# One-Shot Multimodal Learning from Demonstration with Force-Constrained Elastic Maps

arXiv: https://arxiv.org/abs/2607.09515 · HTML: https://mlsanity.com/paper/2607.09515/

## Key facts

- No citing papers in the map yet (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 7 of its 30 references that are in the map.
- First posted on arXiv 10 Jul 2026.

## 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, 7 of 7)

- [Sim2Real Transfer for Reinforcement Learning without Dynamics Randomization](https://mlsanity.com/paper/2002.11635/) (2020)
- [A Compliant, Underactuated Hand for Robust Manipulation](https://mlsanity.com/paper/1301.4394/) (2013)
- [Combining Learning from Demonstration with Learning by Exploration to Facilitate Contact-Rich Tasks](https://mlsanity.com/paper/2103.05904/) (2021)
- [Robot Learning from Demonstration Using Elastic Maps](https://mlsanity.com/paper/2208.02207/) (2022)
- [Confidence-Based Skill Reproduction Through Perturbation Analysis](https://mlsanity.com/paper/2305.03091/) (2023)
- [A Framework for Learning and Reusing Robotic Skills](https://mlsanity.com/paper/2404.18383/) (2024)
- [Parameter-Free Segmentation of Robot Movements with Cross-Correlation Using Different Similarity Metrics](https://mlsanity.com/paper/2505.06100/) (2025)

## Abstract (arXiv)

Robotic manipulation tasks often require simultaneous reasoning over motion and contact forces, yet most Learning from Demonstration (LfD) methods model only spatial trajectories and neglect force interactions with the environment. This limitation reduces robustness and can lead to unsafe or inconsistent task reproduction in force-constrained settings. We propose a novel one-shot multimodal LfD framework for the segmentation, encoding, and reproduction of force-inclusive demonstrations. First, we introduce a multimodal probabilistic segmentation method that adaptively weighs spatial and force modalities over time, enabling the automatic extraction of force-aware motion primitives. Second, we extend the elastic maps representation to incorporate external force constraints during skill encoding and formulate a convex optimization procedure for learning force-consistent trajectory models. The resulting skills reproduce both motion and contact characteristics from a single demonstration while promoting safer execution by accounting for demonstrated force profiles. We validate our approach on five real-world manipulation tasks across two distinct force-sensing configurations: wrist force sensing on a UR5e with a Robotiq 2f-85 gripper and finger force sensing on a Kinova Gen3 with an Openhand Model O gripper. Experimental results demonstrate robust multimodal segmentation, accurate force-aware reproduction, and cross-platform generality.