# Generalize by Touching: Tactile Ensemble Skill Transfer for Robotic Furniture Assembly

arXiv: https://arxiv.org/abs/2404.17684 · HTML: https://mlsanity.com/paper/2404.17684/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 26 Apr 2024.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 27 of 27)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [FeUdal Networks for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1703.01161/) (2017)
- [Accelerating Reinforcement Learning with Learned Skill Priors](https://mlsanity.com/paper/2010.11944/) (2020)
- [MimicPlay: Long-Horizon Imitation Learning by Watching Human Play](https://mlsanity.com/paper/2302.12422/) (2023)
- [Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks](https://mlsanity.com/paper/1810.10191/) (2018)
- [FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation](https://mlsanity.com/paper/2305.12821/) (2023)
- [XSkill: Cross Embodiment Skill Discovery](https://mlsanity.com/paper/2307.09955/) (2023)
- [IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks](https://mlsanity.com/paper/1911.07246/) (2019)
- [Skill-based Model-based Reinforcement Learning](https://mlsanity.com/paper/2207.07560/) (2022)
- [Tactile-RL for Insertion: Generalization to Objects of Unknown Geometry](https://mlsanity.com/paper/2104.01167/) (2021)
- [Visuo-Tactile Transformers for Manipulation](https://mlsanity.com/paper/2210.00121/) (2022)
- [Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization](https://mlsanity.com/paper/2111.07999/) (2021)
- [Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2204.13060/) (2022)
- [Skill-based Meta-Reinforcement Learning](https://mlsanity.com/paper/2204.11828/) (2022)
- [Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks](https://mlsanity.com/paper/2312.06876/) (2023)
- [Robotic Tactile Perception of Object Properties: A Review](https://mlsanity.com/paper/1711.03810/) (2017)
- [Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning](https://mlsanity.com/paper/2310.03718/) (2023)
- [9DTact: A Compact Vision-Based Tactile Sensor for Accurate 3D Shape Reconstruction and Generalizable 6D Force Estimation](https://mlsanity.com/paper/2308.14277/) (2023)
- [Learning from Sparse Offline Datasets via Conservative Density Estimation](https://mlsanity.com/paper/2401.08819/) (2024)
- [Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clustering](https://mlsanity.com/paper/1605.05359/) (2016)
- [Bayesian and Neural Inference on LSTM-based Object Recognition from Tactile and Kinesthetic Information](https://mlsanity.com/paper/2306.06423/) (2023)

## Built on by (most cited first, 7 of 7)

- [EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data](https://mlsanity.com/paper/2406.17768/) (2024)
- [Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications](https://mlsanity.com/paper/2410.20357/) (2024)
- [Tac-DINO: Learning Vision-Tactile Features with Patch Alignment](https://mlsanity.com/paper/2606.12069/) (2026)
- [FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model](https://mlsanity.com/paper/2607.01212/) (2026)
- [Modality Selection and Skill Segmentation via Cross-Modality Attention](https://mlsanity.com/paper/2504.14573/) (2025)
- [Query-Centric Diffusion Policy for Generalizable Robotic Assembly](https://mlsanity.com/paper/2509.18686/) (2025)
- [Simulation-based Learning of Electrical Cabinet Assembly Using Robot Skills](https://mlsanity.com/paper/2602.14561/) (2026)

## Abstract (arXiv)

Furniture assembly remains an unsolved problem in robotic manipulation due to its long task horizon and nongeneralizable operations plan. This paper presents the Tactile Ensemble Skill Transfer (TEST) framework, a pioneering offline reinforcement learning (RL) approach that incorporates tactile feedback in the control loop. TEST's core design is to learn a skill transition model for high-level planning, along with a set of adaptive intra-skill goal-reaching policies. Such design aims to solve the robotic furniture assembly problem in a more generalizable way, facilitating seamless chaining of skills for this long-horizon task. We first sample demonstration from a set of heuristic policies and trajectories consisting of a set of randomized sub-skill segments, enabling the acquisition of rich robot trajectories that capture skill stages, robot states, visual indicators, and crucially, tactile signals. Leveraging these trajectories, our offline RL method discerns skill termination conditions and coordinates skill transitions. Our evaluations highlight the proficiency of TEST on the in-distribution furniture assemblies, its adaptability to unseen furniture configurations, and its robustness against visual disturbances. Ablation studies further accentuate the pivotal role of two algorithmic components: the skill transition model and tactile ensemble policies. Results indicate that TEST can achieve a success rate of 90% and is over 4 times more efficient than the heuristic policy in both in-distribution and generalization settings, suggesting a scalable skill transfer approach for contact-rich manipulation.