mlsanityData to 7 Oct 2026

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

arXiv 2404.17684 ↗First posted 26 Apr 2024cs.RO cs.LGcited by 6

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

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.

Key facts. Cited by 6 papers in the map (data through 7 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.

Builds on

27 of 39 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023XSkill: Cross Embodiment Skill Discovery19 Jul
  2. 2023FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation22 May
  3. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Play24 Feb

Other references · 24

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  3. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  4. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 882
  5. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  6. 2019Solving Rubik's Cube with a Robot Handcited by 699
  7. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  8. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 328
  9. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 220
  10. 2018Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Taskscited by 150
  11. 2019IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Taskscited by 68
  12. 2022Skill-based Model-based Reinforcement Learningcited by 50
12 more
  1. 2021Tactile-RL for Insertion: Generalization to Objects of Unknown Geometrycited by 45
  2. 2021Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularizationcited by 44
  3. 2022Visuo-Tactile Transformers for Manipulationcited by 43
  4. 2022Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learningcited by 38
  5. 2022Skill-based Meta-Reinforcement Learningcited by 36
  6. 2023Interactive Planning Using Large Language Models for Partially Observable Robotics Taskscited by 27
  7. 2017Robotic Tactile Perception of Object Properties: A Reviewcited by 24
  8. 2023Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learningcited by 17
  9. 20239DTact: A Compact Vision-Based Tactile Sensor for Accurate 3D Shape Reconstruction and Generalizable 6D Force Estimationcited by 16
  10. 2024Learning from Sparse Offline Datasets via Conservative Density Estimationcited by 9
  11. 2016Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clusteringcited by 6
  12. 2023Bayesian and Neural Inference on LSTM-based Object Recognition from Tactile and Kinesthetic Informationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 2.

6 papers.

  1. 2024EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Datacited by 13
  2. 2024Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identificationscited by 10
  3. 2026Tac-DINO: Learning Vision-Tactile Features with Patch Alignmentcited by 1
  4. 2026FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Modelcited by 1
  5. 2025Modality Selection and Skill Segmentation via Cross-Modality Attentioncited by 0
  6. 2025Query-Centric Diffusion Policy for Generalizable Robotic Assemblycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2020Supervised Learning and Reinforcement Learning of Feedback Models for Reactive Behaviors: Tactile Feedback Testbed
  2. 2025VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning
  3. 2023Offline Skill Generalization via Task and Motion Planning
  4. 2025RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environments
  5. 2026From Reach to Insert: Tactile-Augmented Precision Assembly under Sub-Millimeter Tolerances
  6. 2026OpenViTac: Learning and Benchmarking Visuo-Tactile Policies in a Unified Sim-and-Real Framework ↗
  7. 2025GrOMP: Grasped Object Manifold Projection for Multimodal Imitation Learning of Manipulation
  8. 2024TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulation