CoFlow Jet signs JOA with NASA to commercialize deflected slip-stream technology for eV/STOL
Palma de Mallorca buying 5 Solaris hydrogen buses

NPS paper concludes commercially scalable technology exists for sensors to enable zero roadway deaths

Neural Propulsion Systems (NPS), a developer of autonomous sensing platforms, issued a white paper that concludes that new innovations enable vehicles with or without human supervision to see soon enough, clear enough and far enough to eliminate roadway deaths.

Achieving zero roadway deaths is necessary for universal adoption of autonomous driving and is the objective of the recently released US National Roadway Safety Strategy.

The paper is written by Dr. Behrooz Rezvani, a serial entrepreneur and currently founder and CEO of NPS; Dr. Babak Hassibi, co-founder and Chief Technologist at NPS; and Dr. Lawrence Burns, former Corporate Vice President of Research & Development and Planning at General Motors and Executive Advisor to NPS.

The paper finds that zero deaths require a sensing and processing peak data rate on the order of 100 X 1012 bits per second (100 Terabits per second) for vehicles to operate safely under worst roadway conditions. This immense requirement is 10 million times greater than the sensory data rate from our eyes to our brains.

The paper also shows that sensing and processing 100 Tb/s can be accomplished by combining breakthrough analytics, advanced multi-band radar, solid state LiDAR, and advanced system on a chip (SoC) technology. Such an approach will allow companies developing advanced human driver assistance systems (ADAS) and fully autonomous driving systems to accelerate progress.

NPS achieved pilot-scale proof-of-concept of the core sensor element required for zero roadway deaths at a Northern California airfield in December 2021. One reason for this successful historic event is the Atomic Norm (AN) method, which is based upon a recently developed mathematical compressed sensing framework that changes how sensor data is processed and understood. [See generally Chandrasekaran et al. (2012)]

Compressed sensing reduces the number of measurements required to maintain a certain level of performance. The AN framework has been tailored specifically for radar, LiDAR detection and signal processing. AN specifically inherits the defining property of compressed sensing and reduces the data rate requirement by orders of magnitude compared to scanning LiDAR and beam-steering radar. It is capable of handling worst-case scenarios (e.g., fast changing environments).

One of AN’s advantages is that it does not require the scene to be physically scanned with narrow beams. Instead, it uses much wider beams and better computation to allow each voxel in the coverage volume to be interrogated individually. The AN method can be applied to do this efficiently and with great efficacy, and NPS has demonstrated this capability for the first time.

—NPS white paper

Based on principles from physics and information theory, it is possible for sensors to see well enough to enable zero roadway deaths. This is not wishful thinking—it’s possible today. We are solely focused on rolling out this historic technology that sees everything sooner, clearer and farther to provide autonomous vehicles with the stopping distance and time needed to reach zero preventable accidents. Henry Ford said his goal was for every working family to own a car. Our goal is to have nobody lose a loved one in a car crash.

—Dr. Behrooz Rezvani


  • Chandrasekaran, V., Recht, B., Parrilo, P.A. et al. (2012) “The Convex Geometry of Linear Inverse Problems.” Found Comput Math 12, 805–849 doi: 10.1007/s10208-012-9135-7



FLIR for night, vision only, and V2X super power sensor, combined with distributed in vehicle computing is the way to go.

The comments to this entry are closed.