End-to-end Contextual Perception and Prediction with Interaction Transformer
This addresses the critical safety problem of predicting realistic multi-actor behavior in autonomous driving, though it appears incremental as it builds on existing Transformer architectures.
The paper tackles 3D object detection and motion forecasting for self-driving by modeling actor interactions with a novel Interaction Transformer, achieving state-of-the-art performance on ATG4D and nuScenes datasets with improved social compliance and fewer predicted collisions.
In this paper, we tackle the problem of detecting objects in 3D and forecasting their future motion in the context of self-driving. Towards this goal, we design a novel approach that explicitly takes into account the interactions between actors. To capture their spatial-temporal dependencies, we propose a recurrent neural network with a novel Transformer architecture, which we call the Interaction Transformer. Importantly, our model can be trained end-to-end, and runs in real-time. We validate our approach on two challenging real-world datasets: ATG4D and nuScenes. We show that our approach can outperform the state-of-the-art on both datasets. In particular, we significantly improve the social compliance between the estimated future trajectories, resulting in far fewer collisions between the predicted actors.