OmniPHY Communications

The field of wireless engineering is on the cusp of a data-driven revolution, powered by measurement and powerful AI tools such as deep learning, that will 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-tuning and designing radio systems and algorithms for specific applications using simplified analytic models and assumptions. This paradigm has worked well for many applications to-date, but struggles to tackle the complexity of optimization for modern real-world systems with high degrees of freedom and suffers from the problem of model mis-match with many real world deployments where we could do better.

Built on foundational research first developed and published by DeepSig principals, OmniPHY enables a new, radically different approach to communications, where systems are learned from wireless channel measurements and optimized directly for real-world hardware & channel effects using end-to-end performance metrics and feedback. By providing a new class of wireless systems that is able to exploit imperfections and degrees of freedom, OmniPHY systems can provide improved efficiency, resilience, and adaptivity in complex high-density, non-linear, hostile, and/or unique communications environments where previous systems were too brittle or inflexible for real-world conditions.

Adaptation and Interoperability

OmniPHY and machine learning approaches to physical layer modem optimization can 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 the degree to which they change the physical layer. In our OmniPHY-5G capabilities we focus on transparent and fluid integration of algorithms into existing 100% standards compliant and interoperable NR ran implementation, but 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. In our non-standards centric OmniPHY, have re-imagined what defines a modem, allowing point-to-point and closed communications ecosystems to adapt completely across the modulation and coding dimensions of the modem, but still providing widely standardized interfaces to network and application layers to utilize the link, and to interoperate 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 Communicatons Links

OmniPHY learned communications links focus on physical layer modulation and representation learning, adapting the fundamental representation of what is transmitted over the link to optimize processing on both ends for key performance metrics such as bit error rate and energy efficiency. As a software modem capability, OmniPHY can be deployed on a range of off-the-shelf compute platforms and radio front-end devices similar to OmniSIG in order to allow for the deployment and integration of communications links into unique and demanding applications. Below we illustrate a UAV-centric application of OmniPHY running on a compact embedded NVIDIA Jetson TX2 platform carrying H.264 streaming video, IP traffic, and MAVLink telemetry data over a fully learned modulation scheme which can adapt on-line to improve performance in response to interference, distortion, or other effects.

Next Generation Satellite, Backhaul, and MESH

OmniPHY provides a unique solution for these closed ecosystem wireless communications solutions where a high degree of adaptation is possible where learning based physical layer techniques can push algorithmic efficiency and performance to the extreme for specific hardware configurations, deployment environments, and wireless system constraints. We are continuing to rapidly develop out standards-free communications system learning and deployment software tools and capabilities, have conducted a number of tests and deployments with partners including NASA and UAS vendors in this space and are continuing to work heavily 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.

Inquiries

To learn more about our OmniPHY communications systems, please contact us!