Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes
This addresses robotic manipulation challenges for diverse shapes, though it appears incremental in combining existing RL techniques.
The paper tackles robotic stacking of objects with complex geometry using a reinforcement learning approach with vision-based interactive policy distillation and simulation-to-reality transfer, achieving efficient handling of multiple object combinations in real-world experiments.
We study the problem of robotic stacking with objects of complex geometry. We propose a challenging and diverse set of such objects that was carefully designed to require strategies beyond a simple "pick-and-place" solution. Our method is a reinforcement learning (RL) approach combined with vision-based interactive policy distillation and simulation-to-reality transfer. Our learned policies can efficiently handle multiple object combinations in the real world and exhibit a large variety of stacking skills. In a large experimental study, we investigate what choices matter for learning such general vision-based agents in simulation, and what affects optimal transfer to the real robot. We then leverage data collected by such policies and improve upon them with offline RL. A video and a blog post of our work are provided as supplementary material.