I am a PhD student at International Institute of Information Technology Hyderabad (IIIT-H), India. I am currently pursuing research on autonomous motion planning at MPI-IS, Tübingen, Germany. My doctoral research focuses on scalable real-time motion planning for multiple agile agents.

During my Ph.D. I have developed algorithms for cooperative multi-agent optimization and navigation in unstructured environments. For artificially intelligent agents to be useful in everyday life, they need to learn to operate safely in largely unstructured environments, perceive and reason about objects in the environment, monitor changes, and plan actions to simplify everyday activities of people. My thesis considers the following two collaborative autonomous tasks and focuses on the aforementioned aspects of artificial intelligence. 

• Multi-agent planning for autonomous aerial motion capture (AirCap):

Aerial outdoor motion capture is a computer vision driven control problem. The challenge is to compute safe, feasible trajectories for flying cameras (drones) to improve the quality of 3-D reconstruction of a moving human subject. In this project, we developed decentralized stochastic algorithms that perform real-time trajectory optimization for aerial vehicles.

• Multi-agent cooperative object manipulation in unstructured environments:

Object manipulation through dynamic environments using multiple mobile manipulators is a computationally and kinodynamically challenging problem. This task requires agents to explore intelligent cooperative behaviors that enable them and a commonly manipulated object to navigate dynamic environments.

Presently, I am working on developing model-free perception-aware algorithms that derive actions from input observations using neural networks. For the aerial motion capture task, we leverage multi-agent deep reinforcement learning algorithms with a parallelized training setup and realistic synthetic environments, all wrapped using the ROS software framework (AirCapRL).

News

• [New!!! RA-L and IROS 2020 accepted]  AirCapRL: Autonomous Aerial Human Motion Capture using Deep Reinforcement Learning -- arXiv.
• [Code of our IEEE RA-L + IROS 2020 submission]  AirCapRL: Autonomous Aerial Human Motion Capture using Deep Reinforcement Learning -- Code here.
• [Supplementary Document for IEEE RA-L + IROS 2020 submission]  AirCapRL: Autonomous Aerial Human Motion Capture using Deep Reinforcement Learning -- Document here.