Reactive Integrated Motion Planning and Execution

Authors: Andreas G. Hofmann, Enrique Fernandez, Justin Helbert, Scott D. Smith, Brian C. Williams

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

Reproducibility Variable Result LLM Response
Research Type Experimental Testing in simulation, and with a robot testbed has shown improvement in planning speed and motion predictability over current motion planners.
Researcher Affiliation Academia Andreas Hofmann, Enrique Fernandez, Justin Helbert, Scott Smith, Brian Williams Massachusetts Institute of Technology 77 Massachusetts Ave. Cambridge, MA 02140
Pseudocode No The paper describes algorithmic concepts but does not present any structured pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper mentions integrating Chekhov with and modifying open-source platforms like Open RAVE, OMPL, and ROS Move It!, but it does not provide an explicit statement or link for the open-sourcing of Chekhov's own code.
Open Datasets No The paper describes conducting tests in a simulated environment and with a robot testbed, involving generated obstacles, but it does not mention the use of a publicly available dataset or provide access information for any dataset it might have created for training/testing.
Dataset Splits No The paper does not provide specific details on dataset splits (e.g., training, validation, testing percentages or counts) or reference predefined splits for reproducibility. Experiments involve generating obstacles for testing rather than using a static dataset with splits.
Hardware Specification Yes These tests were performed using a Macbook Pro, with a 2.3GHz Intel Core i7 (4 cores), running a Linux virtual machine.
Software Dependencies No The paper mentions using "Open RAVE environment", "Open Motion Planning Library (OMPL)", and "ROS Move It!", but it does not provide specific version numbers for these or any other software dependencies.
Experiment Setup Yes In order to test the performance of the incremental update of the APSP structure (and therefore, of incremental re-planning), we repeated the obstacle test, 300 times, with cube-shaped boxes, ranging from 0.2 to 0.6 meters (edge length), placed at random points in the workspace.