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


Submitted to Image and Vision Computing


This paper proposes a strategy for visual perception in the context of autonomous driving. Humans, when not distracted or drunk, are still the best drivers you can currently nd. For this reason we take inspiration from two theoretical ideas about the human mind and its neural organization. The rst 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 aairs 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 articial counterparts of the aforementioned neurocognitive theories. We nd a correspondence between the rst 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 specic 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: cars and lanes. We prove the eciency of our proposed perceptual representations on the SYNTHIA dataset.



This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 731593.