SHARE: Towards Head-Mounted AR with User-Centric SLAM in Shared Human-Robot Workspaces
2026-07-27 • Human-Computer Interaction
Human-Computer InteractionRobotics
AI summaryⓘ
The authors studied how robots and people wearing augmented reality (AR) headsets work together in the same space using a system called SLAM to understand their surroundings. They found that current systems treat all devices the same, causing delays that make AR less responsive. To fix this, the authors created SHARE, which gives higher priority to the AR users' data so their experience feels smoother without hurting how well robots track their environment. Their tests showed that SHARE cuts down delays for AR users and keeps robot tracking accurate, which users also noticed positively.
Human-Robot CollaborationAugmented RealitySimultaneous Localization and Mapping (SLAM)Edge ComputingLatencyVisual Feature RedundancyTracking AccuracyUser ExperienceMulti-agent Systems
Authors
Tianyuan Du, Tianyi Hu, Hanting Ye, Maria Gorlatova
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.