mlsanityData to 7 Oct 2026

CoRMA: Contrastive RMA for Contact-Rich Meta-Adaptation

arXiv 2605.22082 ↗First posted 21 May 2026cs.RO cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

We present CoRMA(Contrastive Robotic Motor Adaptation), a context-based meta-adaptation framework that modifies RMA for force-dominant assembly. CoRMA replaces raw simulator-parameter adaptation with a compact 6D simulator-only semantic contact context describing contact onset, lateral engagement, guided transition, contact direction, and jamming. A deployable causal Transformer adapter infers this context online from force, proprioceptive, and action histories using semantic regression and a force-regime contrastive objective. At deployment, oracle context is removed and replaced by the inferred context, enabling within-episode adaptation without demonstrations, privileged inputs, or gradient updates. We evaluate CoRMA on PegInsert, GearMesh, and NutThread in Isaac Lab / Isaac Sim 5.0 and on a real Marvin arm. Compared with FORGE baselines that achieve high simulation success but degrade substantially on hardware, CoRMA retains higher verified real success under controlled target-pose noise. These results support semantic contact inference as a reusable adaptation interface within a related assembly task family, while broader unseen-task generalization and Real2Sim calibration remain future work.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 21 May 2026.

Builds on

19 of 27 references.

References · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2016Generative Adversarial Imitation Learningcited by 1,576
  4. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  5. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  6. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  7. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  8. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  9. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 312
  10. 2019Stabilizing Transformers for Reinforcement Learningcited by 262
  11. 2018Residual Reinforcement Learning for Robot Controlcited by 242
  12. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
7 more
  1. 2019VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learningcited by 210
  2. 2018Residual Policy Learningcited by 146
  3. 2023IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Realitycited by 44
  4. 2025Residual Off-Policy RL for Finetuning Behavior Cloning Policiescited by 42
  5. 2024A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoalscited by 20
  6. 2024FORGE: Force-Guided Exploration for Robust Contact-Rich Manipulation under Uncertaintycited by 18
  7. 2023Rapid Motor Adaptation for Robotic Manipulator Armscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Proprioception-Anchored Cross-Modal Pretraining for Zero-Shot Sim-to-Real Contact-Rich Assemblycited by 0