Interactive Planning Using Large Language Models for Partially Observable Robotic Tasks.
Lingfeng SunDevesh K. JhaChiori HoriSiddarth JainRadu CorcodelXinghao ZhuMasayoshi TomizukaDiego RomeresPublished in: ICRA (2024)
Keyphrases
- language model
- partially observable
- robotic tasks
- belief space
- planning under uncertainty
- markov decision processes
- motion planning
- dynamical systems
- decision problems
- state space
- reinforcement learning
- partially observable markov decision processes
- belief state
- information retrieval
- document retrieval
- query expansion
- probabilistic model
- infinite horizon
- retrieval model
- planning domains
- robotic systems
- test collection
- planning problems
- dynamic environments
- decision theoretic
- reward function
- degrees of freedom
- ai planning
- mobile robot
- multi modal
- markov chain
- dynamic programming
- orders of magnitude
- finite state
- machine learning