Opening book details…
Can I read ERRA: An Embodied Representation and Reasoning Architecture for Long-Horizon Language-Conditioned Manipulation Tasks on EtoBox?
ERRA: An Embodied Representation and Reasoning Architecture for Long-Horizon Language-Conditioned Manipulation Tasks by Chao Zhao; Shuai Yuan; Chunli Jiang; Junhao Cai; Hongyu Yu; Michael Yu Wang; Qifeng Chen is a Engineering article available to read on EtoBox.
What is ERRA: An Embodied Representation and Reasoning Architecture for Long-Horizon Language-Conditioned Manipulation Tasks about?
This letter introduces ERRA, an embodied learning architecture that enables robots to jointly obtain three fundamental capabilities (reasoning, planning, and interaction) for solving longhorizon language-conditioned manipulation tasks. ERRA is based on tightly-coupled probabilistic inferences at two granularity levels. Coarse-resolution inference is formulated as sequence generation through a large language model, which infers action language from natural language instruction and environment state. The robot then zooms to the fine-resolution inference part to perform the concrete action corresponding to the action language. Fine-resolution inference is constructed as a Markov decision process, which takes action language and environmental sensing as observations and outputs the action. The results of action execution in environments provide feedback for subsequent coarse-resolution reasoning. Such coarse-to-fine inference allows the robot to decompose and achieve long-horizon tasks interactively. In extensive experiments, we show that ERRA can complete various long-horizon manipulation tasks specified by abstract language instructions. We also demonstrate successful generalization
Who reads ERRA: An Embodied Representation and Reasoning Architecture for Long-Horizon Language-Conditioned Manipulation Tasks?
It is typically read by researchers, students, and practitioners in Engineering.
- Author
- Chao Zhao; Shuai Yuan; Chunli Jiang; Junhao Cai; Hongyu Yu; Michael Yu Wang; Qifeng Chen
- Publisher
- Institute of Electrical and Electronics Engineers (IEEE)
- Published
- 2023
- Language
- EN
- Field
- Engineering (Physical Sciences)