Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Embodied AI-empowered Low Altitude Economy: Integrated Sensing, Communications, Computation, and Control (ISC3)

Yaoqi Yang, Yong Chen, Jiacheng Wang, Geng Sun, Dusit Niyato

TL;DR

The paper addresses how to unlock the potential of the Low Altitude Economy (LAE) by integrating sensing, communications, computation, and control (ISC3) through Embodied AI (EAI). It proposes a novel EAI-enabled ISC3 architecture that combines a multi-modal large language model (MMLLM) based agent with an embodied UAV, detailing sensing, communication, computation, and control enhancements. A five-layer decision framework and an express-delivery case study demonstrate how EAI can enable intelligent data acquisition, edge offloading, and optimized flight routing under ISC3 constraints. The work also discusses open issues—privacy, security, data augmentation, and human–machine collaboration—and outlines future research directions for practical deployment in LAE.

Abstract

Low altitude economy (LAE) holds immense potential to drive urban development across various sectors. However, LAE also faces challenges in data collection and processing efficiency, flight control precision, and network performance. The challenges could be solved by realizing an integration of sensing, communications, computation, and control (ISC3) for LAE. In this regard, embodied artificial intelligence (EAI), with its unique perception, planning, and decision-making capabilities, offers a promising solution to realize ISC3. Specifically, this paper investigates an application of EAI into ISC3 to support LAE, exploring potential research focuses, solutions, and case study. We begin by outlining rationales and benefits of introducing EAI into LAE, followed by reviewing research directions and solutions for EAI in ISC3. We then propose a framework of an EAI-enabled ISC3 for LAE. The framework's effectiveness is evaluated through a case study of express delivery utilizing an EAI-enabled UAV. Finally, we discuss several future research directions for advancing EAI-enabled LAE.

Embodied AI-empowered Low Altitude Economy: Integrated Sensing, Communications, Computation, and Control (ISC3)

TL;DR

The paper addresses how to unlock the potential of the Low Altitude Economy (LAE) by integrating sensing, communications, computation, and control (ISC3) through Embodied AI (EAI). It proposes a novel EAI-enabled ISC3 architecture that combines a multi-modal large language model (MMLLM) based agent with an embodied UAV, detailing sensing, communication, computation, and control enhancements. A five-layer decision framework and an express-delivery case study demonstrate how EAI can enable intelligent data acquisition, edge offloading, and optimized flight routing under ISC3 constraints. The work also discusses open issues—privacy, security, data augmentation, and human–machine collaboration—and outlines future research directions for practical deployment in LAE.

Abstract

Low altitude economy (LAE) holds immense potential to drive urban development across various sectors. However, LAE also faces challenges in data collection and processing efficiency, flight control precision, and network performance. The challenges could be solved by realizing an integration of sensing, communications, computation, and control (ISC3) for LAE. In this regard, embodied artificial intelligence (EAI), with its unique perception, planning, and decision-making capabilities, offers a promising solution to realize ISC3. Specifically, this paper investigates an application of EAI into ISC3 to support LAE, exploring potential research focuses, solutions, and case study. We begin by outlining rationales and benefits of introducing EAI into LAE, followed by reviewing research directions and solutions for EAI in ISC3. We then propose a framework of an EAI-enabled ISC3 for LAE. The framework's effectiveness is evaluated through a case study of express delivery utilizing an EAI-enabled UAV. Finally, we discuss several future research directions for advancing EAI-enabled LAE.
Paper Structure (20 sections, 4 figures, 1 table)

This paper contains 20 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Low Altitude Economy
  4. Embodied AI-enabled Aircrafts
  5. Embodied AI for sensing, communications, computation, and control issues in low altitude economic
  6. Research Focus and Solutions
  7. EAI for Improving Sensing Accuracy
  8. EAI for Enhancing Communication Rates
  9. EAI for Optimizing Computation Resources
  10. EAI for Increasing Control Stability
  11. Lessons Learned
  12. Embodied AI-enabled ISC3 for LAE
  13. Research Motivation
  14. Proposed Framework
  15. Case Study and Numerical Results
  16. ...and 5 more sections

Figures (4)

  • Figure 1: Applications of LAE from transportation, agriculture, telecommunication, tourism and and public service and safety fields, and internal relationships between LAE application and the supporting techniques on sensing, communications, computations, and control.
  • Figure 2: Architecture of EAI-enabled aircrafts.
  • Figure 3: Proposed framework of the EAI-enabled ISC3 for LAE. In the MMLLM-driven decision making step, five major layers are included. The input layer receives and preprocesses data from different modalities. The feature extraction layer extracts high-dimensional features from preprocessed inputs. The multi-modal fusion layer integrates feature vectors from different modalities. The context awareness layer processes fused multi-modal representations to capture contextual information. The output layer generates final output based on the specific task.
  • Figure 4: Performance evaluation for the proposed framework in EAI-enabled UAV express delivery scenario. (a) Sensing results of the EAI-enabled UAV, which contains information about delivery position, terrain, weather, traffic, base station distribution. (b) Communication and computation processes of the EAI-enabled UAV. (c) Optimized EAI-enabled UAV's route results in control aspect.