Learning to Interpret Natural Language Commands through Human-Robot Dialog
Authors: Jesse Thomason, Shiqi Zhang, Raymond J Mooney, Peter Stone
IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We introduce a dialog agent for mobile robots that understands human instructions through semantic parsing, actively resolves ambiguities using a dialog manager, and incrementally learns from humanrobot conversations by inducing training data from user paraphrases. Our dialog agent is implemented and tested both on a web interface with hundreds of users via Mechanical Turk and on a mobile robot over several days, tasked with understanding navigation and delivery requests through natural language in an office environment. In both contexts, We observe significant improvements in user satisfaction after learning from conversations. |
| Researcher Affiliation | Academia | Jesse Thomason and Shiqi Zhang and Raymond Mooney and Peter Stone Department of Computer Science, University of Texas at Austin Austin, TX 78712, USA {jesse,szhang,mooney,pstone}@cs.utexas.edu |
| Pseudocode | No | The paper describes the system architecture and its components but does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper provides a link to Mechanical Turk (https://www.mturk.com) and a video demonstration (https://youtu.be/FL9IhJQOzb8), but no link or statement regarding the availability of the source code for the described methodology. |
| Open Datasets | No | The paper mentions collecting data through Mechanical Turk and on a Segbot, but it does not provide any access information (link, DOI, specific citation with authors/year) for the datasets collected or used, indicating they are not publicly available or open. |
| Dataset Splits | Yes | We split the possible task goals into train and test sets. For the 10 possible navigation goals (10 rooms), we randomly selected 2 for testing. For the 50 possible delivery goals (10 people 5 items), we randomly selected 10 for testing (80%/20% train/test split). |
| Hardware Specification | No | The paper mentions the 'Segway-based robot platform (Segbot)' and its sensors 'RGB-D camera (Kinect), laser, and sonar array'. However, it does not specify the computing hardware (e.g., CPU, GPU models, memory) used for running the experiments or training the models. |
| Software Dependencies | No | The paper mentions several software components like 'University of Washington Semantic Parsing Framework (SPF)', 'Robot Operating System (ROS)', 'action language BC', and 'existing ROS packages for path planning (e.g. A* search for global path planning and Elastic Band for local path planning)'. However, it does not provide specific version numbers for any of these components, which is required for reproducible software dependencies. |
| Experiment Setup | Yes | In all experiments, parameters α = 0.95, γ = 0.5 were used. To get the system off the ground we initialize the parser with a small seed lexicon pairings of lexical items with CCG categories and λ-calculus expressions and then train it on a small set of supervised utterance/logical-form pairs. We use a seed lexicon of 105 entries (40 of which are named entities) and a training set of only 5 pairs. |