The field of wireless engineering is on the cusp of a data-driven revolution. This revolution is powered by measurement and powerful AI tools, such as deep learning, that allow wireless systems to adapt and optimize to unprecedented levels of scale, performance, and reliability.
While wireless communications technology has advanced considerably since its invention in the 1890s, the fundamental design methodology has remained unchanged throughout its history: wireless engineers hand-tune and design radio systems and algorithms for specific applications using simplified analytic models and assumptions. This paradigm worked well for many applications until now, but it struggles to tackle the complexity of optimization for modern real-world systems with high degrees of freedom. It also suffers from the problem of model mismatch. There are many real-world deployments where we could do better.
Built on foundational research first developed and published by DeepSig principals, OmniPHY enables a radically different approach to communications. Systems are learned from wireless channel measurements and directly optimized for real-world hardware and channel effects using end-to-end performance metrics and feedback. By providing wireless systems that exploit imperfections and degrees of freedom, OmniPHY systems provide improved efficiency, resilience, and adaptivity in complex high-density, non-linear, hostile, or unique communications environments.
OmniPHY and machine learning approaches to physical layer modem optimization take several forms. They can be implemented transparently as small but key algorithms and subsystems inside complete communications suites, or they can be more comprehensive and radical in how they change the physical layer. With our OmniPHY-5G capabilities, we focus on integrating algorithms into existing 100% standards-compliant, and interoperable 5G-NR RAN implementations.
For some systems, such as point-to-point backhaul, satellite communications, or single-vendor mesh networks — where the ecosystem principally needs to interoperate with itself — more radical physical layer changes are possible. With our non-standards-centric OmniPHY, we have reimagined the definition of a modem, allowing point-to-point and closed communications ecosystems to adapt completely across the modulation and coding dimensions of the modem while still providing standardized interfaces to networks and application layers. This allows the modem to use the link and operate with existing best-practice methods such as FIPS 140-2 class AES256 link encryption, high-performance error correction using polar codes, message authentication, and error detection.
OmniPHY learned communications links focus on physical layer modulation and representation learning. The links adapt the representation of what is transmitted to optimize processing on both ends for key performance metrics such as bit error rate and energy efficiency. As a software modem capability, OmniPHY deploys on a range of off-the-shelf computer platforms and radio front-end devices, such as OmniSIG, to allow for the deployment and integration of communications links into unique and demanding applications.
The illustration below shows a UAV-centric application of OmniPHY running on a compact embedded NVIDIA Jetson TX2 platform. It carries H.264 streaming video, IP traffic, and MAVLink telemetry data over a learned modulation scheme. This scheme adapts online to improve performance in response to interference, distortion, or other effects.
OmniPHY provides a unique solution for closed ecosystem wireless communications solutions where a high degree of adaptation is possible and learning-based physical layer techniques push algorithmic efficiency and performance to the extreme for specific hardware configurations, deployment environments, and wireless system constraints.
We continue to develop our standards-free communications system, learning and deployment software tools, and capabilities. We have conducted tests and deployments with partners including NASA and UAS vendors. We are working with new and existing partners to insert this technology into next-generation systems to save power, reduce parts costs, enhance system performance, and improve resilience and security.
.png "image (2)")