arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1910.03568cs.CVcs.RO
收藏

以对象为中心的模型预测控制前向建模

Object-centric Forward Modeling for Model Predictive Control

Carnegie Mellon University(卡内基梅隆大学);Facebook AI Research(脸书人工智能研究院)

Yufei Ye, Dhiraj Gandhi, Abhinav Gupta, Shubham Tulsiani

摘要:

我们提出了一种学习以对象为中心的前向模型的方法,并表明这使我们能够计划行动序列,以实现遥远的预期目标。我们建议将场景建模为对象的集合,每个对象都具有显式的空间位置和隐式的视觉特征,并学习使用随机交互数据对动作的效果进行建模。我们的模型允许捕获机器人-对象和对象-对象的交互,并导致更有效的样本和准确的预测。我们表明,可以利用这个学习模型来搜索导致所需目标配置的动作序列,并且与学习的纠正模块结合,这可以实现鲁棒的闭环执行。我们目前在模拟和现实世界中的实验,并表明,我们的方法提高了替代隐式或像素空间的前向模型。请查看我们的项目页面(https://judyye.github.io/ocmpc/)获取结果视频。

英文摘要:

We present an approach to learn an object-centric forward model, and show that this allows us to plan for sequences of actions to achieve distant desired goals. We propose to model a scene as a collection of objects, each with an explicit spatial location and implicit visual feature, and learn to model the effects of actions using random interaction data. Our model allows capturing the robot-object and object-object interactions, and leads to more sample-efficient and accurate predictions. We show that this learned model can be leveraged to search for action sequences that lead to desired goal configurations, and that in conjunction with a learned correction module, this allows for robust closed loop execution. We present experiments both in simulation and the real world, and show that our approach improves over alternate implicit or pixel-space forward models. Please see our project page (https://judyye.github.io/ocmpc/) for result videos.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑