Guest Presenters from Edward Waters College and Stanford University: Devin Hunter | Dr. Fabio Stroppa | Dr. Allison Okamura
Guest Faculty Mentor: Dr. Christian Bowers | Edward Waters College | Department of Mathematics and Sciences
The robots of today have grown to be of much more significant use than their predecessors. Robots are now being used in industries outside of the factory setting which can be seen primarily in the medical, transportation, and social fields. With robots taking on all of these new roles within our society, the establishment of robust human-robot collaboration is crucial in order for robots to be able to successfully complete desired tasks without becoming a hinderance to nearby humans. We explored this concept by implementing a shared-autonomy algorithm named MBSA (Motion Based Smart Assistance) to a soft robot simulation and testing out its performance against an object manipulation task. MBSA works such that it takes human user input and measures the distance to a desired target, such as a block, from the robot’s end-effector and applies a force in the direction of the target to the robot if it’s not moving towards the target. The soft robot that we modeled in the simulation is a robot that was being designed by other members within the CHARM lab termed the vine robot. This soft robot was capable of stretching and shrinking itself in size, moving around in a bendy, ‘snake-like’ manner, and had a gripper at the end of it that acted as an end-effector. We used Unity as the 3D-environment software to develop our simulation due to Unity’s reliable physics engine and its powerful inverse kinematics toolbox. In conclusion, MBSA was able to successfully establish shared-autonomy within the vine robot albeit with some issues regarding obstacle avoidance. However, this algorithm shows great promise for future work to be done within this subsection of human-robot interactions.