Various robotic hands, gloves, and grippers have been developed for manufacturing, prosthetics, and rehabilitation. However, the use of rigid links and joints presents challenges in control and safe interactions with humans. The emerging field of soft robotics seeks to create machines that are soft, compliant, and capable of withstanding damage, wear and high stress. This dissertation is focused on advancing soft actuators, soft sensors, and perception for ultimately realizing proprioceptive grasping with soft robotic hands.In this work, several types of soft pneumatic actuators (SPAs) have been tested, fabricated, and tested, including one embedded with 3D-printed conductive polylactic acid (CPLA) layer capable of stiffness tuning and shape modulation. A gripper made of two soft actuators has been prototyped to demonstrate grasping of objects of different sizes and shapes, with desired posture-holding capabilities. Carbon nanotube (CNT)-based flexible sensor arrays have been designed, fabricated, and integrated to SPAs to provide distributed strain measurements. The presented approach allows customized design of stretchable sensor arrays with varied size and shape. Simulation and experimentation have been performed in order to analyze the soft actuator deformation during bending, and to confirm the capability of the integrated sensor array for capturing the actuator deformation. 3D printing of touch and pressure sensors has been further investigated for potential use in robotic hands. In particular, a novel process has been introduced for producing soft conductors and pressure sensors, involving first 3D-printing microchannels in soft substrates and then filling the channel with liquid metal. With a PolyJet printer, functional straight microchannels have been fabricated with sizes down to 150 x 150 micrometers in the cross-section area. In addition, spiral-shaped pressure sensors have been developed with a cross-section size of 350 x 350 micrometers and overall thickness of 1.5 mm (50A and 70A Shore Hardness). Although the sensors require a relatively large pressure threshold to operate, they have shown the ability to withstand high pressures up to 1 MPa and thus have potential to be used in industrial applications among others. Finally, preliminary computational exploration of intelligent grasping has been performed. In particular, the classification of soft grasped objects has been examined through a neuroevolution process for artificial brains. Simulation with SOFA (Simulation Open Framework Architecture) has been conducted to produce the emulated contact force measurements, which have been used to train artificial neural networks, including Markov Brains from the Modular Agent-Based Evolver (MABE) platform, to properly classify the shape and stiffness of the grasped objects.
Read
