# Learning to Throw-Flip

arXiv: https://arxiv.org/abs/2510.10357 · HTML: https://mlsanity.com/paper/2510.10357/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 5 of 5)

- [TossingBot: Learning to Throw Arbitrary Objects with Residual Physics](https://mlsanity.com/paper/1903.11239/) (2019)
- [Throwing Objects into A Moving Basket While Avoiding Obstacles](https://mlsanity.com/paper/2210.00609/) (2022)
- [Learning Accurate Whole-body Throwing with High-frequency Residual Policy and Pullback Tube Acceleration](https://mlsanity.com/paper/2506.16986/) (2025)
- [A Solution to Adaptive Mobile Manipulator Throwing](https://mlsanity.com/paper/2207.10629/) (2022)
- [Dynamic Throwing with Robotic Material Handling Machines](https://mlsanity.com/paper/2405.19001/) (2024)

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

- [Non-Prehensile Throwing: A Reinforcement Learning Perspective](https://mlsanity.com/paper/2609.00771/) (2026)

## Abstract (arXiv)

Dynamic manipulation, such as robot tossing or throwing objects, has recently gained attention as a novel paradigm to speed up logistic operations. However, the focus has predominantly been on the object's landing location, irrespective of its final orientation. In this work, we present a method enabling a robot to accurately "throw-flip" objects to a desired landing pose (position and orientation). Conventionally, objects thrown by revolute robots suffer from parasitic rotation, resulting in highly restricted and uncontrollable landing poses. Our approach is based on two key design choices: first, leveraging the impulse-momentum principle, we design a family of throwing motions that effectively decouple the parasitic rotation, significantly expanding the feasible set of landing poses. Second, we combine a physics-based model of free flight with regression-based learning methods to account for unmodeled effects. Real robot experiments demonstrate that our framework can learn to throw-flip objects to a pose target within (±5 cm, ±45 degrees) threshold in dozens of trials. Thanks to data assimilation, incorporating projectile dynamics reduces sample complexity by an average of 40% when throw-flipping to unseen poses compared to end-to-end learning methods. Additionally, we show that past knowledge on in-hand object spinning can be effectively reused, accelerating learning by 70% when throwing a new object with a Center of Mass (CoM) shift. A video summarizing the proposed method and the hardware experiments is available at https://youtu.be/txYc9b1oflU.