There are some tasks that transmitted robots — the stiff and metallic kind — simply arent cut out for. Soft-bodied robots on the other hand may be able to interact with nation more safely or slip into firm spaces with ease. But for robots to reliably complete their programmed duties they need to know the wherealmosts of all their body parts. Thats a tall task for a soft robot that can deform in a virtually infinite number of ways.
MIT investigationers have developed an algorithm to help engineers design soft robots that collate more advantageous information almost their surroundings. The deep-learning algorithm suggests an optimized placement of sensors within the robots body allowing it to better interact with its environment and complete assigned tasks. The advance is a step toward the automation of robot design. ’The method not only learns a given task but also how to best design the robot to explain that task’ says Alexander Amini. ’Sensor placement is a very hard problem to explain. So having this solution is extremely exciting.’
The investigation will be presented during Aprils IEEE International Conference on Soft Robotics and will be published in the journal IEEE Robotics and Automation Letters. Co-lead authors are Amini and Andrew Spielberg both PhD students in MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). Other co-authors include MIT PhD student Lillian Chin and professors Wojciech Matusik and Daniela Rus.