TridentNet: A Conditional Generative Model for Dynamic Trajectory Generation

TL;DR

This paper introduces TridentNet, a conditional generative model for dynamic trajectory generation in autonomous vehicles, emphasizing lightweight maps, geometric constraints, and a new dataset for validation.

Contribution

The paper presents a novel conditional generative model for trajectory planning that uses lightweight maps and geometric constraints, along with a new dataset for evaluation.

Findings

Low relative errors in trajectory predictions

Effective use of lightweight map representations

Dataset availability for further research

Abstract

In recent years, various state of the art autonomous vehicle systems and architectures have been introduced. These methods include planners that depend on high-definition (HD) maps and models that learn an autonomous agent's controls in an end-to-end fashion. While end-to-end models are geared towards solving the scalability constraints from HD maps, they do not generalize for different vehicles and sensor configurations. To address these shortcomings, we introduce an approach that leverages lightweight map representations, explicitly enforcing geometric constraints, and learns feasible trajectories using a conditional generative model. Additional contributions include a new dataset that is used to verify our proposed models quantitatively. The results indicate low relative errors that can potentially translate to traversable trajectories. The dataset created as part of this work has been made available online.