15 identically-shaped robotic fingertips are benchmarked by a fully automated toolchange system, covering eight different materials and six broadly-ranging sensing mechanisms.

We sensorize the surface of a 3D human-sized hand using a single material, and demonstrate its ability to monitor multimodal stimuli.

Mimicking the structure of the human skin by combining surface level thermoreceptors with deeper mechanoreceptors. Tactile stimuli are identified using a feedforward neural network.

Comparing recalibration methods for a sensorised skin which has damaged and healed in multiple locations, affecting the response of the sensor channels. Transfer learning is used to recover the tactile sensitivity as quickly as possible.

Development, characterisation, and applications of a healable gelatin-based sensor for soft robotics.