KoopCast: Trajectory Forecasting via Koopman Operators
This addresses trajectory prediction for autonomous systems in multi-agent environments, offering interpretability and efficiency, though it appears incremental as it builds on existing operator theory with a hybrid design.
The paper tackles trajectory forecasting in dynamic environments by proposing KoopCast, a model that uses Koopman operator theory for linear representation of nonlinear dynamics, achieving competitive accuracy across benchmarks like ETH/UCY, Waymo Open Motion Dataset, and nuScenes.
We present KoopCast, a lightweight yet efficient model for trajectory forecasting in general dynamic environments. Our approach leverages Koopman operator theory, which enables a linear representation of nonlinear dynamics by lifting trajectories into a higher-dimensional space. The framework follows a two-stage design: first, a probabilistic neural goal estimator predicts plausible long-term targets, specifying where to go; second, a Koopman operator-based refinement module incorporates intention and history into a nonlinear feature space, enabling linear prediction that dictates how to go. This dual structure not only ensures strong predictive accuracy but also inherits the favorable properties of linear operators while faithfully capturing nonlinear dynamics. As a result, our model offers three key advantages: (i) competitive accuracy, (ii) interpretability grounded in Koopman spectral theory, and (iii) low-latency deployment. We validate these benefits on ETH/UCY, the Waymo Open Motion Dataset, and nuScenes, which feature rich multi-agent interactions and map-constrained nonlinear motion. Across benchmarks, KoopCast consistently delivers high predictive accuracy together with mode-level interpretability and practical efficiency.