# RoboCSE: Robot Common Sense Embedding

arXiv: https://arxiv.org/abs/1903.00412 · HTML: https://mlsanity.com/paper/1903.00412/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2019.

## Built on by (most cited first, 9 of 9)

- [Housekeep: Tidying Virtual Households using Commonsense Reasoning](https://mlsanity.com/paper/2205.10712/) (2022)
- [Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks](https://mlsanity.com/paper/2108.01176/) (2021)
- [Continual Learning of Knowledge Graph Embeddings](https://mlsanity.com/paper/2101.05850/) (2021)
- [Towards Robust One-shot Task Execution using Knowledge Graph Embeddings](https://mlsanity.com/paper/2105.04484/) (2021)
- [Explainable Knowledge Graph Embedding: Inference Reconciliation for Knowledge Inferences Supporting Robot Actions](https://mlsanity.com/paper/2205.01836/) (2022)
- [Graph learning in robotics: a survey](https://mlsanity.com/paper/2310.04294/) (2023)
- [Interactive Visual Task Learning for Robots](https://mlsanity.com/paper/2312.13219/) (2023)
- [Learning Embeddings that Capture Spatial Semantics for Indoor Navigation](https://mlsanity.com/paper/2108.00159/) (2021)
- [Semantic-Geometric-Physical-Driven Robot Manipulation Skill Transfer via Skill Library and Tactile Representation](https://mlsanity.com/paper/2411.11714/) (2024)

## Abstract (arXiv)

Autonomous service robots require computational frameworks that allow them to generalize knowledge to new situations in a manner that models uncertainty while scaling to real-world problem sizes. The Robot Common Sense Embedding (RoboCSE) showcases a class of computational frameworks, multi-relational embeddings, that have not been leveraged in robotics to model semantic knowledge. We validate RoboCSE on a realistic home environment simulator (AI2Thor) to measure how well it generalizes learned knowledge about object affordances, locations, and materials. Our experiments show that RoboCSE can perform prediction better than a baseline that uses pre-trained embeddings, such as Word2Vec, achieving statistically significant improvements while using orders of magnitude less memory than our Bayesian Logic Network baseline. In addition, we show that predictions made by RoboCSE are robust to significant reductions in data available for training as well as domain transfer to MatterPort3D, achieving statistically significant improvements over a baseline that memorizes training data.