Deep learning (DL) has proven to be an effective machine learning and computer vision technique. DL-based image segmentation, object recognition and classification will aid many in-situ Mars rover tasks such as path planning and artifact recognition/extraction. However, most of the Deep Neural Network (DNN) architectures are so complex that they are considered a 'black box‘. In this paper, we used integrated gradients to describe the attributions of each neuron to the output classes. It provides a set of explainability tools (ET) that opens the black box of a DNN so that the individual contribution of neurons to category classification can be ranked and visualized. The neurons in each dense layer are mapped and ranked by measuring expected contribution of a neuron to a class vote given a true image label. The importance of neurons is prioritized according to their correct or incorrect contribution to the output classes and suppression or bolstering of incorrect classes, weighted by the size of each class. ET provides an interface to prune the network to enhance high-rank neurons and remove low-performing neurons. ET technology will make DNNs smaller and more efficient for implementation in small embedded systems. It also leads to more explainable and testable DNNs that can make systems easier for Validation & Verification. The goal of ET technology is to enable the adoption of DL in future in-situ planetary exploration missions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Explainability Tools Enabling Deep Learning in Future In-Situ Real-Time Planetary Explorations


    Contributors:


    Publication date :

    2022-03-05


    Size :

    4301632 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Aerobot Design for Planetary Explorations

    Garg, Kanika / Emami, M. Reza | AIAA | 2016


    Tensegrity Lander Architecture for Planetary Explorations

    Saha, Dipanjan / Goyal, Raman / Skelton, Robert E. | TIBKAT | 2021


    Future science goals of in situ Lunar explorations

    Massironi, Matteo / Ferrari, Sabrina | IEEE | 2019


    Explainability of Deep Reinforcement Learning Method with Drones

    Cetin, Ender / Barrado, Cristina / Pastor, Enric | IEEE | 2023


    Enabling Autonomy with a Deep Learning Framework for Planetary Exploration

    Macdonald, Andrew J. / Budhkar, Apeksha / Bonham-Carter, Becca et al. | AIAA | 2022