Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations
This work addresses safe and interpretable motion planning for self-driving vehicles, representing an incremental improvement over existing neural planners.
The paper tackles the problem of motion planning for self-driving vehicles by proposing an end-to-end learnable network that integrates perception, prediction, and planning with interpretable semantic representations, resulting in significantly outperforming state-of-the-art planners in imitating human behaviors and producing safer trajectories.
In this paper we propose a novel end-to-end learnable network that performs joint perception, prediction and motion planning for self-driving vehicles and produces interpretable intermediate representations. Unlike existing neural motion planners, our motion planning costs are consistent with our perception and prediction estimates. This is achieved by a novel differentiable semantic occupancy representation that is explicitly used as cost by the motion planning process. Our network is learned end-to-end from human demonstrations. The experiments in a large-scale manual-driving dataset and closed-loop simulation show that the proposed model significantly outperforms state-of-the-art planners in imitating the human behaviors while producing much safer trajectories.