Any logistics system is driven by two fundamental entities – trucks and drivers.
A driver drives the truck for long distances going through two states of motion. First, when the truck is in movement while being driven by the driver and second, the stationary state when the driver rests or stops at state borders for state permit/transit checks and at tolls. A lot of time is also spent at customer warehouses for loading and unloading.
Similarly, a truck itself, as an independent entity, can go through various phases. There are phases where it is attached to a driver and copies all the properties of the driver or when it is parked without a driver for maintenance or other activities.
In efficient logistics operations, the trucks and drivers need to be optimally utilised. Every minute of their time is precious. For example, if a seat on a flight is not booked, it would be considered unutilised. It implies that the airline missed an opportunity to generate extra revenue without incurring any extra cost. The same applies to logistics too.
The question, therefore, is, how do you optimally utilise both drivers and trucks? If you think deeper, the answer to this question leads to another important question. What do you know about the historical state of trucks and drivers’ behaviour that would enable you to optimise them efficiently? Because without this information, deducing an answer is almost impossible. Moreover, the driver relay model adds an extra layer of complexity as the drivers and trucks are not married and allocation keeps on changing every few hundred kilometres or so.
We are solving this tough problem by mapping every behaviour of trucks and drivers using the power of data. Using IoT sensors, or as we call them, IoMTs (Internet of Moving Things) sensors attached to trucks and GPS location data of drivers, we capture exhaustive data over time. Once this raw data is mapped on a temporal (time) axis, it leads to some very interesting observations and optimisations.
Enter the time continuum.
The continuum captures events occurring in succession, leading from the past to the present and even into the future. It understands the behaviour and maps it to intelligent events. For example, we can process geo-location data and categorise it as time spent in waiting at the border. There are several such intelligent events that are built in the continuum that are associated with driving time, turnaround time, waiting, location intelligence etc. It gives you the power to go back in time and replay all the events associated with these two fundamental entities, the driver and truck. This data is used to find optimal ways of driving trucks of different sizes, on different routes and at different times to minimise turnaround times and probabilities of accidents and maximise reliability and mileage.
For any data-driven problem, getting past a proper and sanitized source is a big win. The continuum delivers the truth. This source of truth is driving the future of intelligence and optimisation for us.