On the Road with 16 Neurons: Mental Imagery with Bio-inspired Deep Neural Networks

by   Alice Plebe, et al.

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


Brain-Inspired Deep Imitation Learning for Autonomous Driving Systems

Autonomous driving has attracted great attention from both academics and...

ROAD: The ROad event Awareness Dataset for Autonomous Driving

Humans approach driving in a holistic fashion which entails, in particul...

Hybrid tracker based optimal path tracking system for complex road environments for autonomous driving

Path tracking system plays a key technology in autonomous driving. The s...

Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous Driving

Reinforcement learning (RL) has shown to reach super human-level perform...

CARNet: A Dynamic Autoencoder for Learning Latent Dynamics in Autonomous Driving Tasks

Autonomous driving has received a lot of attention in the automotive ind...

PyTorch-Hebbian: facilitating local learning in a deep learning framework

Recently, unsupervised local learning, based on Hebb's idea that change ...

Who Needs to Know? Minimal Knowledge for Optimal Coordination

To optimally coordinate with others in cooperative games, it is often cr...

Please sign up or login with your details

Forgot password? Click here to reset