# Exploiting Event Cameras for Spatio-Temporal Prediction of Fast-Changing Trajectories

arXiv: https://arxiv.org/abs/2001.01248 · HTML: https://mlsanity.com/paper/2001.01248/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jan 2020.

## Built on by (most cited first, 5 of 5)

- [EV-Catcher: High-Speed Object Catching Using Low-latency Event-based Neural Networks](https://mlsanity.com/paper/2304.07200/) (2023)
- [Fast Trajectory End-Point Prediction with Event Cameras for Reactive Robot Control](https://mlsanity.com/paper/2302.13796/) (2023)
- [Wandering around: A bioinspired approach to visual attention through object motion sensitivity](https://mlsanity.com/paper/2502.06747/) (2025)
- [Detection of Fast-Moving Objects with Neuromorphic Hardware](https://mlsanity.com/paper/2403.10677/) (2024)
- [ERF-GS: Reconstructing Fast Motion from Disjoint Event-RGB Viewpoints](https://mlsanity.com/paper/2608.08531/) (2026)

## Abstract (arXiv)

This paper investigates trajectory prediction for robotics, to improve the interaction of robots with moving targets, such as catching a bouncing ball. Unexpected, highly-non-linear trajectories cannot easily be predicted with regression-based fitting procedures, therefore we apply state of the art machine learning, specifically based on Long-Short Term Memory (LSTM) architectures. In addition, fast moving targets are better sensed using event cameras, which produce an asynchronous output triggered by spatial change, rather than at fixed temporal intervals as with traditional cameras. We investigate how LSTM models can be adapted for event camera data, and in particular look at the benefit of using asynchronously sampled data.