A Smarter Way to Handle and Move Materials

Intelligent software and robotics will be the differentiator in the logistics industry.

Artificial intelligence (AI) has inspired filmmakers for years. From Fritz Lang to Stanley Kubrick to Steven Spielberg, storytellers have entertained us with tales of intelligent machines.

Science-fiction fantasies have turned into reality—almost. Intelligent machines are part of everyday life from voice-activated speakers to smart thermostats. AI is here now and it’s time for the logistics industry to be inspired, adopt the technology in their global supply chains and explore the possibilities for the future.

Applications range far beyond driverless cars and trucks, the area that has most captured the public’s attention. In fact, though, companies are using AI to improve ways they manage inventory, predict pricing and streamline operations. In a joint report, DHL and IBM evaluated some of the AI applications available today and how it could transform the industry.

AI stands to make the biggest impact on logistics operations that involve manual labor and repetitive tasks. The warehouse is a complex web of interdependent parts. AI-enabled technology will help enable the next wave of process efficiency gains.

Autonomous guided vehicles (AGVs) are already starting to play a bigger role in logistics operations. Within any given logistics operation, it is typical to see multiple people operating material handling equipment such as forklifts, pallet jacks, wheeled totes, and even tugging cars to move goods between locations or vessels. To reduce this, companies today are beginning to use non-industrial, collaborative robotics, including AGVs.

GreyOrange, a Singapore-based robotics and automation company, makes use of AI to allow real-time collaboration between AGVs, enabling optimized navigation path planning, zoning and speeds, as well as self-learning to improve AGV capabilities over time. When given orders to fulfill, the AGVs and the platform are aware of each item that is being transported and the routes that are taken to retrieve and deliver these items.

The Finnish company ZenRobotics has developed a robotic system that uses a combination of computer vision and machine learning algorithms to sort and pick recyclables from moving conveyor belts. Similar sorting capabilities could be applied to parcel and letter-sized shipments.

Other potential areas for AI in warehouse operations include visual inspection of inventory and logistics assets and autonomous fleets. Using cameras along train tracks, IBM Watson was recently able to successfully identify damage on freight cars, classify the damage type and determine the corrective action to make repairs.

Platoons, Pricing and Predictions

DHL will pilot a project next year in Great Britain involving vehicle-to-vehicle communications technology and collaborative assisted cruise control. With this technology, between two to five trucks will be able to follow each other and automatically synchronize acceleration, steering, braking and following distance. The caravan is controlled by a driver operating the lead truck, with a backup driver in each following truck if needed. This is known as platooning.

AI also holds promise to streamline data-driven internal functions, such as accounting, finance, human resources, legal and information technology. Logistics service providers often rely on vast numbers of third parties, including common carriers, subcontracted staff and charter airlines for core functions. That means processing millions of invoices annually.

AI technologies such as natural language processing and data extraction can turn unstructured documents into highly structured data. AI-powered software is available to process lengthy contracts in a fraction of the time that it would take a human to review them and to keep contact information up to date. AI can also offer solutions to the highly complex customs declaration process.

Price prediction is one of the biggest challenges for freight brokers. Pricing varies seasonally, by day of the week, time of day and route. Using reams of historical data, computer models have been built to resemble those built by electronic traders on Wall Street. These models evaluate historical pricing along with current variables, such as weather and traffic, to come up with a quote.

The pricing model is a good example of how AI can help the logistics industry shift its operating model from being reactive to proactive with predictive intelligence. DHL has developed a tool to predict air freight shipment delays. By analyzing 58 characteristics, the tool can anticipate if the average daily transit time for a given route is expected to rise or fall up to a week in advance.

The Holy Grail of Data Analytics

The holy grail of data analytics is to predict significant fluctuations in global shipment volumes before they occur. The need for such insight was brought to light in last year’s fidget spinner fad. The three-paddle shaped spinning toy suddenly and unexpectedly sold an estimated 50 million units in a period of several months. In the U.S., fidget spinners quickly shot up to 20% of all retail toy sales in this period. This inundated air freight and express networks with shipment volumes, as toy merchants rejected the normal lead times associated with ocean shipment of manufactured goods.

As machines get smarter, technology is going to be the differentiator in the logistics industry. All too often with new technologies, though, individuals, teams and organizations fall in love with shiny, new things and promised capabilities. Instead, it is useful to ask: What are the business problems that can be solved using AI? Does this problem demand an AI solution?

Some of things you’re going to try may not produce value. Be willing to experiment and fail. Dream big and AI could help unlock tremendous value.











Leave a Reply