Swingbot: Learning Physical Features from In-Hand Tactile Exploration for Dynamic Swing-Upmanipulation

Non-Exclusively Licensed

Physical features of an object from tactile robotic exploration, including by manipulation of the object with an effector having a tactile sensor that provides measurements representative of physical interaction of the effector and the object. This exploration may include performing a predetermined set of manipulations of the object using the effector. Measurements made during the manipulations are used to form a data representation of physical characteristics of the object, and this data representation is used to control further motion of the object.

Researchers

Edward Adelson / Chen Wang / Shaoxiong Wang / Filipe Fernandes Veiga / Branden Romero

Departments: Department of Brain and Cognitive Sciences, Computer Science & Artificial Intelligence Lab
Technology Areas: Artificial Intelligence (AI) and Machine Learning (ML) / Industrial Engineering & Automation: Autonomous Systems, Robotics / Sensing & Imaging: Optical Sensing
Impact Areas: Connected World

  • learning physical features from tactile robotic exploration
    United States of America | Published application

License this technology

Interested in this technology? Connect with our experienced licensing team to initiate the process.

Sign up for technology updates

Sign up now to receive the latest updates on cutting-edge technologies and innovations.

More Technologies