Sampling for Model Predictive Trajectory Planning in Autonomous Driving using Normalizing Flows
This work addresses trajectory planning for autonomous vehicles, but it appears incremental as it builds on existing sampling-based methods with a learning-based adaptation.
The paper tackled trajectory planning for autonomous driving by investigating sampling approaches, particularly using normalizing flows to generate sampling distributions, and evaluated the algorithm in two simulation scenarios, showing improved efficiency in exploration.
Alongside optimization-based planners, sampling-based approaches are often used in trajectory planning for autonomous driving due to their simplicity. Model predictive path integral control is a framework that builds upon optimization principles while incorporating stochastic sampling of input trajectories. This paper investigates several sampling approaches for trajectory generation. In this context, normalizing flows originating from the field of variational inference are considered for the generation of sampling distributions, as they model transformations of simple to more complex distributions. Accordingly, learning-based normalizing flow models are trained for a more efficient exploration of the input domain for the task at hand. The developed algorithm and the proposed sampling distributions are evaluated in two simulation scenarios.