# Learning-based Cooperative Robotic Paper Wrapping: A Unified Control Policy with Residual Force Control

arXiv: https://arxiv.org/abs/2511.03181 · HTML: https://mlsanity.com/paper/2511.03181/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Builds on (most cited first, 23 of 23)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators](https://mlsanity.com/paper/2309.13037/) (2023)
- [IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data](https://mlsanity.com/paper/1911.05321/) (2019)
- [CLIP model is an Efficient Continual Learner](https://mlsanity.com/paper/2210.03114/) (2022)
- [Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration](https://mlsanity.com/paper/1807.03480/) (2018)
- [VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation](https://mlsanity.com/paper/2503.07135/) (2025)
- [KITE: Keypoint-Conditioned Policies for Semantic Manipulation](https://mlsanity.com/paper/2306.16605/) (2023)
- [Large Language Models for Multi-Robot Systems: A Survey](https://mlsanity.com/paper/2502.03814/) (2025)
- [UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Folding](https://mlsanity.com/paper/2311.01267/) (2023)
- [Learning Variable Compliance Control From a Few Demonstrations for Bimanual Robot with Haptic Feedback Teleoperation System](https://mlsanity.com/paper/2406.14990/) (2024)
- [Learning Language-Conditioned Deformable Object Manipulation with Graph Dynamics](https://mlsanity.com/paper/2303.01310/) (2023)
- [Differentiable Particles for General-Purpose Deformable Object Manipulation](https://mlsanity.com/paper/2405.01044/) (2024)
- [Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attention](https://mlsanity.com/paper/2301.03003/) (2023)
- [3D Deformable Object Manipulation using Fast Online Gaussian Process Regression](https://mlsanity.com/paper/1709.07218/) (2017)
- [Category-Association Based Similarity Matching for Novel Object Pick-and-Place Task](https://mlsanity.com/paper/2201.08177/) (2022)
- [Focused Adaptation of Dynamics Models for Deformable Object Manipulation](https://mlsanity.com/paper/2209.14261/) (2022)
- [Learning Neural Force Manifolds for Sim2Real Robotic Symmetrical Paper Folding](https://mlsanity.com/paper/2301.01968/) (2023)
- [Robotic Paper Wrapping by Learning Force Control](https://mlsanity.com/paper/2503.15685/) (2025)

## Abstract (arXiv)

Human-robot cooperation is essential in environments such as warehouses and retail stores, where workers frequently handle deformable objects like paper, bags, and fabrics. Coordinating robotic actions with human assistance remains difficult due to the unpredictable dynamics of deformable materials and the need for adaptive force control. To explore this challenge, we focus on the task of gift wrapping, which exemplifies a long-horizon manipulation problem involving precise folding, controlled creasing, and secure fixation of paper. Success is achieved when the robot completes the sequence to produce a neatly wrapped package with clean folds and no tears. We propose a learning-based framework that integrates a high-level task planner powered by a large language model (LLM) with a low-level hybrid imitation learning (IL) and reinforcement learning (RL) policy. At its core is a Sub-task Aware Robotic Transformer (START) that learns a unified policy from human demonstrations. The key novelty lies in capturing long-range temporal dependencies across the full wrapping sequence within a single model. Unlike vanilla Action Chunking with Transformer (ACT), typically applied to short tasks, our method introduces sub-task IDs that provide explicit temporal grounding. This enables robust performance across the entire wrapping process and supports flexible execution, as the policy learns sub-goals rather than merely replicating motion sequences. Our framework achieves a 97% success rate on real-world wrapping tasks. We show that the unified transformer-based policy reduces the need for specialized models, allows controlled human supervision, and effectively bridges high-level intent with the fine-grained force control required for deformable object manipulation.