谷歌旗下的DeepMind公司近期推出了一系列针对自主机器人训练的新系统和模型，这些系统和技术旨在解决机器人技术中的关键挑战，包括自主数据收集、计算效率和任务泛化。这些新系统包括AutoRT、SARA-RT和RT-Trajectory，它们都建立在Robotics Transformers基础模型之上。这些技术的应用有望简化机器人的决策流程，增强其对环境的理解能力，并提高机器人在复杂环境中的导航能力。这些进展标志着向更加强大的辅助机器人迈进的重要一步。
Title: DeepMind Advances in Autonomous Robot Training
Keywords: DeepMind, Autonomous Robots, Training Systems
News content:
DeepMind, a subsidiary of Google, has recently unveiled a series of new systems and models aimed at advancing autonomous robot training. These systems and technologies are designed to address key challenges in robotics, including autonomous data collection, computational efficiency, and task generalization. The new systems, including AutoRT, SARA-RT, and RT-Trajectory, are built upon the foundation of Robotics Transformers. The application of these technologies is expected to streamline decision-making processes, enhance environmental understanding, and improve navigation capabilities in complex environments. These advancements represent a significant step towards more powerful assistive robots.
【来源】https://www.maginative.com/article/google-deepmind-unveils-latest-research-in-advanced-robotics-with-autort-sara-rt-and-rt-trajectory/
Views: 1