SOURCE-LINKED INTELLIGENCE

LTLDiff: Finite Linear Temporal Logic-Guided Data Generation and Diffusion Policies for Multi-agent Robotic Manipulation

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Multi-agent robotic manipulation tasks require coordination among agents to satisfy task-level temporal, logical, and safety constraints. Recently, diffusion policies have been used to perform the task. However, they still suffer from desynchronization, incorrect action ordering, and coordination failures in tasks that require simultaneous or sequential multi-agent interaction. Therefore, LTLDiff is proposed as a framework that combines Finite Linear Temporal Logic (LTLf) specification learning for both the generation of demonstrations and learning via diffusion policies. Each task has a speci

Read original source ↗ Open in workspace

recordType

paper

region

Global