Optimization-based Safe Trajectory Planning for Autonomous Ground Vehicle in Multi-Floor Scenarios

2026-06-23

AI Summary

This work addresses the challenge of ensuring both safety and efficiency in trajectory planning for autonomous driving across multi-floor environments. The authors propose a task–trajectory co-optimized two-layer planning framework: at the upper layer, an optimal floor exit is selected using a generalized Voronoi diagram combined with multi-objective optimization; at the lower layer, smooth and dynamically feasible trajectories are generated via numerical optimization, accelerated by a warm-start strategy. A novel obstacle-aware constraint simplification scheme is introduced to significantly enhance computational efficiency in complex scenarios without compromising safety guarantees. Extensive simulations demonstrate that the proposed framework efficiently produces safe, smooth, and dynamically feasible vehicle trajectories in multi-floor settings.

Abstract

The development of trajectory planning strategies for autonomous ground vehicles (AGVs) represents a prevailing research interest within the domain of intelligent transportation systems. This paper introduces a trajectory planning framework tailored for multi-floor scenarios. The framework consists of two main modules: the task planning module and the trajectory planning module. The task planning module involves a strategic selection phase, where a task planning strategy based on generalized voronoi diagrams (GVD) and multi-objective algorithms is proposed to select the floor exits for each floor. The trajectory planning module utilizes optimization-based methods to generate high-quality trajectories, and a warm-started hierarchical planning framework is designed to ensure rapid convergence. Additionally, for handling complex obstacle constraints, a correlation constraint calculation method is designed for reducing obstacle constraints in trajectory planning. Finally, the feasibility and effectiveness of the proposed framework are verified through simulations.

Problem

• autonomous ground vehicle
• multi-floor scenarios
• trajectory planning
• obstacle constraints
• safe navigation

Innovation

• multi-floor trajectory planning
• generalized Voronoi diagram
• optimization-based planning
• warm-started hierarchical framework
• correlation constraint reduction