FRAMES: Failure Recovery And Monitoring of Embodied Skills for Humanoid Loco-Manipulation
Large language model (LLM) planners can decompose natural-language instructions and select reusable robot skills, but choosing the correct skill does not guarantee successful physical execution. This gap is especially important in humanoid loco-manipulation, where errors during approach, grasping, transport, or placeme...
Ajay Vikram Periasami, Xin Luo, Hao-Yu Li et al.
· 0 citations