Autonomous Robotic Stone Stacking with Online next Best Object Target Pose Planning

We show how to form stable compositions with these objects. We present a next best stacking pose searching method in a Stochastic Gradient Descent (SGD) manner, implemented using a physics engine. This approach is validated in an experimental setup using a robotic manipulator by constructing balancing vertical stacks without mortars and adhesives. We show the results of eleven consecutive trials to form such towers autonomously using four arbitrarily placed rocks.