Tangled Program Graphs as an alternative to DRL-based control algorithms for UAVs

TL;DR

This paper explores Tangled Program Graphs as a computationally efficient and explainable alternative to deep reinforcement learning for UAV control, demonstrating promising results in navigation tasks using LiDAR data.

Contribution

The paper introduces Tangled Program Graphs as a novel approach for UAV control, offering advantages over DRL in explainability and computational efficiency.

Findings

TPGs can effectively navigate UAVs using LiDAR data

TPGs are less computationally demanding than DRL

Initial results show promise for TPGs in control tasks

Abstract

Deep reinforcement learning (DRL) is currently the most popular AI-based approach to autonomous vehicle control. An agent, trained for this purpose in simulation, can interact with the real environment with a human-level performance. Despite very good results in terms of selected metrics, this approach has some significant drawbacks: high computational requirements and low explainability. Because of that, a DRL-based agent cannot be used in some control tasks, especially when safety is the key issue. Therefore we propose to use Tangled Program Graphs (TPGs) as an alternative for deep reinforcement learning in control-related tasks. In this approach, input signals are processed by simple programs that are combined in a graph structure. As a result, TPGs are less computationally demanding and their actions can be explained based on the graph structure. In this paper, we present our studies on the use of TPGs as an alternative for DRL in control-related tasks. In particular, we consider the problem of navigating an unmanned aerial vehicle (UAV) through the unknown environment based solely on the on-board LiDAR sensor. The results of our work show promising prospects for the use of TPGs in control related-tasks.