Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving
This work addresses a crucial safety and efficiency challenge for autonomous vehicles, though it appears incremental as it builds on existing deep learning techniques for motion prediction.
The paper tackles the problem of predicting future states of traffic actors for autonomous driving by introducing a deep learning-based approach that uses raster images and convolutional models to infer movement while capturing prediction uncertainty. The method was validated through extensive real-world experiments and successfully tested on self-driving vehicles.
We address one of the crucial aspects necessary for safe and efficient operations of autonomous vehicles, namely predicting future state of traffic actors in the autonomous vehicle's surroundings. We introduce a deep learning-based approach that takes into account a current world state and produces raster images of each actor's vicinity. The rasters are then used as inputs to deep convolutional models to infer future movement of actors while also accounting for and capturing inherent uncertainty of the prediction task. Extensive experiments on real-world data strongly suggest benefits of the proposed approach. Moreover, following completion of the offline tests the system was successfully tested onboard self-driving vehicles.