TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models

TL;DR

This paper introduces TrajPAC, a framework for formal robustness verification of pedestrian trajectory prediction models, addressing ambiguities in definitions and considering all points in disturbance intervals, with experimental evaluation on multiple models and datasets.

Contribution

It provides formal definitions for label and pure robustness, employs a PAC-based verification framework, and offers a prototype tool for analyzing state-of-the-art models.

Findings

TrajPAC successfully verifies robustness of four models.

Identifies potential vulnerabilities in trajectory prediction models.

Analyzes factors influencing robustness performance.

Abstract

Robust pedestrian trajectory forecasting is crucial to developing safe autonomous vehicles. Although previous works have studied adversarial robustness in the context of trajectory forecasting, some significant issues remain unaddressed. In this work, we try to tackle these crucial problems. Firstly, the previous definitions of robustness in trajectory prediction are ambiguous. We thus provide formal definitions for two kinds of robustness, namely label robustness and pure robustness. Secondly, as previous works fail to consider robustness about all points in a disturbance interval, we utilise a probably approximately correct (PAC) framework for robustness verification. Additionally, this framework can not only identify potential counterexamples, but also provides interpretable analyses of the original methods. Our approach is applied using a prototype tool named TrajPAC. With TrajPAC, we evaluate the robustness of four state-of-the-art trajectory prediction models -- Trajectron++, MemoNet, AgentFormer, and MID -- on trajectories from five scenes of the ETH/UCY dataset and scenes of the Stanford Drone Dataset. Using our framework, we also experimentally study various factors that could influence robustness performance.