Stochastic Trajectory Prediction under Unstructured Constraints
This work addresses trajectory prediction for planning and decision-making in domains like robotics or autonomous systems, but it is incremental as it builds on existing constrained prediction methods by extending them to handle unstructured constraints.
The paper tackles the challenge of predicting trajectories under unstructured constraints, which lack differentiable formal definitions, by proposing Controllable Trajectory Diffusion (CTD), a method that uses a conditional generative paradigm to implicitly learn constraint adherence, achieving high accuracy on ETH/UCY and SDD benchmarks.
Trajectory prediction facilitates effective planning and decision-making, while constrained trajectory prediction integrates regulation into prediction. Recent advances in constrained trajectory prediction focus on structured constraints by constructing optimization objectives. However, handling unstructured constraints is challenging due to the lack of differentiable formal definitions. To address this, we propose a novel method for constrained trajectory prediction using a conditional generative paradigm, named Controllable Trajectory Diffusion (CTD). The key idea is that any trajectory corresponds to a degree of conformity to a constraint. By quantifying this degree and treating it as a condition, a model can implicitly learn to predict trajectories under unstructured constraints. CTD employs a pre-trained scoring model to predict the degree of conformity (i.e., a score), and uses this score as a condition for a conditional diffusion model to generate trajectories. Experimental results demonstrate that CTD achieves high accuracy on the ETH/UCY and SDD benchmarks. Qualitative analysis confirms that CTD ensures adherence to unstructured constraints and can predict trajectories that satisfy combinatorial constraints.