Perceiving, Learning, and Recognizing 3D Objects: An Approach to Cognitive Service Robots
Authors: S. Kasaei, Juil Sock, Luis Seabra Lopes, Ana Maria Tome, Tae-Kyun Kim
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We provide extensive experimental results demonstrating system performance in terms of recognition, scalability, next-best-view prediction and real-world robotic applications. Three types of experiments were performed to evaluate the proposed approach. |
| Researcher Affiliation | Academia | University of Aveiro, Aveiro, Portugal Imperial College London, London, UK {seyed.hamidreza, lsl, ana}@ua.pt {ju-il.sock08, tk.kim}@imperial.ac.uk |
| Pseudocode | No | The paper describes the algorithms and methods used, including mathematical formulations, but it does not present them in a structured pseudocode or clearly labeled algorithm block format. |
| Open Source Code | No | The paper provides links to demonstration videos and publicly available datasets, but it does not include an explicit statement or a direct link to the source code for the methodology described in the paper. |
| Open Datasets | Yes | The simulated teacher was connected to the Washington RGB-D Object Dataset (Lai et al. 2011). Imperial College Dataset (Doumanoglou et al. 2016). The dataset is publicly available at: https://goo.gl/BSr2m U |
| Dataset Splits | Yes | To examine the performance of the proposed approach, a 10-fold cross-validation has been used. |
| Hardware Specification | No | The paper mentions a 'JACO robotic arm manufactured by KINOVA' used for system demonstrations. However, it does not provide specific hardware details such as GPU/CPU models, processor types, or memory specifications used for running the main computational experiments (e.g., training models or processing large datasets). |
| Software Dependencies | No | The paper states that 'all modules were developed over Robot Operating System (ROS),' but it does not specify the version number for ROS or any other key software libraries or dependencies with their specific version numbers required for reproducibility. |
| Experiment Setup | No | The paper mentions that 'In all results, number of bins parameter of GOOD descriptor has been set to 15 bins.' However, it does not provide comprehensive experimental setup details such as learning rates, batch sizes, optimizer settings, training schedules, or other hyperparameters crucial for reproducing the experiments. |