PATI: a projection-based augmented table-top interface for robot programming
summary
A projection-based tabletop interface called PATI lets users specify pick-and-place tasks by drawing shapes and arrows with common gestures and shape tools and uses a top-mount projector and 3D camera to ground those annotations to real objects and a UR5 manipulator. A lab study with 17 participants shows programming time drops by 66% faster than the UR5 built-in method, with shorter training, fewer questions and lower NASA TLX scores; the prototype successfully executes the specified pick-and-place sequences and is available as open source.
AI-written summary · about
chapters (4)
- 0:00Start
- 0:11END-USER INTERFACE FOR ROBOT PROGRAMMING
- 0:47THE GOAL: RE-PROGRAM ROBOTS FOR CUSTOM TASKS
- 10:43TOWARDS END-USER ROBOT PROGRAMMING
related talks
09mSituated Live Programming for Human-Robot Collaboration
18mRobotics: why now?
20mRobotic Assembly of Haptic Proxy Objects for Tangible Interaction and Virtual Reality
18mRobiot: A Design Tool for Actuating Everyday Objects with Automatically Generated 3D Printable ...
14mTowards Unobtrusive Physical AI: Augmenting Everyday Objects with Intelligence and Robotic Moveme...
18mFireside Chat pt.1
14mHERMITS: Dynamically Reconfiguring the Interactivity of Self-propelled TUIs with Mechanical ...
33mThe New Generation of Robots
