It is not easy to develop and deploy machine learning models, and even less so to integrate them with the surrounding data pipelines to build large-scale ML systems. The hardest part, however, comes later, when the entire system has been tested, deployed, and is up and running. For deployment is by no means the end of the journey. Much to the contrary, this is when a new challenge starts: maintenance. Maintenance costs of machine learning systems, by which I mean the time engineers use to keep the systems alive and unflawed, may become exorbitant in some cases.

The Dynamic Pickup and Delivery Problem (DPDP) is aimed at dynamically scheduling vehicles among multiple sites in order to minimize the cost when delivery orders are not known a priori. Although DPDP plays an important role in modern logistics and supply chain management, state-of-the-art DPDP algorithms are still limited on their solution quality and efficiency. In practice, they fail to provide a scalable solution as the numbers of vehicles and sites become large. In this paper, we propose a data-driven approach, Spatial-Temporal Aided Double Deep Graph Network (ST-DDGN), to solve industry-scale DPDP. In our method, the delivery demands are first forecast using spatial-temporal prediction method, which guides the neural network to perceive spatial-temporal distribution of delivery demand when dispatching vehicles. Besides, the relationships of individuals such as vehicles are modelled by establishing a graph-based value function. ST-DDGN incorporates attention-based graph embedding with Double DQN (DDQN). As such, it can make the inference across vehicles more efficiently compared with traditional methods. Our method is entirely data driven and thus adaptive, i.e., the relational representation of adjacent vehicles can be learned and corrected by ST-DDGN from data periodically. We have conducted extensive experiments over real-world data to evaluate our solution. The results show that ST-DDGN reduces 11.27% number of the used vehicles and decreases 13.12% total transportation cost on average over the strong baselines, including the heuristic algorithm deployed in our UAT (User Acceptance Test) environment and a variety of vanilla DRL methods. We are due to fully deploy our solution into our online logistics system and it is estimated that millions of USD logistics cost can be saved per year.

The next year will be pivotal for the Air Force's effort to acquire a new class of autonomous drones, as industry teams compete for a chance to build a fleet of robotic wingmen that will soon undergo operational experimentation. The "Skyborg" program is one of the service's top science-and-technology priorities under the "Vanguard" initiative to deliver game-changing capabilities to its warfighters. The aim is to acquire relatively inexpensive, attritable unmanned aircraft that can leverage artificial intelligence and accompany manned fighter jets into battle. "I expect that we will do sorties where a set number are expected to fly with the manned systems, and we'll have crazy new [concepts of operation] for how they'll be used," Assistant Secretary of the Air Force for Acquisition, Technology and Logistics Will Roper said during an online event hosted by the Mitchell Institute for Aerospace Studies. The platforms might even be called upon to conduct kamikaze missions.

If you own an Alexa-powered device, there's now even less of a chance that you'll go hungry. Amazon has given its Alexa voice assistant the ability to place food delivery orders from businesses affiliated with Amazon Restaurants. To expedite the service, Alexa will only be able to re-order from a restaurant or type of cuisine you've ordered from in the past. This is the latest perk being offered to Amazon Prime members who own an Alexa-powered device like an Amazon Tap, Amazon Echo, or Echo Dot. Alexa is able to place restaurant delivery orders for Prime members in over 20 cities, as part of Prime Now, the Amazon service that offers same-day delivery.