Unifying Decision Making and Trajectory Planning in Automated Driving through Time-Varying Potential Fields

TL;DR

This paper introduces a unified framework for decision making and trajectory planning in automated driving using Time-Varying Artificial Potential Fields, explicitly modeling obstacle uncertainty and integrating perception data for real-time, collision-free path generation.

Contribution

The novel approach unifies decision making and trajectory planning with TVAPFs, explicitly modeling dynamic obstacle uncertainty and incorporating perception and V2X data within a finite horizon optimal control problem.

Findings

Demonstrates real-time applicability in simulation with complex scenarios.

Shows improved collision avoidance and maneuver selection.

Validates effectiveness with realistic road topology.

Abstract

This paper proposes a unified decision making and local trajectory planning framework based on Time-Varying Artificial Potential Fields (TVAPFs). The TVAPF explicitly models the predicted motion via bounded uncertainty of dynamic obstacles over the planning horizon, using information from perception and V2X sources when available. TVAPFs are embedded into a finite horizon optimal control problem that jointly selects the driving maneuver and computes a feasible, collision free trajectory. The effectiveness and real-time suitability of the approach are demonstrated through a simulation test in a multi-actor scenario with real road topology, highlighting the advantages of the unified TVAPF-based formulation.