Robust LiDAR-Stereo Fusion for Lunar Autonomy

The Artemis mission requires sensing technologies and associated algorithms to enable vehicles to operate autonomously with fast cadence and high reliability. In support of fast cadence and high reliability autonomy, Quartus Engineering will develop a LIDAR-Stereo fusion system using state of the art algorithms optimized for lunar worthy computing platforms. Fusion of LiDAR and stereo image data using state of the art algorithms can enable accurate long range obstacle detection and mapping while preserving dense visual and texture information. Quartus will initially prototype and compare three fusion methods: LiDAR-guided stereo matching, depth completion and fusion techniques, and deep learning-based fusion. Quartus will leverage the NASA POLAR Stereo dataset and LunarSim to generate synthetic LiDAR-Stereo data that closely mimics lunar conditions. This simulated data will be used to evaluate different algorithmic approaches and downselect a particular fusion and stereo matching pipeline. The downselected fusion and stereo matching pipeline will be re-implemented as an optimized C++ library, with highly parallelizable portions of the algorithms factored into subroutines with support for RISC-V Vector, GPU, or FPGA accelerators. This support for hardware accelerators will be achieved through a combination of OpenCL and Microchip’s SmartHLS compiler software. Finally, Quartus will select an off the shelf RISC-V computer with comparable properties to anticipated lunar worthy RISC-V platforms and evaluate algorithm performance on this test hardware to demonstrate that desired robustness, accuracy, and latency can be achieved on a representative computing device. This work is the first step towards commercializing a LiDAR-Stereo module comprised of a LiDAR system, a stereo system, precise calibrations, and a lunar worthy compute device hosting robust, high accuracy, low latency algorithms for stereo matching and LiDAR-stereo fusion.

Our proposed technology aims to support NASA's mission directives by enhancing the capabilities of lunar mobility systems to navigate and map the lunar surface with high-progress-rate and long-distance autonomous surface mobility. The integration of LiDAR and stereoscopic camera data with low latency processing enables the development of an autonomous lunar rover capable of traveling at speeds at least ten times faster than current Mars rovers, supporting NASA's goal of efficient and extensive lunar exploration. By generating accurate RGB-D images that offer long-range depth estimations while preserving rich texture and color details, our technology enhances real-time hazard detection and avoidance, crucial for maintaining rover safety and operational efficiency. The fusion of LiDAR and stereo camera data will also improve downstream feature extraction and pose estimation, improving the results of subsequent SLAM processing. Additionally, the fusion approach mitigates the challenges posed by extreme lighting conditions and low-texture surfaces on the Moon. This will result in higher fidelity terrain maps and more accurate rover localization, directly contributing to NASA's mapping and exploration objectives. Our software will be optimized for resource-constrained computing platforms, such as RISC-V, GPU, and FPGA accelerators, ensuring efficient real-time processing on lunar-worthy hardware. This aligns with NASA's requirements for robust, low-power, and high-performance computing solutions. In summary, our technology not only addresses the immediate challenges of high-progress-rate, long-distance autonomous surface mobility and sensing for autonomous robotic operations in challenging environmental conditions but also supports NASA's broader mission directives by enhancing the efficiency, safety, and sustainability of autonomous lunar exploration missions. In the near term, the majority of lunar operations will be funded by NASA, including work performed by our first anticipated client, Intuitive Machines. Therefore, in the near term, non-NASA commercialization will focus on terrestrial applications of our LiDAR-Stereo fusion technology. Potential terrestrial applications include: self-driving cars, delivery robots, drones, and other autonomous systems. The high accuracy and long range RGB-D frames that our system will produce may improve operational efficiency and safety in diverse environments, including urban areas and off-road conditions. In particular, we plan to explore commercialization of a terrestrial hardware variant for mining and construction operations, where we also expect growth in demand for reliable autonomous systems that can operate continuously in harsh environments. Longer term, we expect that our LiDAR-Stereo fusion module may be an attractive option for emerging non-NASA lunar mining and construction industries, particularly if the product has established heritage from previous NASA funded missions.

This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.