Get Started
Home
Topics
Search
Library
Research questionHow can real-time social robots reason over long-term context and decide when to act without disrupting fluent multimodal interaction?A social robot must keep producing natural multimodal behavior while integrating accumulated dialogue and visual context. Deliberative reasoning can conflict with continuous interaction when proactive interventions must be chosen within a tight latency budget.
AI
AI Agents
AI Memory
Evaluation & Benchmarks
Inference Optimization
Multimodal Models
Reasoning
Robotics
Latest papersRecent research connected to this question, newest first.ProAct: Harnessing Streaming Motion Generation and Agentic Reasoning for Real-Time Embodied Social InteractionThe source addresses a physical humanoid robot with separate low-latency behavioral and slower cognitive processes. The cognitive process uses accumulated dialogue and visual context to predict user motivation and determine when to intervene, while motion generation follows high-level intentions. Evidence is limited to the reported real-world user studies, motion-generation benchmarks, and ProActBench evaluation of proactive trigger detection and restraint.research paper · Sep 3, 2026
Related questions
How can language-conditioned robots preserve executable actions under irrelevant wording while composing multiple changed constraints correctly?How can robots recognize social gestures in real time despite occlusion, viewpoint changes, and noisy keypoints?How can an accessible humanoid robot integrate multimodal AI for real-world human interaction?How can heterogeneous robot teams coordinate long-horizon tasks with low-latency, resource-aware parallel execution?