arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.09355cs.RO
收藏

结合部分动作执行学习效应的多步规划

Multi-step planning with learned effects of partial action executions

Bogazici University(博加齐奇大学)

Hakan Aktas, Utku Bozdogan, Emre Ugur

AI总结:

提出一种基于Conditional Neural Processes的affordance模型,通过预测部分动作执行的中间效应并结合A*算法实现更准确有效的多步规划。

摘要:

在本文中,我们提出了一种新颖的affordance模型,该模型在基于Conditional Neural Processes构建的预测性神经网络架构的潜在空间中,结合了物体、动作和效应信息。我们的模型允许我们对动作执行期间预期获得的中间效应进行预测,并制定包含部分动作的多步规划。我们首先使用现有的交互数据集比较了模型的预测能力,结果表明在预测lever-up动作的效应时,它优于基于循环神经网络的模型。接下来,我们展示了模型能够为其他动作(如push和grasp动作)生成准确的效应预测。我们的系统被证明能够使用传统的A*搜索算法生成成功的多步规划,将物体带到期望位置。此外,我们实现了一种连续规划方法,并表明与仅考虑完整动作执行的规划相比,使用两种规划算法时,所提出的系统通过部分动作执行序列生成了更准确、更有效的规划。

英文摘要:

In this paper, we propose a novel affordance model, which combines object, action, and effect information in the latent space of a predictive neural network architecture that is built on Conditional Neural Processes. Our model allows us to make predictions of intermediate effects expected to be obtained during action executions and make multi-step plans that include partial actions. We first compared the prediction capability of our model using an existing interaction data set and showed that it outperforms a recurrent neural network-based model in predicting the effects of lever-up actions. Next, we showed that our model can generate accurate effect predictions for other actions, such as push and grasp actions. Our system was shown to generate successful multi-step plans to bring objects to desired positions using the traditional A* search algorithm. Furthermore, we realized a continuous planning method and showed that the proposed system generated more accurate and effective plans with sequences of partial action executions compared to plans that only consider full action executions using both planning algorithms.

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。

↑