Provably-Safe Offloading of Neural Network Controllers for Energy-Efficiency in Autonomous Driving Systems

Title: Provably-Safe Offloading of Neural Network Controllers for Energy-Efficiency in Autonomous Driving Systems

Speaker: Mohanad Odema

Date and Time: Tuesday, January 23rd, 12:00pm

Location: EH 2430

Abstract:

To mitigate the high energy demand of Neural Network (NN) based Autonomous Driving Systems (ADSs), we consider the problem of offloading NN controllers from the ADS to nearby edge-computing infrastructure, but in such a way that formal vehicle safety properties are guaranteed. In particular, we propose the EnergyShield framework, which repurposes a controller “shield” as a low-power runtime safety monitor for the ADS vehicle. Specifically, the shield in EnergyShield provides not only safety interventions but also a formal, state-based quantification of the tolerable edge response time before vehicle safety is compromised. Using EnergyShield, an ADS can then save energy by wirelessly offloading NN computations to edge computers, while still maintaining a formal guarantee of safety until it receives a response (on-vehicle hardware provides a just-in-time fail safe). To validate the benefits of EnergyShield, we implemented and tested it in the Carla simulation environment. Our results show that EnergyShield maintains safe vehicle operation while providing significant energy savings compared to on-vehicle NN evaluation: from 24% to 54% less energy across a range of wireless conditions and edge delays.

Biography:

Odema received a B.Sc degree in Electronics and Communications in 2014 and a M.Sc degree in Computer Engineering in 2018 from Ain Shams University, Egypt. He is currently pursuing a Ph.D. degree in Computer Engineering at UCI where his current research interests are focused on HW/SW co-design methodologies for enhancing the performance efficiency of key AI workloads as from vision and NLP applications in emerging domains such as Edge-AI, autonomous systems, and tinyML.