# RoboCSE: Robot Common Sense Embedding

## TL;DR

RoboCSE introduces a multi-relational embedding framework for robots to generalize semantic knowledge in real-world environments, demonstrating improved prediction accuracy and robustness over existing methods.

## Contribution

This work applies multi-relational embeddings to robotics, enabling better generalization and efficiency in modeling semantic knowledge for autonomous robots.

## Key findings

- RoboCSE outperforms Word2Vec-based baseline in prediction accuracy.
- RoboCSE uses significantly less memory than Bayesian Logic Networks.
- RoboCSE maintains robustness with reduced training data and domain transfer.

## Abstract

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.