Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting
This addresses a critical safety issue in autonomous systems by improving forecasting accuracy, though it appears incremental as it builds on existing ensemble and Transformer methods.
The paper tackles the problem of overconfidence and weak uncertainty quantification in multimodal trajectory forecasting for systems like self-driving vehicles, proposing Hierarchical Light Transformer Ensembles (HLT-Ens) that achieve state-of-the-art performance.
Accurate trajectory forecasting is crucial for the performance of various systems, such as advanced driver-assistance systems and self-driving vehicles. These forecasts allow us to anticipate events that lead to collisions and, therefore, to mitigate them. Deep Neural Networks have excelled in motion forecasting, but overconfidence and weak uncertainty quantification persist. Deep Ensembles address these concerns, yet applying them to multimodal distributions remains challenging. In this paper, we propose a novel approach named Hierarchical Light Transformer Ensembles (HLT-Ens) aimed at efficiently training an ensemble of Transformer architectures using a novel hierarchical loss function. HLT-Ens leverages grouped fully connected layers, inspired by grouped convolution techniques, to capture multimodal distributions effectively. We demonstrate that HLT-Ens achieves state-of-the-art performance levels through extensive experimentation, offering a promising avenue for improving trajectory forecasting techniques.