AI-powered robots are set to track across thousands of kilometres of baked, uneven ground reducing the danger for maintenance workers on Australia's large scale solar farms.
A successful trial by CSIRO, Australia's national science agency, repurposed autonomous robots, originally designed for the mining industry.
Without robots, the work is done on foot, bringing significant cost and safety risks.
Large-scale solar farms can produce upwards of 500 MW of electricity, enough to power over 300,000 homes.
However, maintaining high energy output requires efficient inspection and monitoring of each photovoltaic (PV) panel, along with timely repairs to the racking and supporting materials.
CSIRO has now applied cutting-edge robotic, AI and automation technology into the solar farm space for predictive maintenance, supporting more resilient and sustainable infrastructure.
The robotic system autonomously navigates solar farms in all terrains and conditions, builds precise maps to digitise site conditions, avoids hazards and uses AI to develop a holistic scene understanding.
The robots automatically detect faults across PV panels, such as dust build-up, insect nests or bird droppings, physical damage, loose nuts or bolts, hotspots in panels or electrical connectors, and wiring that needs repair.
The suite of sensors equipped on the robots include Light Detection and Ranging (LiDAR) for accurate 3D perception, RGB cameras for visual inspection, and thermal infrared cameras to identify electrical faults and hotspots.
The integration of robotics into solar operations:
- reduces the need for people to undertake long and hazardous inspections on foot
- lowers maintenance costs, improves efficiency and safety
- helps with early detection of hotspots and electrical issues to maintain panel performance, enhance stability of energy output and extend asset lifespan.
The technology also supports the creation of skilled regional jobs, shifting the focus from repetitive manual walking tasks to targeted technical work in solar farm maintenance, robotics support and data analysis.
Mr Kenrick Anderson, Senior Photovoltaic Engineer, CSIRO: "Hotspots decrease the efficiency of a PV panel over time, because of the electrical and thermal imbalance they cause within the module. If solar farms cost less to run, and can be more consistent in their energy output, this increases the stability of the grid."
Dr Peyman Moghadam, Senior Principal Research Scientist, CSIRO: "We are not just collecting images or 3D data. We are building the foundations for intelligent solar operations, where data from robots, fixed sensors and field systems can be combined. This supports better proactive maintenance decisions and more resilient performance over time. This work reflects CSIRO's broader vision for next-generation robotics and AI to safeguard and transform critical infrastructure, accelerate the energy transition and support the path to net zero."
Mr Ross Dungavell, Senior Robotics Engineer, CSIRO: "It's good to fulfil a need in areas of the country where the labour is not attainable or reliably available. Often you cannot get someone to go out there under such harsh conditions, for extended periods of time. The robot logs and stores every piece of data it captures, its sensors are able to find any fault a panel might have."
CSIRO is currently trialling the robotic and AI systems across pilot sites in Australia and aims to partner with industry to make these capabilities more broadly available and improve renewable energy reliability.
