NaviSlim: Adaptive Context-Aware Navigation and Sensing via Dynamic Slimmable Networks

• URL: http://arxiv.org/abs/2407.01563v1
• Date: Thu, 16 May 2024 01:18:52 GMT
• Title: NaviSlim: Adaptive Context-Aware Navigation and Sensing via Dynamic Slimmable Networks
• Authors: Tim Johnsen, Marco Levorato,
• Abstract summary: NaviSlim is a new class of neural navigation models capable of adapting the amount of resources spent on computing and sensing. NaviSlim is designed as a gated slimmable neural network architecture that, different from existing slimmable networks, can dynamically select a slimming factor to autonomously scale model complexity. We evaluate our NaviSlim models on scenarios with varying difficulty and a test set that showed a dynamic reduced model complexity on average between 57-92%, and between 61-80% sensor utilization.
• Score: 2.145904182587639
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Small-scale autonomous airborne vehicles, such as micro-drones, are expected to be a central component of a broad spectrum of applications ranging from exploration to surveillance and delivery. This class of vehicles is characterized by severe constraints in computing power and energy reservoir, which impairs their ability to support the complex state-of-the-art neural models needed for autonomous operations. The main contribution of this paper is a new class of neural navigation models -- NaviSlim -- capable of adapting the amount of resources spent on computing and sensing in response to the current context (i.e., difficulty of the environment, current trajectory, and navigation goals). Specifically, NaviSlim is designed as a gated slimmable neural network architecture that, different from existing slimmable networks, can dynamically select a slimming factor to autonomously scale model complexity, which consequently optimizes execution time and energy consumption. Moreover, different from existing sensor fusion approaches, NaviSlim can dynamically select power levels of onboard sensors to autonomously reduce power and time spent during sensor acquisition, without the need to switch between different neural networks. By means of extensive training and testing on the robust simulation environment Microsoft AirSim, we evaluate our NaviSlim models on scenarios with varying difficulty and a test set that showed a dynamic reduced model complexity on average between 57-92%, and between 61-80% sensor utilization, as compared to static neural networks designed to match computing and sensing of that required by the most difficult scenario.

Related papers

• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• Optical Flow Matters: an Empirical Comparative Study on Fusing Monocular Extracted Modalities for Better Steering [37.46760714516923]
  This research introduces a new end-to-end method that exploits multimodal information from a single monocular camera to improve the steering predictions for self-driving cars. By focusing on the fusion of RGB imagery with depth completion information or optical flow data, we propose a framework that integrates these modalities through both early and hybrid fusion techniques.
  arXiv  Detail & Related papers  (2024-09-18T09:36:24Z)
• HGFF: A Deep Reinforcement Learning Framework for Lifetime Maximization in Wireless Sensor Networks [5.4894758104028245]
  We propose a new framework combining heterogeneous graph neural network with deep reinforcement learning to automatically construct the movement path of the sink. We design ten types of static and dynamic maps to simulate different wireless sensor networks in the real world. Our approach consistently outperforms the existing methods on all types of maps.
  arXiv  Detail & Related papers  (2024-04-11T13:09:11Z)
• PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search [64.28335667655129]
  Multiple object tracking is a critical task in autonomous driving. As tracking accuracy improves, neural networks become increasingly complex, posing challenges for their practical application in real driving scenarios due to the high level of latency. In this paper, we explore the use of the neural architecture search (NAS) methods to search for efficient architectures for tracking, aiming for low real-time latency while maintaining relatively high accuracy.
  arXiv  Detail & Related papers  (2024-03-23T04:18:49Z)
• Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch [72.26822499434446]
  Auto-Train-Once (ATO) is an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures.
  arXiv  Detail & Related papers  (2024-03-21T02:33:37Z)
• Eco-Driving Control of Connected and Automated Vehicles using Neural Network based Rollout [0.0]
  Connected and autonomous vehicles have the potential to minimize energy consumption. Existing deterministic and methods created to solve the eco-driving problem generally suffer from high computational and memory requirements. This work proposes a hierarchical multi-horizon optimization framework implemented via a neural network.
  arXiv  Detail & Related papers  (2023-10-16T23:13:51Z)
• Autonomous Driving using Spiking Neural Networks on Dynamic Vision Sensor Data: A Case Study of Traffic Light Change Detection [0.0]
  Spiking neural networks (SNNs) provide an alternative model to process information and make decisions. Recent work using SNNs for autonomous driving mostly focused on simple tasks like lane keeping in simplified simulation environments. This project studies SNNs on photo-realistic driving scenes in the CARLA simulator, which is an important step toward using SNNs on real vehicles.
  arXiv  Detail & Related papers  (2023-09-27T23:31:30Z)
• Energy-Efficient On-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing [59.40731173370976]
  We investigate the application of energy-efficient brain-inspired machine learning models for on-board radio resource management. For relevant workloads, spiking neural networks (SNNs) implemented on Loihi 2 yield higher accuracy, while reducing power consumption by more than 100$times$ as compared to the CNN-based reference platform.
  arXiv  Detail & Related papers  (2023-08-22T03:13:57Z)
• Deep Learning for Real Time Satellite Pose Estimation on Low Power Edge TPU [58.720142291102135]
  In this paper we propose a pose estimation software exploiting neural network architectures. We show how low power machine learning accelerators could enable Artificial Intelligence exploitation in space.
  arXiv  Detail & Related papers  (2022-04-07T08:53:18Z)
• Flexible Transmitter Network [84.90891046882213]
  Current neural networks are mostly built upon the MP model, which usually formulates the neuron as executing an activation function on the real-valued weighted aggregation of signals received from other neurons. We propose the Flexible Transmitter (FT) model, a novel bio-plausible neuron model with flexible synaptic plasticity. We present the Flexible Transmitter Network (FTNet), which is built on the most common fully-connected feed-forward architecture.
  arXiv  Detail & Related papers  (2020-04-08T06:55:12Z)
• Zero-Shot Reinforcement Learning with Deep Attention Convolutional Neural Networks [12.282277258055542]
  We show that a deep attention convolutional neural network (DACNN) with specific visual sensor configuration performs as well as training on a dataset with high domain and parameter variation at lower computational complexity. Our new architecture adapts perception with respect to the control objective, resulting in zero-shot learning without pre-training a perception network.
  arXiv  Detail & Related papers  (2020-01-02T19:41:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.