Sandeep Chinchali

alt text 

PhD Candidate,
Computer Science Department,
Stanford University
e-mail: csandeep [@] stanford [DOT] edu

About me

I received a BS (Honors) in Electrical Engineering and a minor in Control and Dynamical Systems from Caltech in 2012. At Caltech, I was president of the Tau Beta Pi Engineering Honors Society and worked on formal verification for robotics with Professors Joel Burdick and Richard Murray.

Currently, I am a Computer Science PhD student at Stanford University co-advised by Prof. Sachin Katti and Prof. Marco Pavone, where I work at the intersection of deep learning, computer networks, and robotics. I am a member of the Stanford Platform Lab.

Previously, I took a two year leave of absence from Stanford to work as the first Machine Learning Research Engineer at my adviser's startup Uhana, which focuses on data-driven control of cellular networks. At Uhana, I built Deep Reinforcement Learning (RL) controllers for cellular network resource allocation problems, some of which were successfully piloted in Proof-of-Concept trials by major network operators.


My research applies deep reinforcement learning (RL) to a variety of scheduling and control problems for cellular networks, Internet-of-Things (IoT Devices), and robotics. My publications span both robotics/AI and systems venues:


  • Scheduling Traffic from IoT Devices on Cellular Networks Using Deep RL (AAAI 2018)

  • Distributed Neural Network Inference Between Edge Devices and the Cloud (Accepted to ACM HotNets 2018)

  • Decoupling Prediction and Control Across Data Boundaries


  • Formal Methods for Autonomous Car Safety Certification (ICRA 2016)

  • Towards Formal Methods for Dexterous Robotic Manipulation (ICRA 2012)

A full list of publications can be found here.

Invited Talks

I have given talks both in industry and academic conferences, including Alphabet's Project Loon, the ITU Workshop on “Machine Learning for 5G and beyond”, AAAI 2018, ISRR 2017, ICRA 2012/16, and Stanford's Platform Lab Industry Reviews.

Talk slides can be found here.