety specifications, robustness criteria, and a novel post-processing algorithm to enhance safety in autonomous systems.

Contribution

It introduces a safety-aware loss function, symbolic error propagation, and a safety-aware non-max-inclusion algorithm for 3D detection networks, extending PIXOR.

Findings

Enhanced robustness under perturbation

Improved safety guarantees in detection

Effective integration of safety specifications

Abstract

We study how state-of-the-art neural networks for 3D object detection using a single-stage pipeline can be made safety aware. We start with the safety specification (reflecting the capability of other components) that partitions the 3D input space by criticality, where the critical area employs a separate criterion on robustness under perturbation, quality of bounding boxes, and the tolerance over false negatives demonstrated on the training set. In the architecture design, we consider symbolic error propagation to allow feature-level perturbation. Subsequently, we introduce a specialized loss function reflecting (1) the safety specification, (2) the use of single-stage detection architecture, and finally, (3) the characterization of robustness under perturbation. We also replace the commonly seen non-max-suppression post-processing algorithm by a safety-aware non-max-inclusion algorithm, in order to maintain the safety claim created by the neural network. The concept is detailed by extending the state-of-the-art PIXOR detector which creates object bounding boxes in bird's eye view with inputs from point clouds.