Decision Transformer-Based Drone Trajectory Planning with Dynamic Safety-Efficiency Trade-Offs

2025-07-29

AI Summary

In UAV trajectory planning under unknown environments, existing methods struggle to dynamically balance safety and efficiency—polynomial approaches require labor-intensive multi-parameter expert tuning, while reinforcement learning lacks an explicit trade-off mechanism. Method: This paper proposes a Decision Transformer–based planning framework that innovatively employs Return-to-Go (RtG) as a temperature parameter, enabling continuous, single-variable control over the safety–efficiency preference without prior knowledge. Training and evaluation are conducted end-to-end in Gazebo using both structured grid and unstructured random scenarios, followed by real-world flight validation. Contribution/Results: Experiments demonstrate that our method consistently outperforms polynomial and reinforcement learning baselines across diverse RtG settings. It enables on-demand generation of either safer or more efficient trajectories, achieving superior reliability and practical applicability in real-world deployment.

Technology Category

Planning, Routing, and Scheduling: Replanning and Plan RepairHumans and AI: Planning and Decision Support for Human-Machine TeamsMultiagent Systems: Multiagent Planning

Application Category

Responsible Web: Machine-in-the-loop, human agency and autonomySearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingGraph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

A drone trajectory planner should be able to dynamically adjust the safety-efficiency trade-off according to varying mission requirements in unknown environments. Although traditional polynomial-based planners offer computational efficiency and smooth trajectory generation, they require expert knowledge to tune multiple parameters to adjust this trade-off. Moreover, even with careful tuning, the resulting adjustment may fail to achieve the desired trade-off. Similarly, although reinforcement learning-based planners are adaptable in unknown environments, they do not explicitly address the safety-efficiency trade-off. To overcome this limitation, we introduce a Decision Transformer-based trajectory planner that leverages a single parameter, Return-to-Go (RTG), as a emph{temperature parameter} to dynamically adjust the safety-efficiency trade-off. In our framework, since RTG intuitively measures the safety and efficiency of a trajectory, RTG tuning does not require expert knowledge. We validate our approach using Gazebo simulations in both structured grid and unstructured random environments. The experimental results demonstrate that our planner can dynamically adjust the safety-efficiency trade-off by simply tuning the RTG parameter. Furthermore, our planner outperforms existing baseline methods across various RTG settings, generating safer trajectories when tuned for safety and more efficient trajectories when tuned for efficiency. Real-world experiments further confirm the reliability and practicality of our proposed planner.

Problem

• Dynamic adjustment of safety-efficiency trade-off in drone trajectories
• Eliminating expert knowledge for parameter tuning in trajectory planning
• Outperforming existing methods in safety and efficiency trade-offs

Innovation

• Decision Transformer adjusts safety-efficiency via RTG
• Single RTG parameter replaces expert tuning
• Outperforms baselines in safety and efficiency