Dexterous and sensorized soft robotic hands

Principal Investigators:

Oliver Brock

Team members:

Vincent Wall (doctoral researcher)
Adrian Sieler (doctoral researcher)

Building anthropomorphic soft robotic hands with human-like manipulation abilities

Research Unit 3, SCIoI Project 17

Inspired by human grasping and manipulation capabilities, we will build anthropomorphic soft robotic hands that also act as a sensor to enable robust interactions with the environment.
Since they are made of soft materials, their morphology adapts to the environment which increases robustness and safety for human-robot interaction.
Our hands will exhibit a high degree of dexterity. To this end, we will construct a new type of opposable thumb based on novel pneumatic actuators which also allows for abduction of the fingers. These advances will enable our hands to perform a large variety of manipulation tasks.
To observe and react to interactions with the object and the environment, we will equip the hands with sensors. The inherent compliance prevents the use of traditional sensors technologies. We will therefore develop new sensor technologies to sensorize highly compliant actuators with many degrees of freedom. This will include fabric based sensors to obtain tactile information, soft strain sensors for proprioception, and acoustic sensors that detect contact events.
To further increase the robustness of soft hands, we will devise control methods that reduce perceptual, model, and motion uncertainty through haptic feedback. We will also develop control strategies that actively extract haptic information from the environment, for example sliding a finger over a surface to determine its friction properties.


Related Publications

Zöller, G., Wall, V., & Brock, O. (2020). Active Acoustic Contact Sensing for Soft Pneumatic Actuators. 2020 IEEE International Conference on Robotics and Automation (ICRA), 7966–7972.
Wall, V., & Brock, O. (2019). Multi-Task Sensorization of Soft Actuators Using Prior Knowledge. 2019 International Conference on Robotics and Automation (ICRA), 9416–9421.

User registration

You don't have permission to register

Reset Password