Visuomotor Mechanical Search: Learning to Retrieve Target Objects in Clutter

TL;DR

This paper introduces a novel deep reinforcement learning method for robotic object retrieval in cluttered environments, combining teacher guidance, privileged critic information, and mid-level representations to improve learning efficiency and uncovering success.

Contribution

The work presents a new RL approach that enhances sample efficiency and effectiveness in unoccluding objects, outperforming baselines and enabling better grasping in cluttered scenes.

Findings

Faster training convergence compared to baselines

Improved uncovering efficiency of occluded objects

Enhanced graspability of target objects after policy execution

Abstract

When searching for objects in cluttered environments, it is often necessary to perform complex interactions in order to move occluding objects out of the way and fully reveal the object of interest and make it graspable. Due to the complexity of the physics involved and the lack of accurate models of the clutter, planning and controlling precise predefined interactions with accurate outcome is extremely hard, when not impossible. In problems where accurate (forward) models are lacking, Deep Reinforcement Learning (RL) has shown to be a viable solution to map observations (e.g. images) to good interactions in the form of close-loop visuomotor policies. However, Deep RL is sample inefficient and fails when applied directly to the problem of unoccluding objects based on images. In this work we present a novel Deep RL procedure that combines i) teacher-aided exploration, ii) a critic with privileged information, and iii) mid-level representations, resulting in sample efficient and effective learning for the problem of uncovering a target object occluded by a heap of unknown objects. Our experiments show that our approach trains faster and converges to more efficient uncovering solutions than baselines and ablations, and that our uncovering policies lead to an average improvement in the graspability of the target object, facilitating downstream retrieval applications.