Summary of Interactive Incremental Learning Of Generalizable Skills with Local Trajectory Modulation, by Markus Knauer et al.
Interactive incremental learning of generalizable skills with local trajectory modulation
by Markus Knauer, Alin Albu-Schäffer, Freek Stulp, João Silvério
First submitted to arxiv on: 9 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Robotics (cs.RO)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes an interactive imitation learning framework that leverages both local and global modulations of trajectory distributions to improve generalization in learning from demonstration (LfD). Building on the kernelized movement primitives (KMP) framework, the approach introduces novel mechanisms for skill modulation using direct human corrective feedback. The method exploits via-points to incrementally improve model accuracy locally, add new objects to the task during execution, and extend the skill into regions where demonstrations were not provided. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a way for robots to learn from humans by combining two existing methods. One method adjusts small parts of a movement, while the other method uses different coordinate systems to generalize over larger areas. The new approach combines these two methods to improve how well the robot generalizes what it learns. It also allows humans to correct the robot’s mistakes and add new objects to the task. This is tested on a specific type of robot arm. |
Keywords
» Artificial intelligence » Generalization
