Summary of Recover: a Neuro-symbolic Framework For Failure Detection and Recovery, by Cristina Cornelio and Mohammed Diab
Recover: A Neuro-Symbolic Framework for Failure Detection and Recovery
by Cristina Cornelio, Mohammed Diab
First submitted to arxiv on: 31 Mar 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG); Logic in Computer Science (cs.LO); Robotics (cs.RO)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers tackle the challenge of identifying failures during task execution and implementing recovery procedures in robotics. They propose a neuro-symbolic framework called Recover, which combines ontologies, logical rules, and large language models (LLMs) to generate recovery plans online. The framework is demonstrated in a simulated kitchen environment using the AI2Thor simulator setting, which includes an ontology describing the environment. The results show that Recover outperforms a baseline method solely relying on LLMs for both failure detection and recovery. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way to help robots recover from mistakes while doing tasks. Right now, most approaches need a lot of data or very specific rules to work well. Some newer methods use big language models to figure out what went wrong and come up with a plan to fix it. But these methods usually happen offline, which means the robot has to start over from scratch and can be expensive. The researchers created a new system called Recover that uses a combination of symbolic information and language models to identify failures and make plans to recover online. They tested their system in a virtual kitchen environment and showed that it works better than just using language models alone. |
