Transportation & Logistics
Case Studies
Newsfor Transportation & Logistics
A global transport provider gains a significant competitive advantage by implementing AI for supply chain visibility
Hong Kong-based Gravity Supply Chain is utilising artificial intelligence (AI) and big data to bring e-commerce-style supply chain visibility to international freight.
Linked use case: Optimise supply chain
ARUP saves 790 engineering hours using machine learning to detect utility clash points planning a light rail system for Auckland
Arup, in a joint venture with Jacobs, was selected to plan a new light rail system for the city of Auckland. The assessment of utility systems clashing at different locations along the proposed rail line was automated using supervised learning algorithms, reducing the amount of engineering time which would have been required for manual checks by 790 hours.
Linked use case: Collate and evaluate site data for architectural planning
AeroMexico''s customer-service can handle as many inquiries as two full-time employees per day through its chatbot
Aeromexico has introduced aerobot, a chatbot that handles customer service queries. Based on natural language processing, it has been trained to recognise the same questions asked differently. If it is not able to assist with a query, the chatbot redirects the client to a human attendant. The company claims that it is currently assisting 1,000 Spanish-speaking clients per day, which is roughly as many queries as two full time employees would handle, while saving costs.
Linked use case: Automate customer service conversations through a text chatbot
Airbus is investing in developing autonomous passenger aircraft
Airbus has set the goal of developing autonomous planes that operate with just one person pilot. It is working with Chinese tech and AI companies in order to make self-driving technologies found in the automotive industry applicable to airplanes. To accelerate the development of the project, which in the future would cut staffing costs down, the company has committed to setting up an innovation hub in Shenzhen, China.
Linked use case: Automate aircraft piloting
Airbus used deep machine vision to detect clouds in satellites decreasing the error rate from 11% to 3%
Airbus used convolutional neural networks to detect clouds in satellite imagery. They decreased the error rate from 11% to 3%, a 72% improvement. They used the TensorFlow ML framework and results were obtained in about a month.
Linked use case: Identify physical properties of scanned images
Avianca Airlines improves customer experience and cuts check-in waiting times in half with natural language processing
Avianca Airlines in collaboration with Accenture built Carla, a chatbot to assist customers with domestic check-in, itinerary checking, flight status updates, weather conditions, simple translations, and other useful reminders. The chatbot, which is available on Facebook Messenger, has been able to assist more than 1,000 customers as well as cut waiting times for check in in half.
Linked use case: Automate customer service conversations through a text chatbot
BlaBlaCar optimises conversion rate and improves retention with machine learning predictive analytics that integrate data from multitudes of sources
BlaBlaCar leveraged Dataiku Data Science Studio, which provides analytics solution allowing users to connect to a wide range of data to build predictive models. The company is aimed at increasing its business intelligence productivity and develop a better understanding and grasp on data lead, which led to improvement in retention and conversion rates.
Linked use case: Accelerate data integration from multiple sources
Boston Public Schools''s plan to reconfigure start times for high school students using an optimisation algorithm backfires
Boston Public Schools intended to leverage traditional AI methods of planning and analytics to reduce sleep deprivation of teenagers due to early school start times. Two MIT graduates were appointed to the task by officials, facing the trade off of minimising the number of school buses required, maximise the number of students starting school after 8am and increasing parental happiness and satisfaction. However, the proposed solution resulted in fury amongst parents as the updated schedule would affect middle and elementary students'' start times as well. Although BPS aimed to reduce inequities, with almost 85 percent of the district getting new start times, many black and brown families would be negatively affected. The proposed change by the algorithm was not implemented.
Linked use case: Optimise driver or pilot choices and path routing to reduce length, cost or environmental impact of trip
CMA CGM enhances its cargo ships piloting and collision avoidance techniques through real time object detection
CMA CGM has collaborated with Shone to deploy an AI-powered system designed to aid crew members, support operations and optimise situational awareness and navigation. Bridge navigation sensors and installed cameras feed the system with data which it then analyses to avoid collisions and automate piloting. The startup uses machine learning to for detecting objects in real time.
Linked use case: Identify and navigate roads and obstructions in real time for autonomous driving
CargoMetrics analyses satellite shipping imagery and plans to to identify investment opportunities based on the data with machine learning
CargoMetrics is an investment firm which uses satellite imagery to collect shipping data and is analyzed using proprietary algorithms in combination with other data to make commodities, equity index futures, and currencies trading decisions. It is building a machine learning system to identify investment decisions based on its various data sources.
Linked use case: Predict asset price movements based on greater quantities of data to inform trading strategies
Chronopost International ensures on-time deliveries during peak activity with machine learning predictive analytics
Chronopost can ensure on-time deliveries during peak activity with ease of delivery rating for all addresses based on parcel tracking and geographical data provided by Dataiku DSS. The custom solution implemented analyses historical internal delivery and retrieval data using a machine learning interface. The company has increased business intelligence productivity and optimised package delivery operational costs .
Linked use case: Optimise quality of service and product delivery
Copa Airlines enhances online customer experience through a chatbot travel agent
Copa Airlines is offering a virtual travel agent, Ana, which is able to respond to customers'' queries, such as destinations or baggage allowances. The chatbot responds within a customer''s browser using natural language processing and supports English and Spanish.
Linked use case: Enable enhanced retail customer experience and service through chatbots
Coyote improves the accurate reporting of speed limits by 9% using machine learning
Coyote provides real time information on traffic hazards, road conditions and speed limits. In order to maintain an accurate reporting of driving speed limits within their embedded maps, the company implemented Dataiku''s machine learning solution. By leveraging predictive algorithms the company was able to detect speed limit anomalies which led to a 9% increase in speed limit reliability and the automation of its correction process.
Linked use case: Automate data cleansing and validation
DARPA simulates flight and landing of Boeing 737 by an AI-driven robot co-pilot
DARPA has announced the successful simulated flight and landing of a Boeing 737 by an AI-driven robot co-pilot named ALIAS, which is an acronym for Aircrew Labor In-Cockpit Automation System. The system was build by Aurora Flight Sciences and consists of cameras, machine learning technology and a robotic arm capable of operating all of the cockpit’s controls.
Linked use case: Automate aircraft piloting
Deutsche Bahn reduces maintenance cost by 25% and delay-causing failures using machine learning
Deutsche Bahn leverages smart sensor and advanced machine learning analytics from Konux to reduce maintenance costs and avoid infrastructure failure. With predictive maintenance, the rail network company has achieved a cost reduction of 25%, through minimisation of downtime and maximisation of performance.
Linked use case: Optimise maintenance scheduling
Didi to tackle traffic congestion and optimise navigation routes with deep learning
Didi has leveraged artificial intelligence to develop a city traffic management system. The company, whose AI research labs are working on deep learning, natural language processing and machine vision, has launched the Smart Transportation Brain to combine video and sensor data from its vehicles and the government for traffic congestion and navigation optimisation. The company aims to facilitate the development of smart traffic lights and monitoring systems to alleviate road congestion.
Linked use case: Predict likelihood of traffic accidents or queues and optimise traffic system to reduce the risk
Eco Marine Power unveils automated control and monitoring systems for ships
Eco Marine Power (EMP) plans to implement an automated control and monitoring system. By integrating three marine computer systems, the platform will enable the company to more easily control all elements of Aquarius Marine Renewable Energy (MRE).
Linked use case: Optimise supply chain including logistics, procurement timing and inventory distribution across warehouses and stores
FLL monitors aircraft movement and gets accurate status reports for gates with machine vision and natural language processing
Fort Lauderdale Hollywood International Airport (FLL) has leveraged Aimee, the Searidge AI platform. The solution is using advanced object detection and recognition artificial neural network technology which makes it capable of detecting aircraft movement. The system analyses real time video footage, offering FLL staff accurate gate status updates for almost all gates.
Linked use case: Augment traffic control processes at (air)ports
Facebook create new location address schemes for developing areas decreasing travel times by 22% in tests
Facebook researchers develop a model of predicting roadways and other human infrastructure from satellite images in order to create an accurate addressing system, particularly for areas where no consistent system exists. The goal is to aid developing countries and improve direction accuracy to help disaster relief. The automatic addressing system covers more than 80% of populated areas.
Linked use case: Create maps from satellite and other remote imagery
GE achieves speed and accuracy in detecting track flaws in real time with machine learning
General Electric (GE) has equipped its freight locomotives with sensors, such as cameras that capture footage of the track and the cab and feed it to machine learning analytic software which is able to process it in real time and determine whether there is a danger. In this way the company has achieved gains in speed and accuracy of detecting things on or around the track and has improved the efficiency of its rail transport solutions.
Linked use case: Monitor and predict problems on rail network
Halvor Lines increases driver performance by 100% over previous systems using machine learning evaluation system
Halvor Lines transport and logistics has piloted a driver performance detection system which uses cameras to evaluate both risky and good driving events. The feedback is automatically sent to managers and drivers are warned or rewarded as events happen. In the pilot driver performance improved a purported 100% over using legacy video systems.
Linked use case: Identify performance and risk for employee drivers through driving patterns and other data
Heathrow Airport tackles delays due to bad weather with the use of AI
Heathrow airport is trialling a system of 20 ultra-high-definition cameras and an AI system to provide air traffic controllers information on runways when there is bad weather. Controllers are sometimes not able to get that information when there are low clouds, causing delays. By analysing 50,000 inbound flights, the system is aimed to alleviate delays and speed up runway control processes.
Linked use case: Monitor transport fleet networks in real time to ensure safety of passengers and drivers
Heathrow aims at tackling gender bias in job listings using natural language processing
Heathrow has implemented Textio, a software that uses natural language processing to identify words and language patterns attracting a diverse pool of job candidates. The airport aims at tackling gender bias issues by using inclusive language in its job adverts.
Linked use case: Optimise job listing to attract more diverse candidates
IUT Annecy aims to beat the current record for the fastest bicycle travelling across flat road by creating the optimal aerodynamic design using machine learning
A team from IUT Annecy has leveraged machine learning technology from Neural Concept, an EPFL startup, to develop a bike with the optimal aerodynamic shape. Based on 3-D shapes that consist of collections of points a convolutional neural network has been trained to identify each shape''s aerodynamic properties. The final product will be demonstrated at the World Human Powered Speed Challenge in September 2018, where the team hopes it will break the world speed record.
Linked use case: Create new products
International Airlines Group enhances in-flight customer experience with AI
International Airlines Group has leveraged Black Swan Analytics'' technology to offer their passengers a better in-flight costumer experience. Black Swan Analytics are providing IAG''s lowcost airline, LEVEL, an integrated system to assist on-board operations. The system offers personalised service to customer as it learns their preferences with the use of AI.