TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models
This work addresses robustness verification for safe autonomous vehicles, but it is incremental as it builds on prior adversarial robustness studies.
The paper tackles the problem of ambiguous robustness definitions and incomplete verification in pedestrian trajectory prediction models by introducing formal definitions and a PAC framework for robustness verification, resulting in the evaluation of four state-of-the-art models on multiple datasets and analysis of influencing factors.
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.