Trajformer: Trajectory Prediction with Local Self-Attentive Contexts for Autonomous Driving
This work provides an incremental improvement in trajectory prediction for autonomous driving systems by enhancing scene context representation.
This paper addresses the problem of multimodal trajectory prediction for autonomous driving by proposing a local feature-extraction pipeline using self-attention. This approach improves the representation of an agent's social context, leading to better predictions and achieving improvements on standard metrics (minADE, minFDE, DAO, DAC) on the Argoverse dataset.
Effective feature-extraction is critical to models' contextual understanding, particularly for applications to robotics and autonomous driving, such as multimodal trajectory prediction. However, state-of-the-art generative methods face limitations in representing the scene context, leading to predictions of inadmissible futures. We alleviate these limitations through the use of self-attention, which enables better control over representing the agent's social context; we propose a local feature-extraction pipeline that produces more salient information downstream, with improved parameter efficiency. We show improvements on standard metrics (minADE, minFDE, DAO, DAC) over various baselines on the Argoverse dataset. We release our code at: https://github.com/Manojbhat09/Trajformer