TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators
Authors: Shreshth Tuli, Rajas Bansal, Rohan Paul, Mausam
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results show a 60.5-78.9% absolute improvement over the baseline in predicting successful symbolic plans in unseen settings for a simulated mobile manipulator. |
| Researcher Affiliation | Academia | 1Department of Computer Science and Engineering, Indian Institute of Technology Delhi, India 2Department of Computing, Imperial College London, UK |
| Pseudocode | No | The paper describes the model's architecture and processing steps in text and diagrams (Figure 2) but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | The implementation and data sets used in experiments are available at https://github.com/reail-iitd/tango. |
| Open Datasets | Yes | We use Py Bullet, a physics simulator [Coumans and Bai, 2016]... The implementation and data sets used in experiments are available at https://github.com/reail-iitd/tango. |
| Dataset Splits | Yes | The annotated corpus was split as (75% : 25%) forming the Training data set and the Test data set to evaluate model accuracy. A 10% fraction of the training data was used as the Validation set for hyper-parameter search. |
| Hardware Specification | No | The paper mentions 'the IIT Delhi HPC facility and Prof. Prem Kalra and Mr. Anil Sharma at the CSE VR Lab for compute resources' but does not provide specific hardware details such as GPU/CPU models or memory specifications. |
| Software Dependencies | No | The paper mentions 'Py Bullet, a physics simulator' and 'Fast Text embeddings' but does not provide specific version numbers for these or any other software dependencies required for replication. |
| Experiment Setup | No | The paper describes the neural network architecture and loss function but does not explicitly state specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or other detailed training configurations. |