# Verifiable Learned Behaviors via Motion Primitive Composition: Applications to Scooping of Granular Media

arXiv: https://arxiv.org/abs/2309.14894 · HTML: https://mlsanity.com/paper/2309.14894/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 39 references that are in the map.
- First posted on arXiv 26 Sep 2023.

## Builds on (most cited first, 13 of 13)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [ChatGPT for Robotics: Design Principles and Model Abilities](https://mlsanity.com/paper/2306.17582/) (2023)
- [Control Barrier Function Based Quadratic Programs for Safety Critical Systems](https://mlsanity.com/paper/1609.06408/) (2016)
- [One-Shot Visual Imitation Learning via Meta-Learning](https://mlsanity.com/paper/1709.04905/) (2017)
- [Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?](https://mlsanity.com/paper/2204.11134/) (2022)
- [Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets](https://mlsanity.com/paper/1705.10479/) (2017)
- [Autonomously Navigating a Surgical Tool Inside the Eye by Learning from Demonstration](https://mlsanity.com/paper/2011.07785/) (2020)
- [A Scenario Approach to Risk-Aware Safety-Critical System Verification](https://mlsanity.com/paper/2203.02595/) (2022)
- [Sample-Based Bounds for Coherent Risk Measures: Applications to Policy Synthesis and Verification](https://mlsanity.com/paper/2204.09833/) (2022)
- [Robotic Handling of Compliant Food Objects by Robust Learning from Demonstration](https://mlsanity.com/paper/2309.12856/) (2023)
- [Robust Locomotion on Legged Robots through Planning on Motion Primitive Graphs](https://mlsanity.com/paper/2209.07503/) (2022)
- [Probabilistic Guarantees for Nonlinear Safety-Critical Optimal Control](https://mlsanity.com/paper/2303.06258/) (2023)

## Built on by (most cited first, 1 of 1)

- [HEIR: Learning Graph-Based Motion Hierarchies](https://mlsanity.com/paper/2510.26786/) (2025)

## Abstract (arXiv)

A robotic behavior model that can reliably generate behaviors from natural language inputs in real time would substantially expedite the adoption of industrial robots due to enhanced system flexibility. To facilitate these efforts, we construct a framework in which learned behaviors, created by a natural language abstractor, are verifiable by construction. Leveraging recent advancements in motion primitives and probabilistic verification, we construct a natural-language behavior abstractor that generates behaviors by synthesizing a directed graph over the provided motion primitives. If these component motion primitives are constructed according to the criteria we specify, the resulting behaviors are probabilistically verifiable. We demonstrate this verifiable behavior generation capacity in both simulation on an exploration task and on hardware with a robot scooping granular media.