Enabling Technologies for Autonomous Driving

Friday, November 03, 2017
EER 0.904 - Mulva Auditorium

Autonomous driving is becoming reality at an increasing pace, with all the tech giants now actively developing the technology. In this talk, we will focus on the key challenges of autonomous driving and how they can be addressed, from a chip maker's perspective. In particular, we will try to bring clarity to two important questions: (1) How do we enable massive compute for big data and machine learning tasks required for autonomous driving in an SoC, but still within a reasonable thermal envelop? (2) What are the key enabling technologies to remove dependency on cost inhibitive sensors for massive adoption of the technology?


VP Technology
Qualcomm Research

Sanjiv Nanda is VP Technology with Qualcomm Research and leads the Autonomous Driving research program. Over fourteen years with Qualcomm, he has helped initiate, incubate and lead a variety of research programs starting from indoor wireless technologies ((WiFi 802.11n), interworking and mobility between cellular and WiFi networks, algorithms and system design for indoor small cells), moving on to machine learning for context awareness and most recently technologies and enablers for autonomous vehicles. Prior to Qualcomm, Sanjiv worked at a startup Narad Networks designing last mile Gigabit Ethernet over coax, and before that at Bell Labs for ten years working on performance analysis and design of wireless and cellular networks. He was the first employee of Rutgers University WINLAB in 1990. His PhD was on image coding from Rensselaer Polytechnic Institute and his undergraduate degree is from IIT Kanpur. Sanjiv holds over 200 US patents and is a Fellow of the IEEE.