Researchers develop autonomous excavator system that’s ‘closely equivalent’ to human performance
By Riley SimpsonJuly 07, 2021
Researchers from the University of Maryland’s Baidu Research Robotics and Auto-Driving Lab (RAL) have introduced an autonomous excavator system (AES), one of the first uncrewed projects to be deployed in real-world scenarios and continuously operating for more than 24 hours.
According to Baidu, the AES can perform material loading tasks for a long duration without any human intervention, and its performance is “closely equivalent” to an experienced human operator’s.
The researchers published their automated excavator system methodology, which could lead to industry-leading safety and productivity benefits, in Science Robotics.
“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 Dr. Liangjun Zhang, corresponding author and head of Baidu.
Excavators are vital for infrastructure construction, mining and rescue applications, Baidu said in a release, and the global market size for excavators was $44.12 billion in 2018 and is expected to grow to $63.14 billion by 2026.
Currently, the construction industry worldwide is facing a skilled labor shortage, including for heavy machinery operators, with the Covid-19 pandemic worsening the crisis over the past 16 months.
Baidu also stated that hazardous and toxic work environments, including cave-ins, ground collapses and other accidents, cause approximately 200 casualties per year in the U.S. and can have other effects on the health and safety of on-site human workers.
To combat these challenges and issues, Baidu said the construction industry is leaning into a scientific approach to create autonomous excavator systems that can provide groundbreaking solutions and grow as a trend alongside the use of other robots in manufacturing, warehouses and transportation.
“We aim to leverage our robust and secure platform, infused with our powerful AI and cloud capabilities to transform the construction industry,” said Dr. Haifeng Wang, CTO of Baidu.
Baidu designed their excavator robots to operate in an extensive range of hazardous environmental conditions and to identify target materials, avoid obstacles, handle uncontrollable environments and continue running under difficult weather conditions.
The AES uses real-time algorithms for perception, planning and control alongside a new architecture to incorporate these capabilities for autonomous operation, and the system’s modular design can be effectively utilized by excavators of all sizes, including 6.5- and 7.5-metric-ton compact excavators, 33.5-metric-ton standard excavators and 49-metric-ton large excavators.
Baidu tested its AES’ efficiency by working 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; the system was able to continuously operate for more than 24 hours without any human intervention.
The AES has also been tested in winter weather conditions, where it excavated 67.1 cubic meters per hour for a compact excavator – a performance in line with a traditional human operator, according to Baidu.
“AES performs consistently and reliably over a long time, while the performance of human operators can be uncertain,” Dr. Zhang said.
Baidu said its researchers will continue to refine core modules of AES and further explore scenarios where extreme weather or environmental conditions may be present.