Subconscious Robotic Imitation Learning
On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning
Abstract (arXiv)
Although robotic imitation learning (RIL) is promising for embodied intelligent robots, existing RIL approaches rely on computationally intensive multi-model trajectory predictions, resulting in slow execution and limited real-time responsiveness. Instead, human beings subconscious can constantly process and store vast amounts of information from their experiences, perceptions, and learning, allowing them to fulfill complex actions such as riding a bike, without consciously thinking about each. Inspired by this phenomenon in action neurology, we introduced subconscious robotic imitation learning (SRIL), wherein cognitive offloading was combined with historical action chunkings to reduce delays caused by model inferences, thereby accelerating task execution. This process was further enhanced by subconscious downsampling and pattern augmented learning policy wherein intent-rich information was addressed with quantized sampling techniques to improve manipulation efficiency. Experimental results demonstrated that execution speeds of the SRIL were 100% to 200% faster over SOTA policies for comprehensive dual-arm tasks, with consistently higher success rates.
Key facts. Cited by 2 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 12 of its 37 references that are in the map. First posted on arXiv 29 Dec 2024.
Builds on
12 of 37 references.
Closest ancestors · 2
Same direction, newest first
- 2024Enabling Stateful Behaviors for Diffusion-based Policy Learning18 Apr
- 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware23 Apr
Other references · 10
- 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 750
- 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 394
- 2024ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulationcited by 315
- 2022gDDIM: Generalized denoising diffusion implicit modelscited by 125
- 2017Neural Map: Structured Memory for Deep Reinforcement Learningcited by 90
- 2024One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillationcited by 89
- 2023One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformerscited by 17
- 2024VQ-ACE: Efficient Policy Search for Dexterous Robotic Manipulation via Action Chunking Embeddingcited by 7
- 2024DA-VIL: Adaptive Dual-Arm Manipulation with Reinforcement Learning and Variable Impedance Controlcited by 3
- 2024Remember and Recall: Associative-Memory-based Trajectory Predictioncited by 2
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
- 2022Learning and Retrieval from Prior Data for Skill-based Imitation Learning
- 2026ConceptACT: Episode-Level Concepts for Sample-Efficient Robotic Imitation Learning
- 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
- 2021Manipulator-Independent Representations for Visual Imitation
- 2023CasIL: Cognizing and Imitating Skills via a Dual Cognition-Action Architecture
- 2026VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memory
- 2018Learning Real-World Robot Policies by Dreaming