Human-robot cross-training: Computational formulation, modeling and evaluation of a human team training strategy
Human-robot cross-training: Computational formulation, modeling and evaluation of a human team training strategy
复制标题
DOI：
10.1109/hri.2013.6483499
复制
发表时间：
2013-03
期刊：
影响因子：
--
通讯作者：
S. Nikolaidis;J. Shah
中科院分区：
文献类型：
--
作者：
S. Nikolaidis;J. Shah
我们设计并评估了人机交叉训练，这是一种广泛使用并经过验证的有效人类团队训练策略。交叉训练是一种交互式规划方法，其中人类和机器人迭代地切换角色以学习协作任务的共享计划。我们首先提出了一个计算公式的机器人的角色间的知识，并表明，它是定量可比的人的心理模型。基于这种编码，我们制定了人-机器人交叉训练，并在人类受试者实验（n = 36）中进行评估。我们将人机交叉训练与标准强化学习技术进行了比较，并表明交叉训练在定量团队绩效指标方面提供了统计学上的显着改善。此外，显着差异出现在感知机器人的性能和人类的信任。这些结果支持了这一假设，即有效和流畅的人机合作可能是最好的实现人类团队合作的有效做法建模。
We design and evaluate human-robot cross-training, a strategy widely used and validated for effective human team training. Cross-training is an interactive planning method in which a human and a robot iteratively switch roles to learn a shared plan for a collaborative task. We first present a computational formulation of the robot's interrole knowledge and show that it is quantitatively comparable to the human mental model. Based on this encoding, we formulate human-robot cross-training and evaluate it in human subject experiments (n = 36). We compare human-robot cross-training to standard reinforcement learning techniques, and show that cross-training provides statistically significant improvements in quantitative team performance measures. Additionally, significant differences emerge in the perceived robot performance and human trust. These results support the hypothesis that effective and fluent human-robot teaming may be best achieved by modeling effective practices for human teamwork.