Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulation

TL;DR

Adv3D introduces a framework for generating realistic vehicle shape variations in closed-loop simulations to evaluate and challenge autonomous vehicle systems more effectively, revealing vulnerabilities in perception and planning modules.

Contribution

The paper presents Adv3D, a novel method for optimizing vehicle shapes in closed-loop simulation to identify scenarios that degrade autonomous vehicle performance.

Findings

Shape variations in closed-loop are more impactful than open-loop.

Optimized shapes cause more autonomy failures and uncomfortable maneuvers.

Realistic shape modifications reveal vulnerabilities in perception and planning.

Abstract

Self-driving vehicles (SDVs) must be rigorously tested on a wide range of scenarios to ensure safe deployment. The industry typically relies on closed-loop simulation to evaluate how the SDV interacts on a corpus of synthetic and real scenarios and verify it performs properly. However, they primarily only test the system's motion planning module, and only consider behavior variations. It is key to evaluate the full autonomy system in closed-loop, and to understand how variations in sensor data based on scene appearance, such as the shape of actors, affect system performance. In this paper, we propose a framework, Adv3D, that takes real world scenarios and performs closed-loop sensor simulation to evaluate autonomy performance, and finds vehicle shapes that make the scenario more challenging, resulting in autonomy failures and uncomfortable SDV maneuvers. Unlike prior works that add contrived adversarial shapes to vehicle roof-tops or roadside to harm perception only, we optimize a low-dimensional shape representation to modify the vehicle shape itself in a realistic manner to degrade autonomy performance (e.g., perception, prediction, and motion planning). Moreover, we find that the shape variations found with Adv3D optimized in closed-loop are much more effective than those in open-loop, demonstrating the importance of finding scene appearance variations that affect autonomy in the interactive setting.