Introspective Planning: Aligning Robots’ Uncertainty with Inherent Task Ambiguity

Introspective Planning:

Aligning Robots' Uncertainty with Inherent Task Ambiguity

Please Check Project Website for More Details

We propose a novel introspective planning scheme that prompts language-enabled agents to proactively assess their own confidence regarding task compliance and safety for multiple candidate plans.

@article{liang2024introspective,
  title={Introspective Planning: Guiding Language-Enabled Agents to Refine Their Own Uncertainty},
  author={Liang, Kaiqu and Zhang, Zixu and Fisac, Jaime Fern{\'a}ndez},
  journal={arXiv preprint arXiv:2402.06529},
  year={2024}
}