目前 robotics 尤其是通用机器人到底研究进展如何?可以从Google DeepMind 在机器人方面在去年 PaLM-E 之后的六篇重要的工作中get到大概,
www.youtube.com 请DeepMind researcher 详细walk through了每一篇。high-level 来看,除了最大的bottleneck依然是数据,算法架构这边虽然还有一些challenges,但是离能够scale不远了。
👇六篇research
1️⃣ RT-2 (28 Jul 2023): how Internet scale vision language models allow robots to understand and manipulate objects that they have never seen in training.
arxiv.org2️⃣ RT-X (13 Oct 2023): a collaboration with academic labs across the country that demonstrates how a single model trained to control a diverse range of robot embodiments can outperform specialist models trained for individual robots.
arxiv.org3️⃣ RT-Trajectory (3 Nov 2023): a project that shows how robots can learn new skills in context from a single human demonstration represented by a simple line drawing.
arxiv.org4️⃣ AutoRT (23 Jan 2024): a system that scales human oversight of robots even in previously unseen environments using a combination of large language models and a robot constitution to power firstling ethical and safety checks.
arxiv.org5️⃣ Learning to learn faster (18 Feb 2024): an approach that enables robots to learn more efficiently from human verbal feedback.
arxiv.org6️⃣ PIVOT (12 Feb 2024): a project that shows how vision language models can be used to guide robot action, this time with no special fine-tuning required.
arxiv.org