...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>The International journal of robotics research >Scaling simulation-to-real transfer by learning a latent space of robot skills
【24h】

Scaling simulation-to-real transfer by learning a latent space of robot skills

机译：通过学习机器人技能的潜在空间来缩放模拟 - 实际转移

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

We present a strategy for simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we propose a method for increasing the sample efficiency and robustness of existing simulation-to-real approaches which exploits hierarchy and online adaptation. Instead of learning a unique policy for each desired robotic task we learn a diverse set of skilk and their variations, and embed those skill variations in a continuously parameterized space. We then interpolate, search, and plan in this space to find a transferable policy which solves more complex, high-level tasks by combining low-level skilk and their variations. In this work, we first characterize the behavior of this learned skill space, by experimenting with several techniques for composing pre-learned latent skills. We then discuss an algorithm which allows our method to perform long-horizon tasks never seen in simulation, by intelligently sequencing short-horizon latent skills. Our algorithm adapts to unseen tasks online by repeatedly choosing new skills from the latent space, using live sensor data and simulation to predict which latent skill will perform best next in the real world. Importantly, our method learns to control a real robot in joint-space to achieve these high-level tasks with little or no on-robot time, despite the fact that the low-level policies may not be perfectly transferable from simulation to real, and that the low-level skills were not trained on any examples of high-level tasks. In addition to our results indicating a lower sample complexity for families of tasks, we believe that our method provides a promising template for combining learning-based methods with proven classical robotics algorithms such as model-predictive control.
机译：我们提出了一种模拟与实际转移的策略，它在最近的机器人技能分解中建立了最近的进步。我们提出了一种提高利用层次结构和在线适应的现有模拟 - 实际方法的采样效率和稳健性的方法，而不是最小化仿真现实差距。而不是为每个所需的机器人任务学习独特的政策，我们学习多样化的Skilk及其变化，并在连续参数化空间中嵌入这些技能变化。然后，我们在这个空间内插入，搜索和计划，找到一个可转让的策略，通过组合低级Skilk及其变体来解决更复杂，高级任务。在这项工作中，我们首先通过试验若干技术来组合撰写预先学习的潜在技能的技术来表征这项学习技能空间的行为。然后，我们讨论了一种允许我们的方法执行在模拟中从未见过的长地平线任务，通过智能地测序短地平线潜在技能。我们的算法通过反复选择来自潜在空间的新技能，使用Live Sensor数据和仿真来预测在现实世界中最佳的潜在技能将在线选择新技能，适应在线。重要的是，我们的方法学会在联合空间中控制一个真正的机器人，以实现很少或没有机器人时间的这些高级任务，尽管低级策略可能无法从模拟完全可转移到真实，以及低级技能没有接受任何高级任务的例子培训。除了我们的结果表明，表明任务家庭的样本复杂性较低，我们认为我们的方法提供了一个有前途的模板，用于将基于学习的方法与经过验证的经典机器人算法相结合，如模型预测控制。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号