Dig Robotics
Since
of increase material moved
Operating costs reduction
GHG emissions reduction
Solution Overview
for
Earthmoving is one of the most critical and costly activities in construction, mining, and quarrying, directly impacting project productivity, schedules, operating costs, and profitability.
Each cycle an earthmoving machine performs has a unique optimal path that maximizes bucket payload with no wasteful overflow while minimizing cycle time, energy consumption, and machine wear. This path includes multiple parameters such as bucket positioning, cut depth, bucket curl, breakout timing, loaded swing, dump positioning within the truck bed, and machine repositioning, among many others.
Even skilled operators struggle to consistently operate the machine along this optimal path, especially in high-intensity, dynamic applications. Research shows excavator operators can be up to 40% less efficient than the theoretical optimum, reducing the amount of material moved, extending project duration, increasing fuel consumption and machine wear, and significantly increasing operating costs.
Our Solution:
Dig Robotics optimizes each cycle by calculating the unique optimal path for each individual cycle, enabling earthmoving machines to move more material in less time and at a lower cost. For a typical large excavator, this can reduce direct operating costs by as much as $300K annually.
Our system uses computer vision and machine learning to model machine kinematics, site topography, bucket geometry, and bucket payload. Cycle data is analyzed using multidimensional graphs, allowing our AI models to identify key performance indicators and calculate the optimal path for the next cycle.
Using the same sensors and AI models, we also optimize material volume and distribution during truck loading.
Our initial product is an aftermarket operator guidance system that provides real-time feedback within the operator’s normal workflow. It can be rapidly deployed across mixed fleets and serves as the foundation for higher levels of automation in collaboration with partners such as Trimble.
How it works:
Unlike conventional machine control systems that follow predefined designs or fully autonomous solutions that require expensive hardware and highly controlled environments, Dig Robotics optimizes the unique excavation and loading cycle performed by each operator in real time.
Our innovation lies in combining computer vision, machine learning, and physics-based modeling to understand machine kinematics, site topography, bucket geometry, and material behavior, then calculating the optimal path for each individual cycle. The system continuously adapts to changing site conditions and provides real-time guidance to the operator in the flow of work, without taking control of the machine.
Classification & Use Cases
Lifecycle stage(s) addressed:
Core technology types:
Key use cases in practice:
Maturity & Traction
Stage
Customers
Regions
Main:┬а
Team
employee(s)
