Human-in-the-Loop SLAM
Authors: Samer Nashed, Joydeep Biswas
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present empirical results showing the effectiveness of Hit L-SLAM at generating globally accurate and consistent maps even when given poor initial estimates of the map. |
| Researcher Affiliation | Academia | Samer B. Nashed, Joydeep Biswas College of Information and Computer Sciences 140 Governors Drive Amherst MA, USA 01003 |
| Pseudocode | No | The paper describes the system's process flow and components in text and diagrams (e.g., Figure 3), but it does not include any explicitly labeled 'Pseudocode' or 'Algorithm' blocks. |
| Open Source Code | Yes | Code and sample data is available at: https://github.com/umass-amrl/hitl-slam |
| Open Datasets | Yes | Code and sample data is available at: https://github.com/umass-amrl/hitl-slam |
| Dataset Splits | No | The paper describes constructing its own datasets and evaluating the system's performance on these, but it does not specify explicit training, validation, or test dataset splits with percentages or sample counts for reproducibility. |
| Hardware Specification | Yes | The authors would like to thank Manuela Veloso from Carnegie Mellon University for providing the Co Bot4 robot used to collect the AMRL datasets, and to perform experiments at University of Massachusetts Amherst. |
| Software Dependencies | No | The paper references other algorithms like Episodic non-Markov Localization (EnML) and Closed-Form Online Pose-Chain SLAM (COP-SLAM), but it does not list specific software dependencies with version numbers (e.g., 'Python 3.8', 'PyTorch 1.9'). |
| Experiment Setup | No | The paper mentions experimental conditions such as limiting the robot's laser range to '1.5m' and introduces constants K1 and K2 for translational and rotational error costs, and a threshold Tp for outlier rejection, but it does not provide specific numerical values for these hyperparameters or other system-level training settings like learning rates or batch sizes. |