Anand Balakrishnan

I am a Ph.D. Student in the Department of Computer Science at the University of Southern California. I am advised by Prof. Jyotirmoy Deshmukh and part of the CPS-VIDA group. My research interests lie in the intersection of Formal Methods, Control Theory, and Artificial Intelligence. Specifically, I am currently working on projects involving:

• Developing methods to learn safe controllers for autonomous systems by incorporating formal methods techniques in reinforcement learning.
• Coordination between heterogenous robot teams to perform tasks efficiently.
• Enforcing safety specifications on controllers trained using reinforcement learning and/or contain deep learning components in them.

Before this, I received my B.S. in Computer Engineering from the University at Buffalo in 2018, where I also worked with Prof. Karthik Dantu at the Distributed Robotics and Networked Embedded Systems Lab.

Publications

Conference Publications and Preprints

• Structured Reward Functions Using STL: Poster Abstract Anand Balakrishnan, and Jyotirmoy V. Deshmukh. Proceedings of the 22Nd ACM International Conference on Hybrid Systems: Computation and Control (HSCC), April 2019
• Specifying and Evaluating Quality Metrics for Vision-Based Perception Systems Anand Balakrishnan, Aniruddh G. Puranic, Xin Qin, Adel Dokhanchi, Jyotirmoy V. Deshmukh, Heni Ben Amor, and Georgios Fainekos. IEEE Proceedings of Design, Automation and Test in Europe (DATE), March 2019
• Augmenting Visual SLAM with Wi-Fi Sensing For Indoor Applications Zakieh S. Hashemifar, Charuvahan Adhivarahan, Anand Balakrishnan, and Karthik Dantu. arXiv Preprint, March 2019
• Poster: Dataset for Experimental Validation of Wi-Fi Sensing Anand Balakrishnan, Praneeth Behara, Zakieh Hashemifar, and Karthik Dantu. 6th Annual Northeastern Robotics Colloquium, October 2017