Summary of Socratic Planner: Inquiry-based Zero-shot Planning For Embodied Instruction Following, by Suyeon Shin et al.
Socratic Planner: Inquiry-Based Zero-Shot Planning for Embodied Instruction Following
by Suyeon Shin, Sujin jeon, Junghyun Kim, Gi-Cheon Kang, Byoung-Tak Zhang
First submitted to arxiv on: 21 Apr 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); 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 The Socratic Planner is a novel, zero-shot planning method that enables embodied instruction following (EIF) without relying on labeled data or training. This planner decomposes instructions into substructural information through self-questioning and answers, creating a high-level plan as a sequence of subgoals. The planner executes these subgoals sequentially, adjusting plans dynamically using visually grounded re-planning mechanisms that incorporate environmental visual information. The Socratic Planner achieves competitive performance on zero-shot and few-shot task planning in the ALFRED benchmark, particularly excelling in tasks requiring higher-dimensional inference. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re playing a game where someone tells you what to do. For example, “Pick up the toy car and put it in the blue box.” You need to figure out how to do that based on what’s around you. This is called Embodied Instruction Following (EIF). The problem is that computers have trouble doing this without being taught exactly how to do each task. A new AI method, called Socratic Planner, can solve this problem without needing any training data. It breaks down the instructions into smaller steps and adjusts its plan as it goes based on what it sees around it. This method does very well in a challenge called ALFRED benchmark. |
Keywords
» Artificial intelligence » Few shot » Inference » Zero shot
