Building Continuous Occupancy Maps With Moving Robots
Authors: Ransalu Senanayake, Fabio Ramos
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our claims are also experimentally validated with both simulated and real-world datasets. |
| Researcher Affiliation | Academia | Ransalu Senanayake, Fabio Ramos School of Information Technologies, The University of Sydney, Australia |
| Pseudocode | No | The paper presents mathematical equations (6)-(8) describing sequential learning steps, but these are not formatted or labeled as a formal pseudocode or algorithm block. |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-source code of the described methodology. It only provides a link for one of the datasets used. |
| Open Datasets | Yes | 1. Dataset 1: A publicly available simulated environment with moving obstacles used in (Senanayake, O Callaghan, and Ramos 2017). ... 3. Dataset 3: A real world dataset to represent an indoor environment at Intel Labs (publicly available: http://radish.sourceforge.net/). |
| Dataset Splits | No | The paper states that '10% of randomly chosen data that were never used for training were used to compute these metrics i.e. testing dataset.' However, it does not explicitly define the proportions for training and validation datasets, nor does it mention a dedicated validation set. |
| Hardware Specification | Yes | The program was developed using the Python programming language and an Intel corei7 laptop (no GPUs) with 8 GB RAM was used to conduct experiments. |
| Software Dependencies | No | The paper mentions that 'The program was developed using the Python programming language', but it does not specify the version of Python or any other software libraries or solvers with their respective version numbers. |
| Experiment Setup | Yes | w N(0, 10^4I) was used as the diffused prior and G matrix of the kernel were 16I, 13I, and 0.15I for datasets 1,2, and 3, respectively. |