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 2209.05255cs.RO
收藏

基于因果关系的机器人任务故障解释、预测和预防方法

A Causal-based Approach to Explain, Predict and Prevent Failures in Robotic Tasks

Chalmers University of Technology(查尔姆斯理工大学)

Maximilian Diehl, Karinne Ramirez-Amaro

摘要:

在真实环境中工作的机器人需要适应意想不到的变化,以避免失败。这是一个开放而复杂的挑战,需要机器人及时预测和识别故障原因,以防止故障发生。在本文中,我们提出了一种因果关系的方法,使机器人能够预测错误可能发生的时间,并通过执行纠正措施来防止错误的发生。首先,我们提出了一个基于因果贝叶斯网络的方法来检测任务执行及其后果之间的因果关系。所获得的模型从模拟数据转移到真实场景,以证明所获得的模型的鲁棒性和通用性。基于因果BN,机器人可以预测执行的动作在其当前状态下是否会成功以及为什么会成功。然后,我们介绍了一种新的方法,通过对比广度优先搜索,找到最接近的状态的替代品,如果当前的行动被预测失败。我们评估我们的方法在两种情况下堆叠立方体的问题; a)单栈(堆叠一个立方体)和; b)多栈(堆叠三个立方体)。在单栈的情况下,我们的方法能够减少出错率的97%。我们还表明,我们的方法可以扩展到在一个模型中捕获多个动作,允许测量及时转移的动作效果,例如第一个立方体的不精确堆栈对第三个立方体的堆栈成功的影响。对于这些复杂的情况,我们的模型能够防止约75%的堆叠错误,即使是具有挑战性的多堆叠场景。因此,证明我们的方法能够解释,预测和防止执行失败,甚至可以扩展到复杂的场景,需要了解操作历史如何影响未来的操作。

英文摘要:

Robots working in real environments need to adapt to unexpected changes to avoid failures. This is an open and complex challenge that requires robots to timely predict and identify the causes of failures to prevent them. In this paper, we present a causal method that will enable robots to predict when errors are likely to occur and prevent them from happening by executing a corrective action. First, we propose a causal-based method to detect the cause-effect relationships between task executions and their consequences by learning a causal Bayesian network (BN). The obtained model is transferred from simulated data to real scenarios to demonstrate the robustness and generalization of the obtained models. Based on the causal BN, the robot can predict if and why the executed action will succeed or not in its current state. Then, we introduce a novel method that finds the closest state alternatives through a contrastive Breadth-First-Search if the current action was predicted to fail. We evaluate our approach for the problem of stacking cubes in two cases; a) single stacks (stacking one cube) and; b) multiple stacks (stacking three cubes). In the single-stack case, our method was able to reduce the error rate by 97%. We also show that our approach can scale to capture multiple actions in one model, allowing to measure timely shifted action effects, such as the impact of an imprecise stack of the first cube on the stacking success of the third cube. For these complex situations, our model was able to prevent around 75% of the stacking errors, even for the challenging multiple-stack scenario. Thus, demonstrating that our method is able to explain, predict, and prevent execution failures, which even scales to complex scenarios that require an understanding of how the action history impacts future actions.

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。

↑