Lucas Systems Algorithmic Planning Partnership Targets Smarter Warehouse Decisions

Lucas Systems has partnered with Carnegie Mellon University (CMU) to advance algorithmic planning for warehouse operations, using data science and predictive modelling to help supervisors make more informed decisions about workforce deployment and task management.

Announced on October 21, 2026, the collaboration builds on work involving master’s students in CMU’s Master of Science in Applied Data Science programme. The students analysed hundreds of data attributes related to warehouse users and their behaviour, developing prediction models intended to support more effective operational planning.

The research addresses a challenge facing distribution centres: although warehouses generate extensive operational data, managers may still rely heavily on experience and manual judgement when deciding how to allocate labour, prioritise tasks and respond to changing workloads.

Lucas Systems aims to translate the research into practical software capabilities that help warehouse supervisors identify useful signals in operational data and make decisions with greater confidence.

Lucas Systems Algorithmic Planning Uses Data to Improve Workforce Decisions

Warehouse operations involve a continuous stream of decisions about which tasks should be completed, which workers should perform them and how available resources should be allocated. These decisions can influence productivity, order fulfilment times and operating costs.

The challenge becomes more complex when order volumes fluctuate, priorities change or the availability of workers and equipment shifts during a working day. Managers may have access to data from warehouse management systems and operational software, but extracting actionable insights from that information is not always straightforward.

Lucas Systems and CMU are exploring how predictive models can help bridge this gap. By studying patterns in warehouse data and worker behaviour, the research seeks to identify relationships that could support better planning decisions.

Rather than relying solely on fixed rules or historical averages, algorithmic approaches can help systems evaluate multiple variables and identify patterns that may otherwise be difficult to detect manually.

The objective is to support supervisors with more relevant recommendations when planning work, while allowing them to apply their operational knowledge and judgement to the final decisions.

Lucas Systems Algorithmic Planning Builds on Carnegie Mellon Research

The collaboration involved students from Carnegie Mellon University’s Master of Science in Applied Data Science programme during the spring 2026 cohort. Their work focused on analysing hundreds of attributes associated with warehouse users and behaviours to develop predictive models.

Lucas Systems’ research and software engineering teams worked with the students on the mathematical and analytical challenges involved in the project. The company says the work has established a foundation for further development of its planning capabilities.

Industry-academic collaborations can give students access to complex operational problems and real-world datasets, while allowing companies to explore approaches that may be difficult to develop through internal teams alone.

In this case, the research connects applied data science with warehouse management, a field where decisions must account for multiple interacting factors. A model that identifies a useful pattern in historical data must still be evaluated to determine whether it improves decisions under real operating conditions.

The next stage will involve translating the research into practical capabilities that can be incorporated into warehouse software and used by supervisors during day-to-day operations.

Lucas Systems Algorithmic Planning Addresses the Warehouse Data Challenge

Modern distribution centres generate information across orders, inventory, worker activity, equipment usage and task completion. Yet more data does not automatically lead to better decisions.

Warehouse supervisors need to determine which information matters at a particular moment and how it should influence priorities. Reviewing large volumes of records manually can be time-consuming, particularly when operational conditions change quickly.

Algorithmic planning aims to turn these data points into more structured decision support. Predictive models can help estimate likely outcomes, identify patterns in activity and inform how tasks might be organised.

For example, a warehouse may need to decide how to assign work when several orders require urgent fulfilment while labour availability is limited. A planning system that considers multiple variables could help supervisors evaluate alternatives more systematically.

These are potential applications of the approach, rather than confirmed outcomes from the newly announced research. The value of the models will depend on their accuracy, the quality of the data and how effectively their recommendations fit actual warehouse workflows.

Lucas Systems Algorithmic Planning Connects Research With Warehouse Software

Lucas Systems develops software for warehouse and distribution centre operations, using data, artificial intelligence, machine learning and optimisation models to support productivity and operational agility.

Its existing software capabilities include tools for improving order batching, task prioritisation, worker travel and inventory slotting. The company has also developed optimisation technologies designed to help warehouses respond to changes in demand, priorities and resource availability.

The CMU collaboration complements this broader focus on making warehouse operations more responsive. Better prediction and planning could help inform decisions about how work is organised, while existing optimisation tools can translate operational constraints into recommendations for execution.

The distinction between research and deployment remains important. The announcement describes the predictive models developed through the student project as a foundation for further development; it does not establish that every resulting capability is already available commercially.

Integrating new algorithms into production software also requires testing, validation and consideration of how recommendations affect workers and operational performance.

Lucas Systems Algorithmic Planning Reflects a Shift Towards Data-Driven Warehouses

Distribution centres are under pressure to fulfil orders efficiently while managing labour availability, fluctuating demand and increasingly complex supply chains. These pressures have increased interest in software that can help operators make decisions using real-time and historical information.

Algorithmic planning offers one way to address that challenge, particularly when it complements rather than replaces the experience of warehouse supervisors. Data-driven recommendations can provide additional context, but human oversight remains important when unexpected events or practical constraints require a different response.

For Lucas Systems, the partnership with Carnegie Mellon provides an opportunity to advance the analytical foundations behind its warehouse software. For the university, the project gives students experience applying data science to a complex industrial problem.

The next measure of progress will be whether the research can be translated into dependable planning capabilities that improve operational decisions at scale. If successful, the work could help warehouses make more productive use of the data they already collect, moving beyond information visibility towards more actionable decision support.