We outline the design and construction of novel robotic arms using machine perception, convolutional neural networks, and symbolic AI for logical control and affordance indexing. We describe our robotic arms built with a humanlike mechanical configuration and aesthetic, with 28 degrees of freedom, touch sensors, and series elastic actuators. The arms were modeled in Roodle and Gazebo with URDF models, as well as Unity, and implemented motion control solutions for solving live games of Baccarat (the casino card game), rock paper scissors, handshaking, and drawing. This included live interactions with people, incorporating both social control of the hands and facial gestures, and physical inverse kinematics (IK) solving for grasping and manipulation tasks. The resulting framework is described as an integral part of the Sophia 2020 alpha platform, which is being used with ongoing research in the authors’ work with team AHAM, an ANA Avatar Xprize effort towards human-AI hybrid telepresence. The uses of the work extend across domains and include arts and social human-robot interaction, as well as targeting more
general co-bot applications. These results are available to test on the broadly released Hanson Robotics Sophia 2020 robot platform for users to try and extend.
David Hanson, Alishba Imran, Abhinandan Vellanki, Sanjeew Kanagaraj
A Neuro-Symbolic Humanlike Arm Controller for Sophia the Robot