Get Started
Research questionHow can long-horizon indoor mobile manipulators track embodiment state and repair plans without dense scene maps?A mobile manipulator’s later actions can become infeasible when earlier skills change object locations or gripper occupancy. The planner must also detect when execution diverges from its assumptions and revise the remaining actions.
Multimodal Models
Reasoning
Robotics
Latest papersRecent research connected to this question, newest first.MoMaStage: Skill-State Graph Guided Planning and Closed-Loop Execution for Long-Horizon Indoor Mobile ManipulationThe work studies a frozen vision-language model coupled to a mobile manipulator through executable skills, a topology-only Skill-State Graph, state verification, and event-driven monitoring. Evidence comes from physics-rich simulation and a real mobile manipulator, with comparisons limited to the evaluated baselines.research paper · Sep 3, 2026
Related questions
How can vision-language-action systems reliably execute long-horizon manipulation while tracking state and conditional dependencies?How can we diagnose vision-language-action models’ failures on spatially ambiguous, long-horizon manipulation tasks?How can quadruped mobile manipulators reach manipulation-ready poses and maintain stable contact?How can object-centric world models predict manipulation-induced changes without accumulating errors that derail planning?
Home
Topics
Search
Library