GEF: A Self-Programming Robot Using Grammatical Evolution

Authors: Charles Peabody, Jennifer Seitzer

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our first meta-level jumping experiment evolved a program that enabled the Finch to successfully navigate the proper exit of a room through a specified door. We then intentionally closed that door at which point the robot had to (a) realize there was a problem, (b) alert the meta-script with the current instruction number, and (c) wait for another program to be wirelessly downloaded.
Researcher Affiliation Academia Charles Peabody and Jennifer Seitzer Department of Mathematics and Computer Science Rollins College, Winter Park, FL 32789 {cpeabody, jseitzer}@rollins.edu
Pseudocode No While Figure 2 is labeled 'GEF System Architecture and Algorithm', it is a diagram and not a structured pseudocode or algorithm block in text format.
Open Source Code No The paper does not include an unambiguous statement that the authors are releasing the code for the work described in this paper, nor a direct link to a source-code repository.
Open Datasets No The paper describes experiments conducted with a Finch robot in a physical environment and does not mention the use of any specific publicly available or open dataset for training or evaluation.
Dataset Splits No The paper describes the robot's behavior and experiments (e.g., navigating a room, handling contingencies) but does not provide specific details about training, validation, or test dataset splits.
Hardware Specification No The paper mentions a 'raspberry pi controller' and a 'laptop' as computational loci but does not provide specific hardware details such as CPU/GPU models, processor types, or memory amounts.
Software Dependencies No The paper mentions 'Java' as the programming language for the robot controller program but does not provide specific version numbers for Java or any other software libraries or dependencies used in the system.
Experiment Setup No The paper describes the system's design and operational flow, including aspects like meta-level jumps and the robot's interaction with its environment, but it does not specify concrete experimental setup details such as hyperparameter values (e.g., for Grammatical Evolution) or training configurations.