Unmanned excavation could soon be a reality

Researchers from Baidu Research Robotics and Auto-Driving Lab (RAL) and the University of Maryland, College Park, claimed to have successfully developed an autonomous excavator system (AES)  that can perform material loading tasks for a long duration without any human intervention.

The team of experts added the system was able to produce results closely equivalent to that of an experienced human operator.

If deployed across the globe, the system will be able to solve issues relating to skills shortages within the construction industry, in addition to providing a safe solution to materials handling work in hazardous environments such as in waste disposal or demolition sites, the team said.

"This work presents an efficient, robust, and general autonomous system architecture that enables excavators of various sizes to perform material loading tasks in the real world autonomously," said Head of Baidu Research Robotics and Auto-Driving Lab, Dr. Liangjun Zhang.

Researchers identified a number of factors that needed to be considered and implemented on a robotic excavator in order for it to function as desired, including the ability to identify target materials, avoid obstacles, handle uncontrollable environments, and continue running under difficult weather conditions.

The resulting product, the AES, involves the use of multiple sensors – including LiDAR, cameras, and proprioceptive sensors –to perceive the 3D environment and identify target materials, and is equipped with advanced algorithms such as a dedusting neural network to generate clean images.

With this modular design, the AES architecture can be effectively utilised by excavators of all sizes – from 6.5-tonne compact excavators all the way up to 49-tonne large excavators to handle a wide range of applications, the researchers said.

To evaluate the efficiency and robustness of AES, researchers teamed up with a leading equipment manufacturing company to deploy the system at a waste disposal site - a toxic and harmful real-world scenario where automation is in strong demand.

Researchers found the AES was able to continuously operate for more than 24 hours without any human intervention.

The team also tested the AES in winter weather conditions, where vaporisation can affect the sensing performance of LiDAR. The amount of materials excavated, in both wet and dry form, was 67.1 cubic meters per hour for a compact excavator, which is in line with the performance of a traditional human operator, Dr. Zhang said.

"AES performs consistently and reliably over a long time, while the performance of human operators can be uncertain," he said.

Researchers also set up ten different scenarios at a closed testing field to see how the system performed in numerous real-world tasks. After testing a variety of large, medium-sized, and compact excavators, they found the AES was able to match the average efficiency of a human operator in terms of the amount of materials excavated per hour.

"This represents a key step moving towards deploying robots with long operating periods, even in uncontrolled indoor and outdoor environments," said University of Maryland’s Dr. Dinesh Manocha.

Going forward, Baidu Research RAL will continue to refine core modules of AES and further explore scenarios where extreme weather or environmental conditions may be present.

"We aim to leverage our robust and secure platform, infused with our powerful AI and cloud capabilities to transform the construction industry," said Baidu Chief Technology Officer, Dr. Haifeng Wang.

The team published its AES research paper, which includes its methodology and findings, in the Science Robotics journal on June 30, 2021.

Hadrian X robot can build house in two days

Komatsu unveils electric remote-controlled excavator concept

Homegrown tech could improve site safety and productivity