Department of Physics, System Engineering and Signal Theory, University of Alicante, San Vicente del Raspeig, Alicante 03690, Spain.
Sensors (Basel). 2011;11(10):9839-62. doi: 10.3390/s111009839. Epub 2011 Oct 20.
Autonomous manipulation in semi-structured environments where human operators can interact is an increasingly common task in robotic applications. This paper describes an intelligent multi-sensorial approach that solves this issue by providing a multi-robotic platform with a high degree of autonomy and the capability to perform complex tasks. The proposed sensorial system is composed of a hybrid visual servo control to efficiently guide the robot towards the object to be manipulated, an inertial motion capture system and an indoor localization system to avoid possible collisions between human operators and robots working in the same workspace, and a tactile sensor algorithm to correctly manipulate the object. The proposed controller employs the whole multi-sensorial system and combines the measurements of each one of the used sensors during two different phases considered in the robot task: a first phase where the robot approaches the object to be grasped, and a second phase of manipulation of the object. In both phases, the unexpected presence of humans is taken into account. This paper also presents the successful results obtained in several experimental setups which verify the validity of the proposed approach.
自主操作在半结构化环境中，人类操作员可以进行交互，这是机器人应用中越来越常见的任务。本文描述了一种智能多传感方法，通过为具有高度自主性和执行复杂任务能力的多机器人平台提供解决方案来解决这个问题。所提出的传感系统由混合视觉伺服控制组成，以有效地引导机器人朝向要操作的物体，惯性运动捕捉系统和室内定位系统，以避免在同一工作空间中工作的人类操作员和机器人之间可能发生碰撞，以及用于正确操作物体的触觉传感器算法。所提出的控制器采用整个多传感系统，并在机器人任务考虑的两个不同阶段中结合使用的每个传感器的测量值：机器人接近要抓取的物体的第一阶段，以及物体的操作的第二阶段。在这两个阶段中，都会考虑到人类的意外存在。本文还介绍了在几个实验设置中获得的成功结果，这些结果验证了所提出方法的有效性。
