Towards Edge Intelligence via Autonomous Navigation: A Robot-Assisted Data Collection Approach

2026-04-04

AI Summary

This work addresses the challenge of enabling efficient and reliable data collection by robotic agents in non-line-of-sight, complex environments within edge intelligence systems. To this end, the authors propose a communication- and learning-driven autonomous navigation method that jointly models navigation, communication, and learning objectives. The approach incorporates a region-aware propagation channel model and a non-point-mass robot dynamics representation, and tackles the resulting non-convex, non-smooth optimization problem via a majorization–minimization (MM) algorithm. The framework supports flexible adjustment of weighting factors to accommodate diverse operational scenarios. Extensive simulations demonstrate that the proposed method significantly outperforms existing baselines in obstacle avoidance, navigation accuracy, data collection efficiency, and model training performance, highlighting its strong environmental adaptability and overall effectiveness.

Abstract

With the growing demand for large-scale and high-quality data in edge intelligence systems, mobile robots are increasingly deployed to collect data proactively, particularly in complex environments. However, existing robot-assisted data collection methods face significant challenges in achieving reliable and efficient performance, especially in non-line-of-sight (NLoS) environments. This paper proposes a communication-and-learning dual-driven (CLD) autonomous navigation scheme that incorporates region-aware propagation characteristics and a non-point-mass robot representation. This scheme enables simultaneous optimization of navigation, communication, and learning performance. An efficient algorithm based on majorization-minimization (MM) is proposed to solve the non-convex and non-smooth CLD problem. Simulation results demonstrate that the proposed scheme achieves superior performance in collision-avoidance navigation, data collection, and model training compared to benchmark methods. It is also shown that CLD can adapt to different scenarios by flexibly adjusting the weight factor among navigation, communication and learning objectives.

Problem

• edge intelligence
• robot-assisted data collection
• non-line-of-sight
• autonomous navigation
• data collection

Innovation

• communication-and-learning dual-driven
• autonomous navigation
• non-point-mass robot
• majorization-minimization
• edge intelligence