Compact Multi-Object Placement Using Adjacency-Aware Reinforcement Learning
On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation
Abstract (arXiv)
Close and precise placement of irregularly shaped objects requires a skilled robotic system. The manipulation of objects that have sensitive top surfaces and a fixed set of neighbors is particularly challenging. To avoid damaging the surface, the robot has to grasp them from the side, and during placement, it has to maintain the spatial relations with adjacent objects, while considering the physical gripper extent. In this work, we propose a framework to learn an agent based on reinforcement learning that generates end-effector motions for placing objects as closely as possible to one another. During the placement, our agent considers the spatial constraints with neighbors defined in a given layout of the objects while avoiding collisions. Our approach learns to place compact object assemblies without the need for predefined spacing between objects, as required by traditional methods. We thoroughly evaluated our approach using a two-finger gripper mounted on a robotic arm with six degrees of freedom. The results demonstrate that our agent significantly outperforms two baseline approaches in object assembly compactness, thereby reducing the space required to position the objects while adhering to specified spatial constraints.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 24 references that are in the map. First posted on arXiv 16 Apr 2024.
Builds on
10 of 24 references.
References · 10
- 2016OpenAI Gymcited by 1,736
- 2020Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Criticscited by 165
- 2021Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapescited by 71
- 2019Towards Practical Multi-Object Manipulation using Relational Reinforcement Learningcited by 55
- 2021Efficient and Interpretable Robot Manipulation with Graph Neural Networkscited by 22
- 2020Self-supervised Learning for Precise Pick-and-place without Object Modelcited by 21
- 2021Active Extrinsic Contact Sensing: Application to General Peg-in-Hole Insertioncited by 19
- 2022Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learningcited by 6
- 2023Pick2Place: Task-aware 6DoF Grasp Estimation via Object-Centric Perspective Affordancecited by 5
- 2023A Grasp Pose is All You Need: Learning Multi-fingered Grasping with Deep Reinforcement Learning from Vision and Touchcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025AnyPlace: Learning Generalized Object Placement for Robot Manipulation
- 2023Working Backwards: Learning to Place by Picking
- 2025Fabrica: Dual-Arm Assembly of General Multi-Part Objects via Integrated Planning and Learning
- 2026Shape Formation for the Cooperative Transportation of Arbitrary Objects Using Multi-Agent Reinforcement Learning
- 2026Non-Prehensile Multi-Object Placement with Mobile Robots via Diffusion-Based Trajectory Planning ↗
- 2025FLEX: A Framework for Learning Robot-Agnostic Force-based Skills Involving Sustained Contact Object Manipulation
- 2025GOPLA: Generalizable Object Placement Learning via Synthetic Augmentation of Human Arrangement
- 2024HACMan++: Spatially-Grounded Motion Primitives for Manipulation