Less Is More: Mixed-Initiative Model-Predictive Control With Human Inputs
Less Is More: Mixed-Initiative Model-Predictive Control With Human Inputs
复制标题
DOI：
10.1109/tro.2013.2248551
复制
发表时间：
2013-06-01
影响因子：
7.8
通讯作者：
Egerstedt, Magnus B.
中科院分区：
文献类型：
--
作者：
Chipalkatty, Rahul;Droge, Greg;Egerstedt, Magnus B.
本文提出了一种将人类输入注入人类与机器人之间的混合主动交互中的新方法。该方法基于模型预测控制（MPC）公式，不可避免地涉及预测系统（机器人动力学以及人类输入）的未来。由于人类与机器人交互，这些预测变得复杂，导致预测方法本身对未来的人类输入产生影响。我们研究和开发不同的预测方案，包括固定和可变水平 MPC 以及不同阶数的人类输入估计器。通过一项受搜索和救援启发的人类操作员研究，我们得出的结论是，最简单的预测方法胜过更复杂的预测方法，即在这种特殊情况下，少即是多。
This paper presents a new method for injecting human inputs into mixed-initiative interactions between humans and robots. The method is based on a model-predictive control (MPC) formulation, which inevitably involves predicting the system (robot dynamics as well as human input) into the future. These predictions are complicated by the fact that the human is interacting with the robot, causing the prediction method itself to have an effect on future human inputs. We investigate and develop different prediction schemes, including fixed and variable horizon MPCs and human input estimators of different orders. Through a search-and-rescue-inspired human operator study, we arrive at the conclusion that the simplest prediction methods outperform the more complex ones, i.e., in this particular case, less is indeed more.