Online, Interactive User Guidance for High-dimensional, Constrained Motion Planning

Authors: Fahad Islam, Oren Salzman, Maxim Likhachev

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate our approach for the case where the planning algorithm is Multi-Heuristic A* (MHA*) and the robot is a 34-DOF humanoid. We show that our approach allows to compute highly-constrained paths with little domain knowledge.
Researcher Affiliation Academia Fahad Islam, Oren Salzman and Maxim Likhachev The Robotics Institute, Carnegie Mellon University {fi,osalzman}@andrew.cmu.edu, maxim@cs.cmu.edu
Pseudocode Yes Algorithm 1 User-guided Planning (A); Algorithm 2 User-guided MHA*
Open Source Code No The paper does not mention or provide a link to any open-source code for the described methodology.
Open Datasets No The paper mentions using a 34-DOF WAREC humanoid robot and motion primitives, which suggests internal data or simulation, but does not provide any public access information (link, DOI, citation) for a dataset.
Dataset Splits No The paper mentions running experiments over "ten different trials" but does not specify any training, validation, or test dataset splits or ratios.
Hardware Specification No The paper does not specify any hardware details such as CPU, GPU models, or memory used for running the experiments.
Software Dependencies No The paper mentions MHA* as the planning algorithm but does not provide specific software versions or dependencies (e.g., Python, PyTorch versions).
Experiment Setup Yes The parameter values used in both experiments are ω1(200), ω2(50) and ε(50) for the heuristic-based, and τ(30) and ω(10) for the vacillation-based stagnation-region detection.