Perceptual Attention-based Predictive Control
This work addresses safety-critical navigation for autonomous vehicles, though it appears incremental as it combines existing methods like MPC and CNNs with uncertainty quantification.
The paper tackles safe visual navigation for autonomous systems by introducing a perceptual attention-based predictive control algorithm that uses MPC to learn attention placement on visual inputs, enabling faster detection of unsafe conditions like novel obstacles. Experimental results on a 1:5 scale terrestrial vehicle show it outperforms previous methods in early detection.
In this paper, we present a novel information processing architecture for safe deep learning-based visual navigation of autonomous systems. The proposed information processing architecture is used to support a perceptual attention-based predictive control algorithm that leverages model predictive control (MPC), convolutional neural networks (CNNs), and uncertainty quantification methods. The novelty of our approach lies in using MPC to learn how to place attention on relevant areas of the visual input, which ultimately allows the system to more rapidly detect unsafe conditions. We accomplish this by using MPC to learn to select regions of interest in the input image, which are used to output control actions as well as estimates of epistemic and aleatoric uncertainty in the attention-aware visual input. We use these uncertainty estimates to quantify the safety of our network controller under the current navigation condition. The proposed architecture and algorithm is tested on a 1:5 scale terrestrial vehicle. Experimental results show that the proposed algorithm outperforms previous approaches on early detection of unsafe conditions, such as when novel obstacles are present in the navigation environment. The proposed architecture is the first step towards using deep learning-based perceptual control policies in safety-critical domains.