Implicit Coordination in Crowded Multi-Agent Navigation

Authors: Julio Godoy, Ioannis Karamouzas, Stephen Guy, Maria Gini

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

Reproducibility Variable Result LLM Response
Research Type Experimental We experimentally validate our coordination approach in a variety of scenarios and show that its performance scales to scenarios with hundreds of agents.
Researcher Affiliation Academia Julio Godoy and Ioannis Karamouzas and Stephen J. Guy and Maria Gini Department of Computer Science and Engineering University of Minnesota 200 Union St SE, Minneapolis MN 55455
Pseudocode Yes Algorithm 1: The C-Nav framework for agent i; Algorithm 2: Compute most similar neighbors of i; Algorithm 3: Compute most constrained neighbors of i; Algorithm 4: Sim Motion(a) for agent i
Open Source Code No The paper includes a link for videos related to the results ("http://motion.cs.umn.edu/r/CNAV/ for videos") but does not explicitly state that the source code for the methodology is provided.
Open Datasets No The paper describes scenarios (Circle, Bidirectional, Crowd) but does not provide specific access information (link, DOI, formal citation with authors/year) for publicly available datasets.
Dataset Splits No The paper does not explicitly provide details about training/validation/test dataset splits (e.g., percentages, sample counts, or references to predefined splits).
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments were provided in the paper.
Software Dependencies No No specific software dependencies with version numbers (e.g., ORCA version, Python version, library versions) were mentioned in the paper.
Experiment Setup Yes In all our experiments, we used ORCA s default settings for the agent s radii (0.5 m), sensing range (15 m) and maximum number of agents sensed (num Neighs=10). We set T=2 timesteps, υmax=1.5 m/s, γ=0.9, k=3 and s=3. The timestep duration, Δt, is set to 25 ms.