# Communication Reduction via Semantic-Based Encoding in DMPC Using LSTMs

arXiv: https://arxiv.org/abs/2608.17592 · HTML: https://mlsanity.com/paper/2608.17592/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 40 references that are in the map.
- First posted on arXiv 18 Aug 2026.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1402.1128/) (2014)
- [Less Data, More Knowledge: Building Next Generation Semantic Communication Networks](https://mlsanity.com/paper/2211.14343/) (2022)
- [Semantic Communications in Networked Systems: A Data Significance Perspective](https://mlsanity.com/paper/2103.05391/) (2021)
- [Goal-oriented Policies for Cost of Actuation Error Minimization in Wireless Autonomous Systems](https://mlsanity.com/paper/2303.04908/) (2023)
- [Distributed Nonlinear MPC of Multi-Agent Systems with Data Compression and Random Delays - Extended Version](https://mlsanity.com/paper/1504.03494/) (2015)
- [Toward Goal-Oriented Communication in Multi-Agent Systems: An overview](https://mlsanity.com/paper/2508.07720/) (2025)
- [Semantic-Functional Communications in Cyber-Physical Systems](https://mlsanity.com/paper/2305.19710/) (2023)
- [Decentralized Real-Time Iterations for Distributed NMPC](https://mlsanity.com/paper/2401.14898/) (2024)
- [Cooperative distributed model predictive control for embedded systems: Experiments with hovercraft formations](https://mlsanity.com/paper/2409.13334/) (2024)
- [Reducing the Communication of Distributed Model Predictive Control: Autoencoders and Formation Control](https://mlsanity.com/paper/2504.05223/) (2025)
- [DMPC-Swarm: Distributed Model Predictive Control on Nano UAV Swarms](https://mlsanity.com/paper/2508.20553/) (2025)

## Abstract (arXiv)

The communication demands of distributed model prediction control (DMPC) can overwhelm even advanced wireless communication technologies as agents must exchange a significant amount of information at least once per time step. To semantically reduce communication demands, this work employs encoder-decoder networks built around long-short term memory (LSTM) cells in a distributed optimization algorithm. Agents publish a reduced representation of a message and receivers reconstruct the original message upon reception. In tests with reduced communication using formations of mobile robots, trained networks retain satisfactory performance and work reliably under conditions overwhelming full communication. As the results show, the usage of LSTMs either allows unprecedented reconstruction accuracy or the usage of different prediction-horizon lengths without the necessity to retrain.