Multi-modal Transformer Path Prediction for Autonomous Vehicle
This work addresses a critical safety problem for autonomous vehicles by enhancing trajectory forecasting, though it is incremental as it builds on existing Transformer methods with specific lane-handling improvements.
The paper tackles vehicle path prediction for autonomous driving by proposing a multi-modal Transformer-based system that incorporates lane information and filters irrelevant lanes, achieving improved accuracy on the nuScene dataset.
Reasoning about vehicle path prediction is an essential and challenging problem for the safe operation of autonomous driving systems. There exist many research works for path prediction. However, most of them do not use lane information and are not based on the Transformer architecture. By utilizing different types of data collected from sensors equipped on the self-driving vehicles, we propose a path prediction system named Multi-modal Transformer Path Prediction (MTPP) that aims to predict long-term future trajectory of target agents. To achieve more accurate path prediction, the Transformer architecture is adopted in our model. To better utilize the lane information, the lanes which are in opposite direction to target agent are not likely to be taken by the target agent and are consequently filtered out. In addition, consecutive lane chunks are combined to ensure the lane input to be long enough for path prediction. An extensive evaluation is conducted to show the efficacy of the proposed system using nuScene, a real-world trajectory forecasting dataset.