# Motion Perceiver: Real-Time Occupancy Forecasting for Embedded Systems

arXiv: https://arxiv.org/abs/2306.08879 · HTML: https://mlsanity.com/paper/2306.08879/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2023.

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

- [Hybrid-Prediction Integrated Planning for Autonomous Driving](https://mlsanity.com/paper/2402.02426/) (2024)
- [OccProphet: Pushing Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with Observer-Forecaster-Refiner Framework](https://mlsanity.com/paper/2502.15180/) (2025)
- [FSF-Net: Enhance 4D Occupancy Forecasting with Coarse BEV Scene Flow for Autonomous Driving](https://mlsanity.com/paper/2409.15841/) (2024)

## Abstract (arXiv)

This work introduces a novel and adaptable architecture designed for real-time occupancy forecasting that outperforms existing state-of-the-art models on the Waymo Open Motion Dataset in Soft IOU. The proposed model uses recursive latent state estimation with learned transformer-based functions to effectively update and evolve the state. This enables highly efficient real-time inference on embedded systems, as profiled on an Nvidia Xavier AGX. Our model, MotionPerceiver, achieves this by encoding a scene into a latent state that evolves in time through self-attention mechanisms. Additionally, it incorporates relevant scene observations, such as traffic signals, road topology and agent detections, through cross-attention mechanisms. This forms an efficient data-streaming architecture, that contrasts with the expensive, fixed-sequence input common in existing models. The architecture also offers the distinct advantage of generating occupancy predictions through localized querying based on a point-of-interest, as opposed to generating fixed-size occupancy images that render potentially irrelevant regions.