Complex tasks and multi-use machinery will require human intervention for a long time yet, say researchers
The dream that one day fleets of high tech self-driving machines will save construction from delays and labour shortages is unlikely to come true, at least in the short term, according to the latest research.
A study of over 30 industry and technology experts, by technology consultancy Arthur D Little, found that building will lag behind other sectors in the uptake of autonomous machines due to the inherent complexity and rugged conditions of job sites.
Hundreds of off-highway vehicles already run driverless in mines, warehouses and other locations worldwide, but the complex and dynamic nature of construction sites, where machines are typically used for a limited amount of time at changing locations, make it the ‘most difficult environment for autonomous technology’.
According to the study, this will minimise the role of autonomous machines in the near future, except in niche applications such as haulage trucks.
Alexander Krug, partner at Arthur D Little told RIBAJ: ‘The autonomous “pioneer” applications of today and the close future all have similar characteristics, many of which are not fulfilled by most construction machinery. They have a high utilisation duty cycle, but construction machines are often multi-purpose and have very low utilisation. They operate in a closed-off work environment, but building sites are complex and dynamic and their machines are only used for a limited time at changing locations.’
He continued: ‘Autonomous pioneer applications require a single and simple work function, but many processes on a construction site require the exact interplay of several machines, which would require automation of the entire process.’
The degree of automation for driving and work functions in an off-highway vehicle is typically differentiated into four distinct levels. According to Krug, the vast majority of vehicles on construction sites for the next 10–15 years will be limited to Level 2 automation and still need a human operator to assist with most functions.
The term ‘autonomous machine’ only applies to Level 3 and Level 4 vehicles that do not require a local operator for most of their regular work. These machines exploit 3D-perception sensors such as LiDAR, radar, and stereo cameras, global navigation satellite system and specific sensors to monitor the custom work functions. Level 3 dump trucks are already used in mining operations and Level 4 autonomy will in future be driven by greater sensor integration and software enhancements.
Fully autonomous machines have the potential to bring numerous benefits to construction, depending on the application, such as 24/7 operation, higher productivity, reliability and predictability. They could reduce labour costs and improve safety by eliminating human error and taking people away from difficult and dangerous work environments.
Key players involved in the development of driverless construction vehicles include manufacturers like Volvo, Komatsu and Caterpillar and specialised robotic companies, for example retrofitters like ASI and Built Robotics.
Widespread uptake of the technology will not be possible, however, until the business case turns positive. According to the report, autonomous machines remain too expensive for the majority of use cases in most industries, mainly due to the cost of high-performance components and systems, including sensors, software and high-performance back end.