MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction
This work addresses trajectory prediction for autonomous systems, offering improved diversity and controllability, but it is incremental as it builds on existing normalizing flow methods.
The paper tackled the problem of weak diversity in trajectory prediction by proposing a mixed Gaussian prior for normalizing flow models, achieving state-of-the-art performance in trajectory alignment and diversity on UCY/ETH and SDD datasets.
To predict future trajectories, the normalizing flow with a standard Gaussian prior suffers from weak diversity. The ineffectiveness comes from the conflict between the fact of asymmetric and multi-modal distribution of likely outcomes and symmetric and single-modal original distribution and supervision losses. Instead, we propose constructing a mixed Gaussian prior for a normalizing flow model for trajectory prediction. The prior is constructed by analyzing the trajectory patterns in the training samples without requiring extra annotations while showing better expressiveness and being multi-modal and asymmetric. Besides diversity, it also provides better controllability for probabilistic trajectory generation. We name our method Mixed Gaussian Flow (MGF). It achieves state-of-the-art performance in the evaluation of both trajectory alignment and diversity on the popular UCY/ETH and SDD datasets. Code is available at https://github.com/mulplue/MGF.