CausalAgents: A Robustness Benchmark for Motion Forecasting using Causal Relationships

As machine learning models become increasingly prevalent in motion forecasting systems for autonomous vehicles (AVs), it is critical that we ensure that model predictions are safe and reliable. However, exhaustively collecting and labeling the data necessary to fully test the long tail of rare and challenging scenarios is difficult and expensive. In this work, we construct a new benchmark for evaluating and improving model robustness by applying perturbations to existing data. Specifically, we conduct an extensive labeling effort to identify causal agents, or agents whose presence influences human driver behavior in any way, in the Waymo Open Motion Dataset (WOMD), and we use these labels to perturb the data by deleting non-causal agents from the scene. We then evaluate a diverse set of state-of-the-art deep-learning model architectures on our proposed benchmark and find that all models exhibit large shifts under perturbation. Under non-causal perturbations, we observe a $25$-$38\%$ relative change in minADE as compared to the original. We then investigate techniques to improve model robustness, including increasing the training dataset size and using targeted data augmentations that drop agents throughout training. We plan to provide the causal agent labels as an additional attribute to WOMD and release the robustness benchmarks to aid the community in building more reliable and safe deep-learning models for motion forecasting.