Bioinspired Sensing and Computational Methods Enabling Edge Computing for Autonomous Platforms

Abstract

The objective of this work is to use novel sensor processing techniques to provide improved autonomous robot capabilities by changing the way onboard computation is performed. The scope of this project is circuit and algorithm co-development, computer simulation, and circuit/sensor hardware experiments. We will assess the performance of the proposed bio-inspired edge computing method for sensor data output. The proposed method’s computation capabilities will be compared to standard digital implementation methods (e.g. image processing, neural networks, position localization). The system level problem being addressed is to explore the intersection of sensors and computing for optimal architectures. The anticipated outcome is that by understanding the sensor format and computation we will be able to define better resource optimized architectures. This will provide better onboard computation systems for small autonomous robots performing missions. This is important because onboard computation is limited due to size and power constraints. Potential applications are for integration into multi-vehicle autonomy systems to improve navigation, acoustic localization, or underwater sound tracking in challenging environments. The broad technical approach is to develop non-traditional computing, such as neuromorphic computation and sensing architectures. A potential impact is improved system robustness to noise. This architecture is efficient for making decisions on small amounts of information and incrementally refined. An anticipated outcome is that this provides a framework for integrating progressive observations to improve the solution with an efficient architecture. This NEEC proposal focuses on the intersection of sensing and computing.

Document Details

Document Type
DoD Grant Award
Publication Date
Mar 18, 2025
Source ID
N001742210005

Entities

People

  • Scott Koziol

Organizations

  • Baylor University
  • United States Navy

Tags

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Robotics and Automation.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy
  • Autonomy - Autonomous System Control
  • Biotechnology