Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Going Beyond Literal Command-Based Instructions: Extending Robotic Natural Language Interaction Capabilities
Authors: Tom Williams, Gordon Briggs, Bradley Oosterveld, Matthias Scheutz
AAAI 2015 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the potential of these inference algorithms for natural human-robot interactions by running them as part of an integrated cognitive robotic architecture on a mobile robot in a dialoguebased instruction task. and To demonstrate the operation of the proposed inference algorithms for natural human-robot interactions, we consider a dialogue interaction that occurs as part of a Search-and Rescue Task. |
| Researcher Affiliation | Academia | Tom Williams, Gordon Briggs, Bradley Oosterveld, and Matthias Scheutz Human-Robot Interaction Laboratory Tufts University, Medford, MA, USA EMAIL |
| Pseudocode | Yes | Algorithm 1 get Intended Meaning({ΘU,mu},{ΘC,mc},R) and Algorithm 2 get Semantics({ΘI,mi},{ΘC,mc},R) |
| Open Source Code | No | The paper only provides a link to a video demonstration: 'A video of this interaction in operation on a Willow Garage PR2 robot can be viewed at https://vimeo.com/106203678.'. There is no explicit statement or link for the source code of the methodology described in the paper. |
| Open Datasets | No | The paper describes a demonstration scenario with predefined conditions and pragmatic rules for a 'Search-and Rescue Task', but it does not specify a publicly available or open dataset for training or evaluation. |
| Dataset Splits | No | The paper describes a demonstration and specific scenarios (Ulow, Umed, Uhigh, Cjim, Crobot, Cunk) with predefined parameters and rules, but it does not provide specific dataset split information (e.g., percentages or sample counts) for training, validation, or testing. |
| Hardware Specification | Yes | A video of this interaction in operation on a Willow Garage PR2 robot can be viewed at https://vimeo.com/106203678. |
| Software Dependencies | No | The paper mentions using the DIARC architecture and Dempster-Shafer theory but does not provide specific software dependencies with version numbers (e.g., library names with versions like 'Python 3.8' or 'PyTorch 1.9'). |
| Experiment Setup | Yes | All beliefs and plausibilities listed in this section are rounded to two decimal places for the reader s convenience. and Ulow (with uncertainty interval [0.95, 1.00]), Umed (with uncertainty interval [0.62, 0.96]), and Uhigh (with uncertainty interval [0.31, 0.81]). and We introduce an uncertainty threshold Λ (set to 0.1) |