Bridging the Gap Between Multi-Step and One-Shot Trajectory Prediction via Self-Supervision
This work addresses trajectory prediction for autonomous driving, but it is incremental as it builds on existing methods with simplistic modeling.
The paper tackles the challenge of vehicle trajectory prediction in autonomous driving by proposing a multi-branch self-supervised predictor that chains trajectory segments, achieving competitive results on the INTERACTION dataset and exploring uncertainty estimation with positive correlations between error and proposed metrics.
Accurate vehicle trajectory prediction is an unsolved problem in autonomous driving with various open research questions. State-of-the-art approaches regress trajectories either in a one-shot or step-wise manner. Although one-shot approaches are usually preferred for their simplicity, they relinquish powerful self-supervision schemes that can be constructed by chaining multiple time-steps. We address this issue by proposing a middle-ground where multiple trajectory segments are chained together. Our proposed Multi-Branch Self-Supervised Predictor receives additional training on new predictions starting at intermediate future segments. In addition, the model 'imagines' the latent context and 'predicts the past' while combining multi-modal trajectories in a tree-like manner. We deliberately keep aspects such as interaction and environment modeling simplistic and nevertheless achieve competitive results on the INTERACTION dataset. Furthermore, we investigate the sparsely explored uncertainty estimation of deterministic predictors. We find positive correlations between the prediction error and two proposed metrics, which might pave way for determining prediction confidence.