Object-Based World Modeling in Semi-Static Environments with Dependent Dirichlet Process Mixtures

Authors: Lawson L. S. Wong, Thanard Kurutach, Tomás Lozano-Pérez, Leslie Pack Kaelbling

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

Reproducibility Variable Result LLM Response
Research Type Experimental 6 Experiments Approximate MAP inference for world modeling via ICM, MCMCDA, and the two-stage ICM-MCMC were tested on a simulated domain, and on a sequence of robot vision data constructed from the static scenes in Wong et al. [2015].
Researcher Affiliation Academia Lawson L. S. Wong Brown University Providence, RI 02912 lsw@brown.edu Thanard Kurutach, Tom as Lozano-P erez, MIT Computer Science and Artificial Intelligence Laboratory Cambridge, MA 02139, USA {kurutach, tlp, lpk}@csail.mit.edu Leslie Pack Kaelbling
Pseudocode Yes Figure 2: ICM-MCMC, a two-stage inference algorithm for DDPMM, using ICM and MCMCDA [Oh et al., 2009].
Open Source Code No The paper does not provide any specific links to source code repositories, nor does it state that the code is being released or is available in supplementary materials.
Open Datasets Yes We used a simulated domain similar to the one given in the MCMCDA paper [Oh et al., 2009]. We also applied the same algorithms to the static robot vision data from Wong et al. [2015].
Dataset Splits No The paper mentions using a simulated domain over '10 epochs' and '5 views per epoch', and concatenating 'static robot vision data from Wong et al. [2015]' to create dynamic scenes. However, it does not explicitly provide specific train/validation/test dataset splits (e.g., percentages, sample counts, or predefined split citations) needed for reproducibility.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment.
Experiment Setup Yes Noise parameters were similar to Oh et al. [2009]. between epochs, we assume that the location changes with isotropic Gaussian noise, standard deviation 0.1. Since changes were significant between epochs, we assumed a relatively low 0.5 probability of survival. To perform MAP inference on MCMCDA and ICM-MCMC, the most-likely sample was chosen, from 105 samples in MCMCDA, and 104 in the second stage of ICM-MCMC.