Robot assistants are increasingly capable of assisting users in everyday environments, yet they don’t take users’ cognitive context into consideration. As a result, proactive behaviors may interrupt users during cognitively demanding tasks, before they can acknowledge or respond. We identify this pre-acknowledgment window as a critical phase and introduce our real-time optimization approach that adapts how robots approach and communicate during this window, using user engagement signals and task context. Our system jointly optimizes movement and speech by solving structured, closed-form quadratic subproblems that balance disturbance, clarity, and efficiency online. This enables continuous adjustment of approach movement, timing of intent expression, and level of detail without explicit user input. In a within-subjects ablation user study (N = 12), we find that adapting speech to context improves intent clarity, that speed adaptation alone has limited impact without paired speech adaptation, and that coordinating both channels yields the strongest animacy. We also demonstrate the real-world application in three everyday scenarios.
Publication
Ziru Wei, Di Wen, Leyuan Chen, Hassan Shahzad, Alexandra Ion. 2026. While You’re Still Busy: Context-Aware Approach Optimization for Proactive Mobile Robots. In Proceedings of UIST ’26. Detroit, MI, USA. November 2-5, 2026. DOI: https://doi.org/10.1145/3830398.3830714