# Interactive incremental learning of generalizable skills with local trajectory modulation

arXiv: https://arxiv.org/abs/2409.05655 · HTML: https://mlsanity.com/paper/2409.05655/

## Key facts

- Cited by 5 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 15 of its 43 references that are in the map.
- First posted on arXiv 9 Sep 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, 15 of 15)

- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Interactive Imitation Learning in Robotics: A Survey](https://mlsanity.com/paper/2211.00600/) (2022)
- [Kernelized Movement Primitives](https://mlsanity.com/paper/1708.08638/) (2017)
- [ILoSA: Interactive Learning of Stiffness and Attractors](https://mlsanity.com/paper/2103.03099/) (2021)
- [Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives](https://mlsanity.com/paper/1903.02114/) (2019)
- [Interactive Imitation Learning in State-Space](https://mlsanity.com/paper/2008.00524/) (2020)
- [Learning Task-Parameterized Skills from Few Demonstrations](https://mlsanity.com/paper/2201.09975/) (2022)
- [Learning from demonstration with model-based Gaussian process](https://mlsanity.com/paper/1910.05005/) (2019)
- [Learning to Pick at Non-Zero-Velocity from Interactive Demonstrations](https://mlsanity.com/paper/2110.04534/) (2021)
- [Trajectory Deformations from Physical Human-Robot Interaction](https://mlsanity.com/paper/1710.09871/) (2017)
- [Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation](https://mlsanity.com/paper/1903.01240/) (2019)
- [Incremental Skill Learning of Stable Dynamical Systems](https://mlsanity.com/paper/2003.11803/) (2020)
- [Learning from Few Demonstrations with Frame-Weighted Motion Generation](https://mlsanity.com/paper/2303.14188/) (2023)
- [Learning Dynamical Systems Encoding Non-Linearity within Space Curvature](https://mlsanity.com/paper/2403.11948/) (2024)
- [Shared Autonomy via Variable Impedance Control and Virtual Potential Fields for Encoding Human Demonstration](https://mlsanity.com/paper/2403.12720/) (2024)

## Built on by (most cited first, 5 of 5)

- [Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey](https://mlsanity.com/paper/2506.00098/) (2025)
- [IROSA: Interactive Robot Skill Adaptation using Natural Language](https://mlsanity.com/paper/2603.03897/) (2026)
- [VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations](https://mlsanity.com/paper/2608.06210/) (2026)
- [MOMO: A framework for seamless physical, verbal, and graphical robot skill learning and adaptation](https://mlsanity.com/paper/2604.20468/) (2026)
- [CLASP: Language-Driven Robot Skill Selection and Composition using Task-Parameterized Learning](https://mlsanity.com/paper/2606.08169/) (2026)

## Abstract (arXiv)

The problem of generalization in learning from demonstration (LfD) has received considerable attention over the years, particularly within the context of movement primitives, where a number of approaches have emerged. Recently, two important approaches have gained recognition. While one leverages via-points to adapt skills locally by modulating demonstrated trajectories, another relies on so-called task-parameterized models that encode movements with respect to different coordinate systems, using a product of probabilities for generalization. While the former are well-suited to precise, local modulations, the latter aim at generalizing over large regions of the workspace and often involve multiple objects. Addressing the quality of generalization by leveraging both approaches simultaneously has received little attention. In this work, we propose an interactive imitation learning framework that simultaneously leverages local and global modulations of trajectory distributions. Building on the kernelized movement primitives (KMP) framework, we introduce novel mechanisms for skill modulation from direct human corrective feedback. Our approach particularly exploits the concept of via-points to incrementally and interactively 1) improve the model accuracy locally, 2) add new objects to the task during execution and 3) extend the skill into regions where demonstrations were not provided. We evaluate our method on a bearing ring-loading task using a torque-controlled, 7-DoF, DLR SARA robot.