ESA title

PLECO

  • ACTIVITYDemonstration Project
  • STATUSOngoing
  • THEMATIC AREAEnergy

Objectives of the service

Large-scale solar plants face continuous efficiency losses due to dust accumulation, particularly in desert and remote environments. These losses can reach significant levels, directly impacting energy production, operational costs, and return on investment. Traditional cleaning methods are labour-intensive, water-dependent, and often unsafe. 

The project delivers a fully autonomous robotic system designed to operate continuously across utility-scale solar plants. The system combines dry cleaning, inspection, and data analysis into a single integrated service that maintains panel performance while reducing operational complexity. 

Beyond cleaning, the solution introduces predictive maintenance capabilities, enabling early detection of underperforming or defective panels. This transforms maintenance from a reactive process into a proactive, data-driven approach. 

The activity demonstrates the system in real operational environments, validating both technical performance and commercial viability. It also highlights how space-enabled technologies support reliable, scalable solar operations in remote locations, contributing to the global transition towards sustainable energy. 

Users and their needs

The service targets operators of utility-scale photovoltaic plants where operational efficiency, reliability, and cost control are critical. 

Main user groups: 

  • Solar plant operators responsible for performance and maintenance 

  • EPC contractors managing large solar installations 

  • Energy producers and independent power producers 

  • Government-backed renewable energy projects 

Target regions include Europe, the Middle East, North Africa, Asia-Pacific, and Australia, where large solar installations operate under challenging environmental conditions. 

Key user needs: 

  • Maintain maximum energy output despite dust and soiling 

  • Reduce operational expenditure linked to cleaning and maintenance 

  • Improve worker safety by limiting manual intervention 

  • Operate reliably in remote areas with limited infrastructure 

  • Minimise water usage in arid regions 

  • Access clear, actionable insights on panel performance and faults 

The main challenge is delivering a solution that combines autonomy, reliability, and scalability while integrating seamlessly into existing solar plant operations.

Service/ system concept

The system combines autonomous robotic platforms with advanced sensing technologies and cloud-based analytics to deliver a complete solar maintenance solution. 

Each robot operates along solar panel rows using high-precision positioning, performing continuous dry cleaning while simultaneously collecting inspection data. The inspection system integrates thermal imaging, RGB cameras, and LiDAR to detect defects, anomalies, and performance issues. 

Collected data is processed locally on the robot, where anomalies are identified and prioritised. Only relevant data is transmitted to the cloud, optimising bandwidth usage while ensuring critical insights are retained. Cloud-based AI tools analyse this data and generate maintenance reports, enabling targeted interventions. 

The system architecture includes: 

  • Autonomous robots operating in the field 

  • Multi-source communication (4G, Wi-Fi, satellite) 

  • A central cloud platform for monitoring and analytics 

  • A user interface providing actionable insights 

From the user perspective, the system provides continuous, autonomous operation combined with remote visibility and decision support. 

Space Added Value

Space technologies are fundamental to enabling the system’s autonomy, reliability, and scalability. 

Satellite navigation (GNSS-RTK) provides centimetre-level positioning accuracy, allowing robots to navigate precisely between panel rows, repeat cleaning paths, and accurately tag detected defects. This level of precision is essential for autonomous operation in large-scale solar plants. 

Satellite communications ensure connectivity in remote environments where terrestrial networks are unreliable or unavailable. Each robot integrates multiple communication options and dynamically switches between them to maintain continuous data transmission. 

The combined use of space assets enables: 

  • Reliable operation in isolated solar farms 

  • Continuous monitoring and data transmission 

  • Scalable deployment across global markets 

  • High resilience through multi-path connectivity 

Without space-based technologies, achieving this level of autonomy and reliability in remote solar environments would not be feasible.

 

The solution contributes to increasing solar energy production efficiency by maintaining clean panels without the use of water, making it particularly suitable for arid regions. 

Key benefits:​ 

  • Reduce water consumption 

  • Increase renewable energy 

  • Reduce CO2 emissions 

  • Improve worker safety 

  • Create Skilled Jobs 

Current Status

The system is undergoing field testing in Sicily, Egypt, Luxembourg and Belgium within an operational solar plant environment. The activity has been focusing on validating autonomous navigation, dry cleaning, inspection data capture and remote monitoring under real operating conditions. ​ 

Achievements to date:  

  • Deployment of the B1A prototype on site in Sicily, Egypt, Luxembourg and in Belgium 

  • Validation of autonomous navigation and cleaning capabilities in operational conditions  

  • Testing of inspection functions, including data acquisition and processing  

  • Integration of communication systems supporting remote monitoring  

  • Definition of the SATCOM strategy 

  • Establishment of the PLECO visual identity and website​  

Current workstreams:  

  • Assessment of robustness and reliability during continuous operation  

  • Refinement of navigation and cleaning performance under site-specific constraints  

  • Collection of operational data to support optimisation  

  • Progressive integration of predictive maintenance and advanced analytics ​ 

 

Status Date

Updated: 10 November 2026