LOW-LEVEL ESTIMATION AND CONTROL WITH A FULLY SPIKING NEURAL NETWORK AUTOPILOT FOR AUTONOMOUS DRONE FLIGHT

Abstract

There is a need in the Department of Defense (DoD) for advanced compute capabilities on platforms severely limited in Size, Weight, and Power (SWaP). For example, drones hold a large potential for various types of missions, if they are able to perform these missions in an autonomous fashion. However, current solutions for the artificial intelligence of robots require substantial resources in terms of sensing, computing power, and memory. For the swift onboard execution of deep artificial neural networks, processors are needed with Graphical Processing Units (GPUs). A typical processor is the NVidia TX2, weighing 76 grams and consuming 7.5 Watts. This makes it suboptimal for small drones (< 500 grams) if they have to fly longer distances and makes it unacceptable for very light-weight drones (<100 grams) that will be operating in swarms to perform collective missions. Spiking neural networks (SNNs) form a novel generation of neural networks that are highly promising, since they will reduce the required computing energy in the order of a factor 1000 or more1. This enormous reduction in energy expenditure comes from the fact that neurons in SNNs fire sparsely and asynchronously, and neurons only spend energy when firing. In the context of integrated circuit technology reaching fundamental physical limits due to thermal and stability issues, big technology companies have started to design hardware specifically for spiking nets, such as Intel’s Loihi and IBM’s True North. The main problem with SNNs is that their richer internal dynamics and the discrete nature of spikes make the straightforward utilization of traditional learning mechanisms such as backpropagation impossible. Most SNNs have been applied to relatively “simple” tasks, and only in recent years there has been progress towards more complex tasks such as visual object recognition.

Document Details

Document Type
DoD Grant Award
Publication Date
Aug 11, 2021
Source ID
FA86552017044

Entities

People

  • Guido de Croon

Organizations

  • Air Force Office of Scientific Research
  • Delft University of Technology
  • United States Air Force

Tags

Readers

  • Aerial Unmanned Vehicle Swarm Micro Periodontal Dentistry.
  • Neural Network Machine Learning.
  • Parallel and Distributed Computing.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks
  • Autonomy
  • Autonomy - Autonomous System Control