Working Backwards: Learning to Place by Picking
This addresses the challenge of data collection for contact-constrained placement tasks in home robotics, offering an incremental improvement over existing demonstration methods.
The paper tackles the problem of autonomously collecting demonstrations for robotic object placement tasks by introducing placing via picking (PvP), which reverses the grasping process to generate data without human intervention. The method achieves higher success rates and data efficiency compared to kinesthetic teaching in scenarios like dishwasher loading and table setting.
We present placing via picking (PvP), a method to autonomously collect real-world demonstrations for a family of placing tasks in which objects must be manipulated to specific, contact-constrained locations. With PvP, we approach the collection of robotic object placement demonstrations by reversing the grasping process and exploiting the inherent symmetry of the pick and place problems. Specifically, we obtain placing demonstrations from a set of grasp sequences of objects initially located at their target placement locations. Our system can collect hundreds of demonstrations in contact-constrained environments without human intervention using two modules: compliant control for grasping and tactile regrasping. We train a policy directly from visual observations through behavioural cloning, using the autonomously-collected demonstrations. By doing so, the policy can generalize to object placement scenarios outside of the training environment without privileged information (e.g., placing a plate picked up from a table). We validate our approach in home robot scenarios that include dishwasher loading and table setting. Our approach yields robotic placing policies that outperform policies trained with kinesthetic teaching, both in terms of success rate and data efficiency, while requiring no human supervision.