行動 ALOHA：使用低成本全身遠端操作學習雙手行動機器人操作

摘要

從人類示範中學習的模仿學習在機器人技術中展現了令人印象深刻的表現。然而，大多數研究結果集中在桌面操作，缺乏對於一般實用任務所需的移動性和靈巧性。在這項研究中，我們開發了一個系統，用於模仿雙手雙足控制的移動操作任務。我們首先提出了Mobile ALOHA，這是一個用於數據收集的低成本全身遠程操作系統。它通過增加移動底盤和全身遠程操作界面來擴展ALOHA系統。利用Mobile ALOHA收集的數據，我們進行了監督式行為克隆，發現與現有靜態ALOHA數據集進行聯合訓練可以提高移動操作任務的性能。對於每個任務的50個示範，聯合訓練可以將成功率提高多達90％，使Mobile ALOHA能夠自主完成複雜的移動操作任務，例如炒和上菜一塊蝦、打開一個雙門壁櫥以存放沉重的炊具、呼叫並進入電梯，以及使用廚房水龍頭輕輕沖洗使用過的平底鍋。項目網站：https://mobile-aloha.github.io

English

Imitation learning from human demonstrations has shown impressive performance in robotics. However, most results focus on table-top manipulation, lacking the mobility and dexterity necessary for generally useful tasks. In this work, we develop a system for imitating mobile manipulation tasks that are bimanual and require whole-body control. We first present Mobile ALOHA, a low-cost and whole-body teleoperation system for data collection. It augments the ALOHA system with a mobile base, and a whole-body teleoperation interface. Using data collected with Mobile ALOHA, we then perform supervised behavior cloning and find that co-training with existing static ALOHA datasets boosts performance on mobile manipulation tasks. With 50 demonstrations for each task, co-training can increase success rates by up to 90%, allowing Mobile ALOHA to autonomously complete complex mobile manipulation tasks such as sauteing and serving a piece of shrimp, opening a two-door wall cabinet to store heavy cooking pots, calling and entering an elevator, and lightly rinsing a used pan using a kitchen faucet. Project website: https://mobile-aloha.github.io

行動 ALOHA：使用低成本全身遠端操作學習雙手行動機器人操作

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

摘要

Support