This work presents the experiments and solution outline for our teams winning submission in the Learn To Race Autonomous Racing Virtual Challenge 2022 hosted by AIcrowd. The objective of the Learn-to-Race competition is to push the boundary of autonomous technology, with a focus on achieving the safety benefits of autonomous driving. In the description the competition is framed as a reinforcement learning (RL) challenge. We focused our initial efforts on implementation of Soft Actor Critic (SAC) variants. Our goal was to learn non-trivial control of the race car exclusively from visual and geometric features, directly mapping pixels to control actions. We made suitable modifications to the default reward policy aiming to promote smooth steering and acceleration control. The framework for the competition provided real time simulation, meaning a single episode (learning experience) is measured in minutes. Instead of pursuing parallelisation of episodes we opted to explore a more traditional approach in which the visual perception was processed (via learned operators) and fed into rule-based controllers. Such a system, while not as academically "attractive" as a pixels-to-actions approach, results in a system that requires less training, is more explainable, generalises better and is easily tuned and ultimately out-performed all other agents in the competition by a large margin.

Amazon is reportedly using artificial intelligence (AI) to determine how much its delivery drivers should be paid by and their employment status. According to The Information, which first reported the news, the AI-powered surveillance cameras in delivery trucks are monitoring the driver's behavior and scoring them on safety infractions like tailgating, speeding or illegal U-turns. The news outlet says it obtained confidential documents that reveal cameras inside vans count the number of potentially dangerous actions – most equal one point, but others like running a stop sign are worth 10 points. The documents also states that contracted drives receive a report card each week, showing their performance that ranges from'fantastic' to'poor' that shows how many infractions occurred for every 100 trips. Those with five or fewer violations per 100 trips usually receive a'fantastic' score, according to The Information. The Amazon documents also states that the firm will remove some infractions to balance to account for'edge cases' where the cameras' AI software misidentifies violations.