The Evolution of Artificial Intelligence in Logistics

AI in Logistics

This is the first article in a two-part series focused on the history and future of artificial intelligence in logistics.

AI in Logistics has come a long way. Who really could have imagined driverless cars, pilotless aircrafts or predictive capabilities other than from the pages of science fiction? But thanks to a whirlwind evolution of tech, AI has left the laboratory and evolved into an integral and ubiquitous part of our lives.

The industry knows it too, with Forbes Insights research showing that 65 percent of senior transportation-focused executives believe logistics, supply chain, and transportation processes are in the midst of a renaissance. Furthermore, a cross-industry study on AI adoption by McKinsey & Co. found that early adopters with a proactive AI strategy in the transportation and logistics sector enjoyed profit margins.

AI is here and it is here to stay. But how did we get here, and where are we going? Let’s dig a little deeper into AI and its evolution in the logistics sector.

AI in Logistics: From Then Until Now

AI in Logistics

Artificial Intelligence has undergone a long, winding evolution to get to this point of application in logistics. From the term’s origin more than 50 years ago by Stanford computer science professor John McCarthy, the technology has continued to grow in its scope of application. AI can be defined as making it possible for machines to learn from experience, adjust to new inputs and perform human-like tasks. It is an umbrella term, typified by a machine’s ability to sense, process and learn about the world around it.

“The data has not been properly utilized until now. Previous tracking efforts did not provide “clean” data and had been regularly stored on paper, making proper analysis more difficult. The difference today, however, is not only the presence of more data but also vastly more powerful computing and algorithms to sort, evaluate and result in action.”

This can be seen in a number of logistics applications. While trucking, rail and ocean freight have been tracked by satellite via telematics for decades, and versions of electronic driver logs have been around for nearly 20 years, the data has not been properly utilized until now. Previous tracking efforts did not provide “clean” data and had been regularly stored on paper, making proper analysis more difficult. The difference today, however, is not only the presence of more data but also vastly more powerful computing and algorithms to sort, evaluate and result in action.

For instance, as signaled in its report on AI, DHL notes that it has “developed a machine learning-based tool to predict air freight transit time delays in order to enable proactive mitigation. By analyzing 58 different parameters of internal data, the machine learning model is able to predict if the average daily transit time for a given lane is expected to rise or fall up to a week in advance.” Better algorithms and data crunching enables AI to identify inefficiencies and move cargo around the world faster than ever.

Three driving trends are paving the way for AI’s current boom: cheaper, better computing power, the ever-increasing usability of Big Data, and improved algorithms. These forces continue to culminate in more powerful AI applications, providing present and future applications which intrinsically alter what is possible in logistics. Much like the agricultural revolution, the digital revolution is impacting many different aspects of modern life – and logistics is one of the industries primed for disruption. It is beginning its journey to become an AI-driven industry – but the future remains rife with challenges to overcome and opportunities to realize.

The Current Status Quo

Let’s break down the impact of AI thus far, starting with data management and capabilities. Elements of AI are now regularly used for predictive analytics in relation to intelligent transportation and route planning, demand planning and others. Some warehouse operations are also being integrated with augmented guidance and robotic systems to accelerate inventory management. Amazon and Ocado are a couple of the first movers in this area, and there is no doubt this will expand in the coming years.

AI in Logistics

Picture Credit: IBM

Big Data means collected information can finally be used in actionable ways. Harnessing all the data from the supply chain, analyzing it, identifying patterns and providing insight to every link of the supply chain are true steps forward. According to DHL’s report, “one of the most underutilized assets in the industry is the high volume of data that supply chains generate on a daily basis. This data is both structured and unstructured, and AI will enable logistics companies to exploit it.”

This goes back to improved network management. For example, AI can help to fill out any company’s incomplete shipment data. An algorithm has the ability to unlock 5 or 10 percent of shipment data to create a full data set and make precise dedications. As a result, this would ultimately provide a clear understanding of how empty or full any vehicle is – an invaluable resource in logistics.

AI in Logistics

Picture Credit: Fizyr/PostNL

Computer vision will no doubt continue to improve over the coming years. Computer vision-based AI is allowing us to see things in new ways: including the supply chain. According to logistics giant DHL, visual inspection powered by AI is identifying “damage, classifying the damage type, and determining the appropriate corrective action” faster than ever before.” A good example of this is from retail giant Amazon, who utilize computer vision systems which can help to unload a trailer of inventory in only 30 minutes compared to hours without using such systems. Or perhaps the startup Fizyr: who have developed the world’s best-trained machine learning algorithms to enable robots to handle any pile of various items or fully unknown parcels using machine vision.

Logistics companies are also making great strides with autonomous vehicles. Never before has AI been so affordable and accessible, and industry giants are starting to leverage the technology into their transportation. Google and Mercedes Benz are investing heavily in the concept of autonomous vehicles, it is only a matter of time before autonomous trucks are seen on roads around the world. Moreover, autonomous vehicles are also primed to make a splash within the warehouse by assisting the human employees with picking, sorting and moving goods.

Such AI-derived upgrades improve not only efficiencies but also company bottom lines. According to analysis from the World Economic Forum, by 2025, the digital transformation of the logistics industry could bring $1.5 trillion of value to logistics players, plus an additional $2.4 trillion worth of benefits to society through reduced emissions, less traffic congestion and better prices – and the truth is this is only the beginning.

While the above concepts are already impressive steps forward in terms of technology, the future of AI in logistics looks brighter – and stranger- than ever. Airborne fulfillment centers, self-learning systems and experimental delivery methods are on the horizon – begging the question: how far is too far in the weird and wonderful world of AI in logistics?

To learn more about the future of AI in logistics, please see the second article in the series which will be published soon.

You might also like