Smooth-Trajectron++: Augmenting the Trajectron++ behaviour prediction model with smooth attention
This work addresses trajectory forecasting for autonomous vehicles, but it is incremental as it builds on an existing model with a cognitive-inspired modification.
The authors tackled the problem of predicting future trajectories of multiple traffic agents for autonomous vehicles by enhancing the Trajectron++ model with a smoothing term in its attention module, resulting in improved performance on benchmarks compared to the original model.
Understanding traffic participants' behaviour is crucial for predicting their future trajectories, aiding in developing safe and reliable planning systems for autonomous vehicles. Integrating cognitive processes and machine learning models has shown promise in other domains but is lacking in the trajectory forecasting of multiple traffic agents in large-scale autonomous driving datasets. This work investigates the state-of-the-art trajectory forecasting model Trajectron++ which we enhance by incorporating a smoothing term in its attention module. This attention mechanism mimics human attention inspired by cognitive science research indicating limits to attention switching. We evaluate the performance of the resulting Smooth-Trajectron++ model and compare it to the original model on various benchmarks, revealing the potential of incorporating insights from human cognition into trajectory prediction models.