Autonomous driving at unsignalized intersections is still considered a challenging application for machine learning due to the complications associated with handling complex multi-agent scenarios characterized by a high degree of uncertainty. Automating the decision-making process in these safety-critical environments involves comprehending multiple levels of abstraction associated with learning robust driving behaviors to enable the vehicle to navigate efficiently. In this survey, we aim at exploring the state-of-the-art techniques implemented for decision-making applications, with a focus on algorithms that combine Reinforcement Learning (RL) and deep learning for learning traversing policies at unsignalized intersections. The reviewed schemes vary in the proposed driving scenario, in the assumptions made for the used intersection model, in the tackled challenges, and in the learning algorithms that are used. We have presented comparisons for these techniques to highlight their limitations and strengths. Based on our in-depth investigation, it can be discerned that a robust decision-making scheme for navigating real-world unsignalized intersection has yet to be developed. Along with our analysis and discussion, we recommend potential research directions encouraging the interested players to tackle the highlighted challenges. By adhering to our recommendations, decision-making architectures that are both non-overcautious and safe, yet feasible, can be trained and validated in real-world unsignalized intersections environments.

Autonomous vehicles are taking a leap forward by performing operations without human intervention through continuous monitoring of their surroundings using multiple sensors. Images gathered through vehicle mounted cameras can be large, requiring specialized storage such as cloud. However, cloud data centres can be prone to security and privacy challenges. A partial image-based, homomorphic searchable encryption scheme is proposed, which uses pixel-level encryption to identify objects within encrypted images. The scheme provides Object-Trapdoor and Trapdoor-Image indistinguishability – as the trapdoors are probabilistic. The proposed scheme is deployed on a cloud data centre and tested over a real data set. The proposed scheme reduces storage overhead by approximately 20 times, and is 33 times more efficient compared to the generic Paillier homomorphic searchable encryption scheme. Security analysis demonstrates that the scheme maintains high levels of security and privacy.