# Screw Geometry Meets Bandits: Incremental Acquisition of Demonstrations to Generate Manipulation Plans

arXiv: https://arxiv.org/abs/2410.18275 · HTML: https://mlsanity.com/paper/2410.18275/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 48 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Builds on (most cited first, 10 of 10)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation](https://mlsanity.com/paper/2401.02117/) (2024)
- [Optimal Best Arm Identification with Fixed Confidence](https://mlsanity.com/paper/1602.04589/) (2016)
- [SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion](https://mlsanity.com/paper/2209.03855/) (2022)
- [Hierarchical Neural Dynamic Policies](https://mlsanity.com/paper/2107.05627/) (2021)
- [Merging Position and Orientation Motion Primitives](https://mlsanity.com/paper/2003.11507/) (2020)
- [EVE: Enabling Anyone to Train Robots using Augmented Reality](https://mlsanity.com/paper/2404.06089/) (2024)
- [Human-Guided Planning for Complex Manipulation Tasks Using the Screw Geometry of Motion](https://mlsanity.com/paper/2209.05672/) (2022)
- [Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning](https://mlsanity.com/paper/2211.15542/) (2022)

## Abstract (arXiv)

In this paper, we study the problem of methodically obtaining a sufficient set of kinesthetic demonstrations, one at a time, such that a robot can be confident of its ability to perform a complex manipulation task in a given region of its workspace. Although programming by demonstration has been an active area of research, the problems of checking whether a set of demonstrations is sufficient and systematically seeking additional demonstrations have remained open. We present an approach for the robot to incrementally and actively ask for new demonstration examples, one at a time, until the robot can assess with high confidence that it can perform the task successfully. Our approach uses: (i) a screw geometric representation of motion to generate manipulation plans from demonstrations, which makes the sufficiency of a set of demonstrations measurable; (ii) a sampling strategy based on PAC-learning from multi-armed bandit optimization to evaluate the robot's ability to generate manipulation plans in a subregion of its task space; and (iii) a heuristic to seek additional demonstration from areas of weakness. We present results of a user study conducted with 22 participants (without any background in robotics) on two example manipulation tasks, namely pouring and scooping, to assess the utility and usability of our approach. The results show that a handful of examples (fewer than 10) were needed to successfully teach the robot to plan tasks. A short video supplement is available on YouTube: https://youtu.be/KbAPgIouIvo