Soft robots present an avenue toward unprecedented societal acceptance, utility in populated environments, and direct interaction with humans. However, the compliance that makes them attractive also makes soft robots difficult to control. We present two low-cost approaches to control the motion of soft actuators in applications common in human-interaction tasks. First, we present a passive impedance approach, which employs restriction to pneumatic channels to regulate the inflation/deflation rate of a pneumatic actuator and eliminate the overshoot/oscillation seen in many underdamped silicone-based soft actuators. Second, we present a visual servoing feedback control approach. We present an elastomeric pneumatic finger as an example system on which both methods are evaluated and compared to an uncontrolled underdamped actuator. We perturb the actuator and demonstrate its ability to increase distal curvature around the obstacle and maintain the desired end position. In this approach, we use the continuum deformation characteristic of soft actuators as an advantage for control rather than a problem to be minimized. With their low cost and complexity, these techniques present great opportunity for soft robots to improve human–robot interaction.

中文翻译：

---

软促动器的位置控制，迈向固有安全相互作用的下一步

软机器人为实现前所未有的社会接受度，在人口稠密的环境中使用以及与人直接互动提供了一种途径。但是，使它们具有吸引力的顺从性也使软机器人难以控制。在人机交互任务中常见的应用中，我们提出了两种低成本的方法来控制软执行器的运动。首先，我们提出一种无源阻抗方法，该方法采用了对气动通道的限制来调节气动执行器的充气/放气速率，并消除了许多欠阻尼的基于硅的软执行器中出现的过冲/振荡。其次，我们提出了一种视觉伺服反馈控制方法。我们以弹性气动手指为例，对两种方法都进行了评估，并将其与不受控制的欠阻尼执行器进行了比较。我们扰动执行器，并证明其有能力增加障碍物周围的远侧曲率并保持所需的最终位置。在这种方法中，我们将软执行器的连续变形特性用作控制的优势，而不是将其最小化的问题。这些技术具有低成本和复杂性的特点，为软机器人改善人机交互提供了巨大的机会。