MIDCA: A Metacognitive, Integrated Dual-Cycle Architecture for Self-Regulated Autonomy

Authors: Michael Cox, Zohreh Alavi, Dustin Dannenhauer, Vahid Eyorokon, Hector Munoz-Avila, Don Perlis

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We formally define the mechanism and report empirical results from this goal generation algorithm. Finally, we describe the similarity between its choices at the cognitive level with those at the metacognitive.
Researcher Affiliation Academia Michael T. Cox, Zohreh Alavi, Dustin Dannenhauer,* Vahid Eyorokon, Hector Munoz-Avila,* and Don Perlis Wright State University Dayton, OH 45435 michael.cox@wright.edu *Lehigh University Bethlehem, PA 18015 hem4@lehigh.edu University of Maryland College Park, MD 20742 perlis@cs.umd.edu
Pseudocode No The paper provides formal definitions using mathematical equations and block diagrams, but it does not include any structured pseudocode or clearly labeled algorithm blocks.
Open Source Code Yes The full source code with documentation and examples is available at https://github.com/mclumd/MIDCA
Open Datasets No The paper refers to a "blocksworld domain implemented in the standard simulator" but does not provide specific access information (link, DOI, or formal citation) for the dataset used in the experiments.
Dataset Splits No The paper describes experimental scenarios but does not provide specific dataset split information (e.g., percentages or sample counts for training, validation, or test sets) needed to reproduce the data partitioning.
Hardware Specification No The paper mentions interacting with a "Baxter humanoid robot" but does not provide specific details about the computing hardware (e.g., CPU, GPU models, memory) used to run the simulations or train the system.
Software Dependencies No The paper mentions software components like "SHOP2 hierarchical network planner", "XPLAIN/Meta-AQUA", and "ROS middleware", but it does not provide specific version numbers for these or any other software dependencies.
Experiment Setup No The paper describes the experimental domain (blocksworld, house building) and the conditions tested (exogenous goals, statistical goal generation, GDA), but it does not provide concrete numerical values for hyperparameters or other system-level training settings needed to reproduce the experiments.