Learning Forward & Reverse Skills from a Single Unfinished Demonstration for Constrained Manipulation Tasks

Published July 16, 2026 · Category: Robotics

Overview

arXiv:2607.13882v1 Announce Type: new Abstract: Learning from demonstration (LfD) enables robots to learn manipulation skills directly from expert demonstrations but remains challenging for contact-rich tasks involving geometric constraints and force interaction. Existing approaches typically require multiple complete demonstrations and do not support reverse skill execution. In this paper, we present a unified one-shot framework for constrained manipulation that learns both forward and reverse execution from a single, possibly unfinished demonstration. Our method decomposes demonstrations into non-contact and contact phases, with non-contact motion encoded with dynamic movement primitives (DMP), and contact motion represented as a sequence of screw motion primitives segmented by our proposed geometry-driven twist-direction segmentation algorithm. During execution, screw primitives are executed sequentially under admittance-guided pose correction and speed regulation, enabling task completion beyond the demonstrated trajectory length as well as reverse skill execution without additional learning data. Experiments on peg insertion, battery insertion, lock opening, and screw driving tasks demonstrate improved success rates and robustness over segmentation and one-shot trajectory learning baselines. Details are available on the project website: https://tuwien-asl.github.io/LfD-Screw/.

Source

Originally published at arxiv.org.

Related Articles

• HRO: Hierarchical Room-to-Object Framework for Zero-Shot Object Goal Navigation with Large Language Models
• Unifying Decision-Making and Trajectory-Planning in Unsignalized Intersections Using Time-Varying Potential Fields
• SPINE: Bridging the Cyber-Physical Gap with Agentic AI