Problem
Research questions and friction points this paper is trying to address.
Robotics
Autonomous Object Placement
Domestic Environment
Working Backwards: Learning to Place by Picking
🤖 AI Summary
To address the challenge of unsupervised, high-precision object placement in home environments (e.g., dishwasher loading, table setting), this paper proposes “Placement via Pickup” (PvP). The method introduces the novel *inverse placement* paradigm: starting from a desired target pose, it leverages geometric and contact symmetries inherent in grasping to autonomously generate physically feasible placement demonstrations—without human demonstrations, privileged information, or manual intervention. Integrating compliant control, tactile-driven regrasping, and visuomotor policy learning, PvP autonomously collects hundreds of high-quality placement trajectories in real domestic settings. Experiments demonstrate that PvP significantly outperforms conventional imitation learning in both success rate and data efficiency, while exhibiting strong generalization across diverse objects, poses, and household scenes.
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
PvP Method
Self-learning Placement
Visual-based Strategy
🔎 Similar Papers
No similar papers found.
