# SAGE: A Split-Architecture Methodology for Efficient End-to-End Autonomous Vehicle Control

arXiv: https://arxiv.org/abs/2107.10895 · HTML: https://mlsanity.com/paper/2107.10895/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 47 references that are in the map.
- First posted on arXiv 22 Jul 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019)
- [A Survey of End-to-End Driving: Architectures and Training Methods](https://mlsanity.com/paper/2003.06404/) (2020)
- [On Offline Evaluation of Vision-based Driving Models](https://mlsanity.com/paper/1809.04843/) (2018)
- [Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks](https://mlsanity.com/paper/2007.15818/) (2020)
- [End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners](https://mlsanity.com/paper/1803.10158/) (2018)
- [LENS: Layer Distribution Enabled Neural Architecture Search in Edge-Cloud Hierarchies](https://mlsanity.com/paper/2107.09309/) (2021)

## Built on by (most cited first, 8 of 8)

- [RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understanding](https://mlsanity.com/paper/2304.08600/) (2023)
- [EcoFusion: Energy-Aware Adaptive Sensor Fusion for Efficient Autonomous Vehicle Perception](https://mlsanity.com/paper/2202.11330/) (2022)
- [Romanus: Robust Task Offloading in Modular Multi-Sensor Autonomous Driving Systems](https://mlsanity.com/paper/2207.08865/) (2022)
- [EnergyShield: Provably-Safe Offloading of Neural Network Controllers for Energy Efficiency](https://mlsanity.com/paper/2302.06572/) (2023)
- [Performance Implications of Multi-Chiplet Neural Processing Units on Autonomous Driving Perception](https://mlsanity.com/paper/2411.16007/) (2024)
- [SEO: Safety-Aware Energy Optimization Framework for Multi-Sensor Neural Controllers at the Edge](https://mlsanity.com/paper/2302.12493/) (2023)
- [CARMA: Context-Aware Runtime Reconfiguration for Energy-Efficient Sensor Fusion](https://mlsanity.com/paper/2306.15748/) (2023)
- [Energy-Efficient Autonomous Driving with Adaptive Perception and Robust Decision](https://mlsanity.com/paper/2510.25205/) (2025)

## Abstract (arXiv)

Autonomous vehicles (AV) are expected to revolutionize transportation and improve road safety significantly. However, these benefits do not come without cost; AVs require large Deep-Learning (DL) models and powerful hardware platforms to operate reliably in real-time, requiring between several hundred watts to one kilowatt of power. This power consumption can dramatically reduce vehicles' driving range and affect emissions. To address this problem, we propose SAGE: a methodology for selectively offloading the key energy-consuming modules of DL architectures to the cloud to optimize edge energy usage while meeting real-time latency constraints. Furthermore, we leverage Head Network Distillation (HND) to introduce efficient bottlenecks within the DL architecture in order to minimize the network overhead costs of offloading with almost no degradation in the model's performance. We evaluate SAGE using an Nvidia Jetson TX2 and an industry-standard Nvidia Drive PX2 as the AV edge devices and demonstrate that our offloading strategy is practical for a wide range of DL models and internet connection bandwidths on 3G, 4G LTE, and WiFi technologies. Compared to edge-only computation, SAGE reduces energy consumption by an average of 36.13%, 47.07%, and 55.66% for an AV with one low-resolution camera, one high-resolution camera, and three high-resolution cameras, respectively. SAGE also reduces upload data size by up to 98.40% compared to direct camera offloading.