A Unified Multi-Layer Framework for Skill Acquisition from Imperfect Human Demonstrations

• URL: http://arxiv.org/abs/2604.08341v1
• Date: Thu, 09 Apr 2026 15:13:19 GMT
• Title: A Unified Multi-Layer Framework for Skill Acquisition from Imperfect Human Demonstrations
• Abstract summary: Current Human-Robot Interaction (HRI) systems for skill teaching are fragmented.<n>Existing approaches in the literature do not offer a cohesive framework that is simultaneously efficient, intuitive, and universally safe.<n>This paper presents a novel, layered control framework that enables robust, compliant Learning from Demonstration.
• Score: 7.8260466406864575
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Current Human-Robot Interaction (HRI) systems for skill teaching are fragmented, and existing approaches in the literature do not offer a cohesive framework that is simultaneously efficient, intuitive, and universally safe. This paper presents a novel, layered control framework that addresses this fundamental gap by enabling robust, compliant Learning from Demonstration (LfD) built upon a foundation of universal robot compliance. The proposed approach is structured in three progressive and interconnected stages. First, we introduce a real-time LfD method that learns both the trajectory and variable impedance from a single demonstration, significantly improving efficiency and reproduction fidelity. To ensure high-quality and intuitive {kinesthetic teaching}, we then present a null-space optimization strategy that proactively manages singularities and provides a consistent interaction feel during human demonstration. Finally, to ensure generalized safety, we introduce a foundational null-space compliance method that enables the entire robot body to compliantly adapt to post-learning external interactions without compromising main task performance. This final contribution transforms the system into a versatile HRI platform, moving beyond end-effector (EE)-specific applications. We validate the complete framework through comprehensive comparative experiments on a 7-DOF KUKA LWR robot. The results demonstrate a safer, more intuitive, and more efficient unified system for a wide range of human-robot collaborative tasks.

Related papers

• CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment [54.84167973913561]
  CoEnv is a framework that leverages simulation for safe strategy exploration while ensuring reliable real-world deployment.<n>CoEnv operates through three stages: real-to-sim scene reconstruction that digitizes physical workspaces, VLM-driven action synthesis supporting both real-time planning with code-based trajectory generation, and validated sim-to-real transfer with collision detection for safe deployment.
  arXiv  Detail & Related papers  (2026-04-07T06:24:41Z)
• InterReal: A Unified Physics-Based Imitation Framework for Learning Human-Object Interaction Skills [16.31202379413011]
  We develop a unified physics-based imitation learning framework for Real-world human-object Interaction (HOI) control.<n>InterReal enables humanoid robots to track HOI reference motions, facilitating the learning of fine-grained interactive skills.<n>A meta-policy guided by critical tracking error metrics explores and allocates reward signals to the low-level reinforcement learning objective.
  arXiv  Detail & Related papers  (2026-03-08T07:44:35Z)
• Interaction-Grounded Learning for Contextual Markov Decision Processes with Personalized Feedback [59.287761696290865]
  We propose a computationally efficient algorithm that achieves a sublinear regret guarantee for contextual episodic Markov Decision Processes (MDPs) with personalized feedback.<n>We demonstrate the effectiveness of our method in learning personalized objectives from multi-turn interactions through experiments on both a synthetic episodic MDP and a real-world user booking dataset.
  arXiv  Detail & Related papers  (2026-02-09T06:29:54Z)
• Scalable Dexterous Robot Learning with AR-based Remote Human-Robot Interactions [8.111267700755986]
  This paper focuses on the scalable robot learning for manipulation in the dexterous robot arm-hand systems.<n>We present a unified framework to address the general manipulation task problem.
  arXiv  Detail & Related papers  (2026-02-07T03:47:21Z)
• ConceptACT: Episode-Level Concepts for Sample-Efficient Robotic Imitation Learning [2.9277370836568264]
  ConceptACT is an extension of Action Chunking with Transformers that leverages episode-level semantic concept annotations during training to improve learning efficiency.<n>We integrate concepts using a modified transformer architecture in which the final encoder layer implements concept-aware cross-attention, supervised to align with human annotations.
  arXiv  Detail & Related papers  (2026-01-23T19:24:00Z)
• Generalizable Geometric Prior and Recurrent Spiking Feature Learning for Humanoid Robot Manipulation [90.90219129619344]
  This paper presents a novel R-prior-S, Recurrent Geometric-priormodal Policy with Spiking features.<n>To ground high-level reasoning in physical reality, we leverage lightweight 2D geometric inductive biases.<n>For the data efficiency issue in robotic action generation, we introduce a Recursive Adaptive Spiking Network.
  arXiv  Detail & Related papers  (2026-01-13T23:36:30Z)
• Learning specifications for reactive synthesis with safety constraints [9.76292270520872]
  We model latent tasks as probabilistic formal languages and introduce a tailored reactive synthesis framework.<n>We adapt existing evidence-driven state algorithms merging and incorporate safety requirements throughout the learning process.<n>Our approach models the interaction as a two-player game between the robot and the environment, accounting for dynamic changes.
  arXiv  Detail & Related papers  (2026-01-09T05:17:45Z)
• StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation [56.996371714721995]
  We propose an unsupervised approach that learns a highly compressed two-token state representation.<n>Our representation is efficient, interpretable, and integrates seamlessly into existing VLA-based models.<n>We name our method StaMo for its ability to learn generalizable robotic Motion from compact State representation.
  arXiv  Detail & Related papers  (2025-10-06T17:37:24Z)
• Self-Augmented Robot Trajectory: Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precision [2.3548641190233264]
  Self-Augmented Robot Trajectory (SART) is a framework that enables policy learning from a single human demonstration.<n>SART achieves substantially higher success rates than policies trained solely on human-collected demonstrations.
  arXiv  Detail & Related papers  (2025-09-11T23:10:56Z)
• Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics [50.191655141020505]
  This work advances model-based reinforcement learning by addressing the challenges of long-horizon prediction, error accumulation, and sim-to-real transfer.<n>By providing a scalable and robust framework, the introduced methods pave the way for adaptive and efficient robotic systems in real-world applications.
  arXiv  Detail & Related papers  (2025-01-17T10:39:09Z)
• Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration [68.94506047556412]
  We propose to leverage a sequential bias to learn control policies for complex robotic tasks using a single demonstration. We show that DCIL-II can solve with unprecedented sample efficiency some challenging simulated tasks such as humanoid locomotion and stand-up.
  arXiv  Detail & Related papers  (2022-11-09T10:28:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.