# Neural Motion Prediction for In-flight Uneven Object Catching

arXiv: https://arxiv.org/abs/2103.08368 · HTML: https://mlsanity.com/paper/2103.08368/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2021.

## Built on by (most cited first, 3 of 3)

- [Feedback Favors the Generalization of Neural ODEs](https://mlsanity.com/paper/2410.10253/) (2024)
- [Modular Neural Network Policies for Learning In-Flight Object Catching with a Robot Hand-Arm System](https://mlsanity.com/paper/2312.13987/) (2023)
- [Spatiotemporal Agility: Time-Constrained Reinforcement Learning for Vision-Guided Dynamic Quadrupedal Interception](https://mlsanity.com/paper/2608.06907/) (2026)

## Abstract (arXiv)

In-flight objects capture is extremely challenging. The robot is required to complete trajectory prediction, interception position calculation and motion planning in sequence within tens of milliseconds. As in-flight uneven objects are affected by various kinds of forces, motion prediction is difficult for a time-varying acceleration. In order to compensate the system's non-linearity, we introduce the Neural Acceleration Estimator (NAE) that estimates the varying acceleration by observing a small fragment of previous deflected trajectory. Moreover, end-to-end training with Differantiable Filter (NAE-DF) gives a supervision for measurement uncertainty and further improves the prediction accuracy. Experimental results show that motion prediction with NAE and NAE-DF is superior to other methods and has a good generalization performance on unseen objects. We test our methods on a robot, performing velocity control in real world and respectively achieve 83.3% and 86.7% success rate on a ploy urethane banana and a gourd. We also release an object in-flight dataset containing 1,500 trajectorys for uneven objects.