GP-Localize: Persistent Mobile Robot Localization Using Online Sparse Gaussian Process Observation Model
Authors: Nuo Xu, Kian Hsiang Low, Jie Chen, Keng Kiat Lim, Etkin Ozgul
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirical evaluation via simulated experiments with real-world datasets and a real robot experiment shows that GP-Localize outperforms existing GP localization algorithms. |
| Researcher Affiliation | Academia | Department of Computer Science, National University of Singapore, Republic of Singapore Singapore-MIT Alliance for Research and Technology, Republic of Singapore {xunuo, lowkh, kengkiat, ebozgul}@comp.nus.edu.sg , chenjie@smart.mit.edu |
| Pseudocode | No | The paper describes algorithms verbally and mathematically but does not include a dedicated pseudocode block or algorithm figure. |
| Open Source Code | No | The paper does not provide an explicit statement about the release of source code or a link to a code repository. |
| Open Datasets | Yes | (a) Wireless signal strength (WSS) (signal-to-noise ratio) data (Chen and Guestrin 2007) produced by 6 Wi Fi access points (APs) and measured at over 200 locations throughout the fifth floor of Wean Hall in Carnegie Mellon University (Fig. 1, Section 4.1), (b) indoor environmental quality (IEQ) (i.e., temperature ( F) and light (Lux)) data (Bodik et al. 2004) measured by 54 sensors deployed in the Intel Berkeley Research lab (Fig. 3, Section 4.2), (c) urban traffic speeds (UTS) (km/h) data (Chen et al. 2012; 2013) measured at 775 road segments... |
| Dataset Splits | No | The paper describes different datasets and experiment runs but does not specify explicit training, validation, or test dataset splits. |
| Hardware Specification | No | The paper mentions a 'Pioneer 3-DX mobile robot' as part of the experiment setup, but does not provide specific details on the computational hardware (e.g., CPU, GPU models, memory) used for running the models or simulations. |
| Software Dependencies | No | The paper mentions software like 'Player/Stage simulator' and 'Robot Operating System (ROS)' but does not provide specific version numbers for these or other software dependencies. |
| Experiment Setup | Yes | Our GP-Localize algorithm is implemented using an odometry motion model4, our online sparse GP (i.e., setting τ = 10 and |S| = 40) for representing the observation model (Section 3), and a particle filter4 of 400 particles for representing the belief of the robot s location. The number C of sample paths in (9) is set to 400 for all experiments. |