The Singapore-incorporated joint venture
targets industrial agriculture with map-free, AI-driven spraying drones.
Singapore:
DroneDash Technologies and GEODNET, the world’s largest decentralized GNSS-RTK
network, announced the formation of GEODASH Aerosystems Pte. Ltd., a joint
venture aimed at developing a new agricultural spraying drone for large-scale
farming operations. The platform combines real-time AI vision with
centimeter-level RTK positioning, allowing the system to operate without
repeated pre-mapping of fields. The company said the technology is aimed at oil
palm plantations in Southeast Asia, and sugarcane, soybean, and corn operations
in the United States and South America, with commercial deployment targeted for
Q3 2026. Beyond spraying, the platform is designed to generate canopy,
crop-stress, terrain, and spray-effectiveness data for agronomy teams.
According
to Paul Yam, CEO, DroneDash Technologies and GEODASH Aerosystems, “Agriculture
does not need bigger drones — it needs smarter ones. By removing repeated
manual pre-mapping and integrating AI Smart Farming intelligence into every
flight, we are turning spraying drones into tools that both execute operations
and inform agronomic decisions. Plantation operators can move faster while
improving consistency, efficiency, and outcomes.” According to Mike
Horton, Founder, GEODNET and Co-Founder, GEODASH Aerosystems, “When
centimetre-level RTK positioning is combined with real-time perception and
backend analytics, autonomy becomes predictable and reliable. GEODASH
Aerosystems demonstrates how precision positioning infrastructure can enable
both accurate operations and continuous data-driven agriculture management.”
According
to TechSci Research, GEODASH reflects a broader
transformation in farm mechanization, where drones are evolving from niche
equipment into continuous agronomic intelligence platforms. The real commercial
value lies not only in faster spraying but in the ability to reduce mapping
overhead, improve deployment speed, and capture actionable field data during
each mission. That is particularly relevant for plantation and broad-acre
agriculture, where field variability, terrain, and labor constraints make
conventional workflows inefficient. For the agriculture industry, this
strengthens demand for AI-enabled field operations, variable-rate application,
connectivity infrastructure, and data-management platforms that can translate
aerial intelligence into crop-action plans. It also highlights how precision
agriculture is becoming more operationally scalable in emerging and mature farm
economies alike. Companies with strength in sensors, guidance systems, aerial
analytics, and farm software are likely to benefit as deployment shifts from
pilots to commercial fleets.