Sensors are an important part of any robot control system. While soft pneumatic actuators can't use most sensors from rigid robotics, they exhibit properties that make new sensing modalities possible. The air inside the air chamber of a pneumatic actuator conducts sound and this sound carries information about where it originated and which path it traveled.
This thesis develops and characterizes a contact sensor by playing back a known sound and analyzing how it changes when a PneuFlex actuator touches an object in different ways.
A small microphone and speaker are embedded into the airchamber, a sound with a wide spectrum is played back, recorded and run through a classifier. The spatial resolution of this sensor is very high and can distinguish between areas of contact 3mm in size on a 85mm long actuator.
The developed sensor is able to sense contact at six different locations with high classification rate. Both a loud environment and changing the touched test objects have a very small influence on active contact location sensing performance. The sensor can be trained to work on human and robot operators and the accuracy of the sensor can reach 3.7 mm. Finally, it is presented in an experiment showing a live sensor on a robot.
Gabriel Zöller and Vincent Wall and Oliver Brock. Acoustic Sensing for Soft Pneumatic Actuators. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6986-6991, 2018.