RiskMap: A Unified Driving Context Representation for Autonomous Motion Planning in Urban Driving Environment

TL;DR

RiskMap introduces a unified, differentiable risk field representation for urban autonomous driving, enhancing planning safety and efficiency by visualizing sensor noise and traffic cognition.

Contribution

The paper presents RiskMap, a novel deep neural network-based, unified risk field representation that improves real-time motion planning in complex urban traffic scenarios.

Findings

RiskMap improves driving safety and smoothness.

The method visualizes sensor noise effectively.

RiskMap enhances planning efficiency in urban environments.

Abstract

Motion planning is a complicated task that requires the combination of perception, map information integration and prediction, particularly when driving in heavy traffic. Developing an extensible and efficient representation that visualizes sensor noise and provides basis to real-time planning tasks is desirable. We aim to develop an interpretable map representation, which offers prior of driving cost in planning tasks. In this way, we can simplify the planning process for dealing with complex driving scenarios and visualize sensor noise. Specifically, we propose a unified context representation empowered by deep neural networks. The unified representation is a differentiable risk field, which is an analytical representation of statistical cognition regarding traffic participants for downstream planning tasks. This representation method is nominated as RiskMap. A sampling-based planner is adopted to train and compare RiskMap generation methods. In this paper, the RiskMap generation tools and model structures are explored, the results illustrate that our method can improve driving safety and smoothness, and the limitation of our method is also discussed.