On the Road with 16 Neurons: Mental Imagery with Bio-inspired Deep Neural Networks
arXiv:2003.08745 · doi:10.1109/ACCESS.2020.3028185
Abstract
This paper proposes a strategy for visual prediction in the context of autonomous driving. Humans, when not distracted or drunk, are still the best drivers you can currently find. For this reason we take inspiration from two theoretical ideas about the human mind and its neural organization. The first idea concerns how the brain uses a hierarchical structure of neuron ensembles to extract abstract concepts from visual experience and code them into compact representations. The second idea suggests that these neural perceptual representations are not neutral but functional to the prediction of the future state of affairs in the environment. Similarly, the prediction mechanism is not neutral but oriented to the current planning of a future action. We identify within the deep learning framework two artificial counterparts of the aforementioned neurocognitive theories. We find a correspondence between the first theoretical idea and the architecture of convolutional autoencoders, while we translate the second theory into a training procedure that learns compact representations which are not neutral but oriented to driving tasks, from two distinct perspectives. From a static perspective, we force groups of neural units in the compact representations to distinctly represent specific concepts crucial to the driving task. From a dynamic perspective, we encourage the compact representations to be predictive of how the current road scenario will change in the future. We successfully learn compact representations that use as few as 16 neural units for each of the two basic driving concepts we consider: car and lane. We prove the efficiency of our proposed perceptual representations on the SYNTHIA dataset. Our source code is available at https://github.com/3lis/rnn_vae
arXiv comment18 pages, 10 figures
References in corpus (19)
- Deep Learning in Neural Networks: An Overview
- Auto-Encoding Variational Bayes
- Representation Learning with Contrastive Predictive Coding
- YOLOv3: An Incremental Improvement
- End to End Learning for Self-Driving Cars
- Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Conditional Image Generation with PixelCNN Decoders
- A Survey of Deep Learning Techniques for Autonomous Driving
- Pixel Recurrent Neural Networks
- Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
- Deep Convolutional Inverse Graphics Network
- Recent Advances in Autoencoder-Based Representation Learning
- Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car
- Stacked What-Where Auto-encoders
- BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
- Learning a Driving Simulator
- End-to-End Deep Learning for Steering Autonomous Vehicles Considering Temporal Dependencies
- Self-supervised learning for autonomous vehicles perception: A conciliation between analytical and learning methods