SHARE: Towards Head-Mounted AR with User-Centric SLAM in Shared Human-Robot Workspaces

2026-07-26

AI Summary

Existing multi-agent SLAM systems process visual data from both robots and AR users uniformly at the edge, disregarding their divergent latency requirements, which leads to high latency and degraded user experience on the AR side. This work proposes SHARE, a novel system that introduces the first user-centric quality-of-experience model tailored for heterogeneous human-robot collaboration. SHARE features an adaptive SLAM scheduling mechanism centered on AR users, dynamically adjusting transmission priorities and leveraging visual feature redundancy within shared workspaces to reduce edge computing overhead. Experimental results demonstrate that SHARE maintains robot tracking error below 2 cm while reducing average end-to-end latency for AR users to 13.22 ms—43.3% lower than the baseline—significantly enhancing perceptual quality and user experience.

Abstract

Human-Robot Collaboration (HRC) in shared physical spaces using Augmented Reality (AR) interfaces is powered by Simultaneous Localization and Mapping (SLAM). Existing multi-agent SLAM systems rely on an edge server to combine visual findings of multiple resource-constrained agents, perform computation, and schedule updates to their local maps. However, the edge treats all agents uniformly and ignores the fundamentally different latency requirements of heterogeneous HRC agents: robots and head-mounted AR users. This uniform resource allocation often results in high lag for user manipulation, as it does not meet the stringent latency requirements of AR. In this work, we design, implement, and evaluate SHARE, a user-centric SLAM system that strategically prioritizes AR user experience while maintaining accurate tracking performance for robots. SHARE builds a first-of-its-kind experience model for HRC agents and adaptively adjusts transmission priorities to match it. To reduce end-to-end latency, SHARE leverages the redundancy of visual features acquired by agents in shared human-robot workspaces to reduce computation time induced by edge-based processing. Real-world deployment with commercial AR headsets and a ground robot achieves 13.22 ms average latency for AR users (43.3% reduction from baseline) while maintaining sub-2-centimeter tracking accuracy. User studies further reveal statistically significant improvements in user perception.

Problem

• Human-Robot Collaboration
• Augmented Reality
• SLAM
• Latency
• Edge Computing

Innovation

• user-centric SLAM
• human-robot collaboration
• augmented reality
• edge computing
• latency optimization