# HeteroEdge: Addressing Asymmetry in Heterogeneous Collaborative Autonomous Systems

arXiv: https://arxiv.org/abs/2305.03252 · HTML: https://mlsanity.com/paper/2305.03252/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 30 references that are in the map.
- First posted on arXiv 5 May 2023.

## Builds on (most cited first, 5 of 5)

- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [An Overview of Drone Energy Consumption Factors and Models](https://mlsanity.com/paper/2206.10775/) (2022)
- [Underwater Node Localization using Optoacoustic Signals](https://mlsanity.com/paper/2201.08540/) (2022)
- [Heuristic Algorithms for Co-scheduling of Edge Analytics and Routes for UAV Fleet Missions](https://mlsanity.com/paper/2102.08768/) (2021)

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

- [TinyVQA: Compact Multimodal Deep Neural Network for Visual Question Answering on Resource-Constrained Devices](https://mlsanity.com/paper/2404.03574/) (2024)
- [Joint Retrieval of Cloud properties using Attention-based Deep Learning Models](https://mlsanity.com/paper/2504.03133/) (2025)
- [Detecting Abnormal Health Conditions in Smart Home Using a Drone](https://mlsanity.com/paper/2310.05012/) (2023)

## Abstract (arXiv)

Gathering knowledge about surroundings and generating situational awareness for IoT devices is of utmost importance for systems developed for smart urban and uncontested environments. For example, a large-area surveillance system is typically equipped with multi-modal sensors such as cameras and LIDARs and is required to execute deep learning algorithms for action, face, behavior, and object recognition. However, these systems face power and memory constraints due to their ubiquitous nature, making it crucial to optimize data processing, deep learning algorithm input, and model inference communication. In this paper, we propose a self-adaptive optimization framework for a testbed comprising two Unmanned Ground Vehicles (UGVs) and two NVIDIA Jetson devices. This framework efficiently manages multiple tasks (storage, processing, computation, transmission, inference) on heterogeneous nodes concurrently. It involves compressing and masking input image frames, identifying similar frames, and profiling devices to obtain boundary conditions for optimization.. Finally, we propose and optimize a novel parameter split-ratio, which indicates the proportion of the data required to be offloaded to another device while considering the networking bandwidth, busy factor, memory (CPU, GPU, RAM), and power constraints of the devices in the testbed. Our evaluations captured while executing multiple tasks (e.g., PoseNet, SegNet, ImageNet, DetectNet, DepthNet) simultaneously, reveal that executing 70% (split-ratio=70%) of the data on the auxiliary node minimizes the offloading latency by approx. 33% (18.7 ms/image to 12.5 ms/image) and the total operation time by approx. 47% (69.32s to 36.43s) compared to the baseline configuration (executing on the primary node).