Efficient Speed Planning for Autonomous Driving in Dynamic Environment with Interaction Point Model

TL;DR

This paper introduces a learning-based Interaction Point Model for autonomous driving that improves speed planning in dynamic environments by effectively handling interactions with other traffic participants, reducing the need for manual tuning.

Contribution

The paper presents a novel Interaction Point Model and integrates it into a planning framework, enhancing robustness and adaptability in complex, dynamic traffic scenarios.

Findings

Effective interaction modeling with protection time and priority

Robust planning demonstrated in simulations

Reduces manual parameter tuning

Abstract

Safely interacting with other traffic participants is one of the core requirements for autonomous driving, especially in intersections and occlusions. Most existing approaches are designed for particular scenarios and require significant human labor in parameter tuning to be applied to different situations. To solve this problem, we first propose a learning-based Interaction Point Model (IPM), which describes the interaction between agents with the protection time and interaction priority in a unified manner. We further integrate the proposed IPM into a novel planning framework, demonstrating its effectiveness and robustness through comprehensive simulations in highly dynamic environments.