arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.00330cs.RO
收藏

基于GPU的动态学习路径积分控制

GPU Based Path Integral Control with Learned Dynamics

Georgia Institute of Technology(佐治亚理工学院);University of Washington(华盛顿大学)

Grady Williams, Eric Rombokas, Tom Daniel

摘要:

我们提出了一种算法,结合了最新的进展,基于模型的路径积分控制与机器学习方法来学习前向动力学模型。我们利用GPU的并行计算能力,从学习的概率动力学模型中快速获取大量样本,我们使用这些样本来近似最优控制的路径积分形式。由此产生的算法以滚动时域的方式实时运行,并且不受关于成本、约束或动态的限制性假设的影响。一个简单的变化的路径积分控制制定允许算法在规划过程中考虑模型的不确定性,我们证明了其性能的四旋翼导航任务。除了这种新颖的适应路径积分控制,这是第一次,滚动时域实现迭代路径积分控制已运行在一个真实的系统。

英文摘要:

We present an algorithm which combines recent advances in model based path integral control with machine learning approaches to learning forward dynamics models. We take advantage of the parallel computing power of a GPU to quickly take a massive number of samples from a learned probabilistic dynamics model, which we use to approximate the path integral form of the optimal control. The resulting algorithm runs in a receding-horizon fashion in realtime, and is subject to no restrictive assumptions about costs, constraints, or dynamics. A simple change to the path integral control formulation allows the algorithm to take model uncertainty into account during planning, and we demonstrate its performance on a quadrotor navigation task. In addition to this novel adaptation of path integral control, this is the first time that a receding-horizon implementation of iterative path integral control has been run on a real system.

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。

↑