robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

์ €์ž: Yuke Zhu, Josiah Wong, Ajay Mandlekar, Roberto Martรญn-Martรญn, Abhishek Joshi, Kevin Lin, Abhiram Maddukuri, Soroush Nasiriany, Yifeng Zhu | ๋‚ ์งœ: 2020-09-25 | URL: https://arxiv.org/abs/2009.12293 📄 PDF


Essence

Figure 2

Figure 2: System diagram of robosuite modules. An actor (e.g. a Policy or

robosuite๋Š” MuJoCo ๋ฌผ๋ฆฌ ์—”์ง„์„ ๊ธฐ๋ฐ˜์œผ๋กœ ํ•˜๋Š” ๋ชจ๋“ˆ์‹ ๋กœ๋ด‡ ์‹œ๋ฎฌ๋ ˆ์ด์…˜ ํ”„๋ ˆ์ž„์›Œํฌ๋กœ, ๋กœ๋ด‡ ํ•™์Šต ์—ฐ๊ตฌ๋ฅผ ์œ„ํ•œ ๋ฒค์น˜๋งˆํฌ ํ™˜๊ฒฝ๊ณผ ์žฌํ˜„ ๊ฐ€๋Šฅํ•œ ์‹คํ—˜ ํ™˜๊ฒฝ์„ ์ œ๊ณตํ•œ๋‹ค.

Motivation

Achievement

Figure 1

Figure 1: Procedurally generated robotic environments with robosuite APIs

How

Figure 2

Figure 2: System diagram of robosuite modules. An actor (e.g. a Policy or

Originality

Limitation & Further Study

Evaluation

Novelty: 4/5 Technical Soundness: 3/5 Significance: 4/5 Clarity: 4/5 Overall: 4/5

์ดํ‰: robosuite๋Š” ๋กœ๋ด‡ ํ•™์Šต ์ปค๋ฎค๋‹ˆํ‹ฐ๋ฅผ ์œ„ํ•œ ํฌ๊ด„์ ์ด๊ณ  ์ž˜ ์„ค๊ณ„๋œ ์˜คํ”ˆ์†Œ์Šค ํ”„๋ ˆ์ž„์›Œํฌ๋กœ, ๋ชจ๋“ˆ์‹ ์•„ํ‚คํ…์ฒ˜์™€ ํ‘œ์ค€ํ™”๋œ ๋ฒค์น˜๋งˆํฌ๋ฅผ ํ†ตํ•ด ์žฌํ˜„ ๊ฐ€๋Šฅํ•œ ์—ฐ๊ตฌ๋ฅผ ์ด‰์ง„ํ•˜๋ฉฐ AI-๋กœ๋ณดํ‹ฑ์Šค ๊ต์ฐจ ๋ถ„์•ผ์˜ ์ง„์ž… ์žฅ๋ฒฝ์„ ํ˜„์ €ํžˆ ๋‚ฎ์ถ˜๋‹ค.

← ๋ชฉ๋ก์œผ๋กœ ๋Œ์•„๊ฐ€๊ธฐ

๐ŸŽง Audio Overview

์ด ๋…ผ๋ฌธ ๋ฆฌ๋ทฐ๋ฅผ ํŒŸ์บ์ŠคํŠธํ˜• ์˜ค๋””์˜ค๋กœ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค. (Gemini ยท ํ‚ค๋Š” ๋ธŒ๋ผ์šฐ์ €์—๋งŒ ์ €์žฅ ยท ์™„์„ฑ๋ณธ์€ ์ด๋ฉ”์ผ๋กœ๋„ ์ „์†ก)
โ–ธ ๊ณ ๊ธ‰: ๊ตฌ์„ฑ ๋ฐฉํ–ฅ(๋Œ€๋ณธ ์ž‘์„ฑ ์ง€์นจ) ์ง์ ‘ ์ˆ˜์ •