.png)
Leopard
Leopard is a cutting-edge Data Processing Unit (DPU) designed for Micro and Mini Satellites in a compact PC-104 form factor, offering powerful on-board data analysis using Artificial Intelligence.
Specification
- Independent Supervisor (control, telemetry, software updates, FDIR)
- 1-2 Processing node with Zynq SoC
AMD Zynq UltraScale+ ZU6EG | ZU9EG | ZU15EG
• Quad ARM Cortex-A53 CPU 1.2 GHz
• Dual ARM Cortex-R5 in lock-step
• FPGA for custom function implementation
• 16 GiB DDR4 (with ECC)
• 4 GiB SLC flash-based file system storage (with EDAC)
• 2 x 240 GiB pSLC flash-based mass data storage
• Supervisor control I/F (TMTC): CAN bus
• PL-connected LVDS and GPIOs
• QuadGTH transceivers
• Supply voltage: 7 to 14 V
• Power consumption: 7.5 W to 20 W - depending on workload and specified processing speed
• 64-bit Linux
• Fully reconfigurable in orbit
• Compatible with Vitis AI Deep learning accelerator
Possibility to introduce additional redundancy to each version
PC-104
Advantages
High-Performance Processing
Up to 3 Tera Operations Per Second (TOPS) for fast and efficient data processing.
AI-Driven
Utilizes deep learning algorithms directly in space, reducing the need and costs of data transfers to Earth.
Compact Design
CubeSat-compatible (<1U) with the ability to integrate seamlessly with various Micro and Mini satellite platforms.
Key applications
Image Segmentation and Detection
Processes images on-board for real-time detection of changes in landscapes or urban areas, suitable for Earth observation.
Signal Enhancement
Enhances signal quality on-board, ensuring reliable, high-quality data transmission for communication satellites and remote sensing.
Data Compression and Encryption
Performs on-board data compression and encryption, speeding up secure data transfers and reducing bandwidth usage.
Compatibility
Leopard DPU is compatible with the HyperScape100 hyperspectral camera by Simera Sense, enabling real-time onboard data processing, reduced data downlink, and faster access to actionable insights directly in orbit.
Use cases
John Doe
CEO, XYZ Corp
Jane Smith
CTO, ABC Inc
Mike Johnson
COO, DEF Corp
Sarah Williams
CFO, GHI Inc
Intuition-1
- The Intuition-1 mission demonstrates advanced onboard processing capabilities through a 6U satellite equipped with a 192-band hyperspectral sensor and Leopard Data Processing Unit, launched in November 2023.
- The satellite successfully implements AI-driven image processing in orbit, achieving 3 TOPS processing speed while reducing data transmission through intelligent filtering of cloud-covered images.
- The ongoing mission validates KP Labs' innovative approach to onboard data processing, enabling real-time analysis of environmental conditions through advanced AI capabilities.
LeopardISS - IGNIS mission
- The LeopardISS experiment will launch to ISS as part of Poland's IGNIS mission, featuring astronaut Sławosz Uznański's direct involvement with the system in 2025.
- The project enables validation of advanced AI algorithms in space conditions, starting with PUT's 3D mapping research for future planetary exploration.
- Through international collaboration, the platform provides opportunities for researchers worldwide to test and validate their AI technologies in actual space conditions.
Would you like to try it out?
A Smart Mission Lab is a remote testing environment that provides users with access to real satellite hardware, allowing them to evaluate and test it before making a purchase.
Let's talk
Contact us for any inquiries or collaboration opportunities—our team is here to assist you.
