Online Explanation Generation for Human-Robot Teaming
Online Explanation Generation for Human-Robot Teaming
复制标题
人机协作的在线解释生成
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Yu Zhang
中科院分区：
文献类型：
--
作者：
Mehrdad Zakershahrak;Ze Gong;Yu Zhang
随着人工智能成为我们生活中不可或缺的一部分，开发体现在人工智能或机器人代理的决策过程中的可解释人工智能变得势在必行。对于机器人队友来说，能够产生解释来证明自己的行为是可解释机构的关键要求之一。之前关于解释生成的工作一直专注于支持机器人决策或行为背后的原理。然而，这些方法没有考虑到理解所收到的解释的心理需求。换句话说，无论提供多少信息，人类队友都应该理解解释。在这项工作中，我们认为解释，特别是那些复杂的解释，应该在执行过程中以在线的方式进行，这有助于传播要解释的信息，从而减少人类在高认知要求的任务中的脑力劳动。然而，这里的一个挑战是，解释的不同部分可能相互依赖，在生成在线解释时必须考虑到这一点。为此，给出了满足不同“在线”性质的三种变体的在线解释生成的一般公式。新的解释生成方法基于我们先前工作中介绍的模型协调设置。我们使用NASA任务负载指数(TLX)在模拟的漫游车域中对我们的方法进行了评估，并对两个标准IPC域中的10个不同问题进行了综合评估。结果强烈表明，我们的方法产生的解释被认为是认知要求较低的，比基线更受欢迎，并且在计算上是有效的。
As AI becomes an integral part of our lives, the development of explainable AI, embodied in the decision-making process of an AI or robotic agent, becomes imperative. For a robotic teammate, the ability to generate explanations to justify its behavior is one of the key requirements of explainable agency. Prior work on explanation generation has been focused on supporting the rationale behind the robot's decision or behavior. These approaches, however, fail to consider the mental demand for understanding the received explanation. In other words, the human teammate is expected to understand an explanation no matter how much information is presented. In this work, we argue that explanations, especially those of a complex nature, should be made in an online fashion during the execution, which helps spread out the information to be explained and thus reduce the mental workload of humans in highly cognitive demanding tasks. However, a challenge here is that the different parts of an explanation may be dependent on each other, which must be taken into account when generating online explanations. To this end, a general formulation of online explanation generation is presented with three variations satisfying different "online" properties. The new explanation generation methods are based on a model reconciliation setting introduced in our prior work. We evaluated our methods both with human subjects in a simulated rover domain, using NASA Task Load Index (TLX), and synthetically with ten different problems across two standard IPC domains. Results strongly suggest that our methods generate explanations that are perceived as less cognitively demanding and much preferred over the baselines and are computationally efficient.
你到底想从我这里得到什么？
DOI：
10.1609/aaai.v34i03.5630
发表时间：
2020
期刊：
Proceedings of the AAAI Conference on Artificial Intelligence
影响因子：
--
作者：
Gong, Ze;Zhang, Yu
通讯作者：
Zhang, Yu
影响因子：
2.4
作者：
Tsang, PS;Velaquez, VL
通讯作者：
Velaquez, VL