Perception Helps Planning: Facilitating Multi-Stage Lane-Level Integration via Double-Edge Structures

TL;DR

This paper introduces PHP, a framework that integrates perception of lane-level traffic elements into planning for autonomous driving, improving safety and efficiency by aligning planning with traffic constraints.

Contribution

The novel PHP framework combines perception and planning at lane-level, utilizing a double-edge structure and transformer-based feature extraction for enhanced autonomous driving performance.

Findings

Achieves up to 33.47% improvement in driving score

Operates at 22.57 FPS in benchmarks

Sets new state-of-the-art performance on Carla benchmarks

Abstract

When planning for autonomous driving, it is crucial to consider essential traffic elements such as lanes, intersections, traffic regulations, and dynamic agents. However, they are often overlooked by the traditional end-to-end planning methods, likely leading to inefficiencies and non-compliance with traffic regulations. In this work, we endeavor to integrate the perception of these elements into the planning task. To this end, we propose Perception Helps Planning (PHP), a novel framework that reconciles lane-level planning with perception. This integration ensures that planning is inherently aligned with traffic constraints, thus facilitating safe and efficient driving. Specifically, PHP focuses on both edges of a lane for planning and perception purposes, taking into consideration the 3D positions of both lane edges and attributes for lane intersections, lane directions, lane occupancy, and planning. In the algorithmic design, the process begins with the transformer encoding multi-camera images to extract the above features and predicting lane-level perception results. Next, the hierarchical feature early fusion module refines the features for predicting planning attributes. Finally, the double-edge interpreter utilizes a late-fusion process specifically designed to integrate lane-level perception and planning information, culminating in the generation of vehicle control signals. Experiments on three Carla benchmarks show significant improvements in driving score of 27.20%, 33.47%, and 15.54% over existing algorithms, respectively, achieving the state-of-the-art performance, with the system operating up to 22.57 FPS.