A Computationally Efficient Model for Pedestrian Motion Prediction
It addresses the need for fast and accurate pedestrian prediction in autonomous driving, but the improvements are incremental.
The paper proposes a computationally efficient pedestrian motion prediction model based on a road map structure for autonomous driving collision avoidance. It demonstrates competitive accuracy compared to state-of-the-art methods in simulations and real data tests.
We present a mathematical model to predict pedestrian motion over a finite horizon, intended for use in collision avoidance algorithms for autonomous driving. The model is based on a road map structure, and assumes a rational pedestrian behavior. We compare our model with the state-of-the art and discuss its accuracy, and limitations, both in simulations and in comparison to real data.