Baidu Research Robotics and Auto-Driving Lab (Baidu RAL), an AI development company, and the University of Maryland, College Park (UMD) have developed a real-time mapping approach for autonomous navigation of excavators on complex terrains. 

The company said the Terrain Traversability Mapping (TTM) can navigate through unstructured outdoor environments consisting of deep pits, steep hills, rock piles and other complex terrain features.

The researchers developed a learning-based geometric method to extract terrain features from RGB images and 3D point clouds and incorporate them into a global map for planning and navigation.

 

The method includes using physical characteristics of the excavator, such as maximum climbing degree and machine specifications, to determine the traversable area, adapt to changing environments and update the information in real-time.

Additionally, the researchers developed an autonomous excavator terrain dataset, which consists of RGB images and LiDAR point clouds from construction sites with seven different categories based on navigability.

The development is part of a wider trend in the mining industry that sees robotic systems as a way of alleviating labour shortages, especially shilled heavy machinery operators, to meet current increasing demand.

The global market for excavators was $44.12 billion in 2018 and is expected to grow to $63.14 billion by 2026.