Autonomous Navigation via Deep Reinforcement Learning for Resource Constraint Edge Nodes Using Transfer Learning

Abstract

Smart and agile drones are fast becoming ubiquitous at the edge of the cloud. The usage of these drones are constrained by their limited power and compute capability. In this paper, we present a Transfer Learning (TL) based approach to reduce on-board computation required to train a deep neural network for autonomous navigation via Deep Reinforcement Learning for a target algorithmic performance. A library of 3D realistic meta-environments is manually designed using Unreal Gaming Engine and the network is trained end-toend. These trained meta-weights are then used as initializers to the network in a test environment and fine-tuned for the last few fully connected layers. Variation in drone dynamics and environmental characteristics is carried out to show robustness of the approach. Using NVIDIA GPU profiler it was shown that the energy consumption and training latency is reduced by 3.7x and 1.8x respectively without significant degradation in the performance in terms of average distance traveled before crash i.e. Mean Safe Flight (MSF). The approach is also tested on a real environment using DJI Tello drone and similar results were reported. The code of the approach can be found on GitHub: https://github.com/aqeelanwar/Deep-Reinforcement-Learning-DJI-Tello.git. The video of the drone with proposed approach will be uploaded to YouTube.

Counter a Drone in a Complex Neighborhood Area by Deep Reinforcement Learning

“…Anwar et al [8] studied the DRL for autonomous navigation. Transfer learning is applied to reduce the training computation load.…”

B5G and Explainable Deep Learning Assisted Healthcare Vertical at the Edge: COVID-I9 Perspective

“…This global deep learning model could be hosted by the World Health Organization (WHO). Edge learning can allow 5G mMTC phenomena to be realized by deploying deep learning models to recognize blood pressure cuffs, bed monitors, infusion pumps, and other monitoring devices, tracking staff with proper PPE, and monitoring COVID-19 inventory and patients [9]. Leveraging the eMBB pillar of 5G, COVID-19 treatment-supporting doctors and nurses around the globe can share results, perform rural telemedicine, and leverage augmented and virtual reality experiences to manage COVID-19 patients, all without risking infection.…”

Counter a Drone and the Performance Analysis of Deep Reinforcement Learning Method and Human Pilot

“…Recently, researchers have proposed some studies about autonomous drones in the area of deep reinforcement learning (DRL). Anwar et al [1] studied the DRL for autonomous navigation. Transfer learning is applied to reduce the training computation load.…”