Context-aware Pedestrian Trajectory Prediction with Multimodal Transformer
This work addresses the problem of accurate and fast trajectory prediction for autonomous vehicles, though it appears incremental as it builds on existing transformer methods with multimodal inputs.
The paper tackles pedestrian trajectory prediction by proposing a multimodal transformer architecture that inputs pedestrian locations and ego-vehicle speeds, achieving state-of-the-art results with the lowest error across three time horizons (0.5, 1.0, and 1.5 seconds) on PIE and JAAD datasets.
We propose a novel solution for predicting future trajectories of pedestrians. Our method uses a multimodal encoder-decoder transformer architecture, which takes as input both pedestrian locations and ego-vehicle speeds. Notably, our decoder predicts the entire future trajectory in a single-pass and does not perform one-step-ahead prediction, which makes the method effective for embedded edge deployment. We perform detailed experiments and evaluate our method on two popular datasets, PIE and JAAD. Quantitative results demonstrate the superiority of our proposed model over the current state-of-the-art, which consistently achieves the lowest error for 3 time horizons of 0.5, 1.0 and 1.5 seconds. Moreover, the proposed method is significantly faster than the state-of-the-art for the two datasets of PIE and JAAD. Lastly, ablation experiments demonstrate the impact of the key multimodal configuration of our method.