Nitish Dashora

I am a PhD student at MIT CSAIL studying continual learning and robotic AI. I am advised by Pulkit Agrawal and am thankful to be supported by the NSF GRFP. I recieved my B.S. in Electrical Engineering and Computer Science (EECS) from UC Berkeley with Honors. I was an undergraduate researcher at Berkeley Artificial Intelligence Research under Sergey Levine. I also previously worked with Bruno Olshausen from the Redwood Center for Theoretical Neuroscience. Lastly, I was a member of Machine Learning at Berkeley where I led research projects, made free course content, and mentored incoming students.

Summer 2024: On hiatus
Summer 2023: Research intern at the Center for Human-Compatible AI under Prof. Stuart Russell studying exploration and skill discovery.
Summer 2022: Software development engineer intern at Amazon Web Services creating optimized multi-cluster Spark/Hadoop algorithms.
Summer 2021: Research fellow at NASA JPL with team CoStar working on robotic planning and navigation.

Email  /  CV  /  Bio  /  Twitter  /  Github  /  LinkedIn

I am most interested in the theory of intelligence and how to create general learning systems that encompass this definition. The age-old question of AGI has so strongly captivated me that I am certain I would like to dedicate my life’s career to exploring it. I think that physical embodiment will play a significant role in the creation of AGI, thus I find that robotics and robot learning is an excellent testbed for AI research.

We present a compositional skill discovery feedback loop for fast online exploration and planning.

We present a multi-robot visual navigation foundation model for effective fine-tuning and novel task adaptation.

DAgger-like imitative learning with model predictive path integral control works as an end-to-end navigation system.

Combining geometric costmaps and learned models improves long-range navigation in offroad environments.

Hierarchical Sparse Codes with learned steering can handle MNIST deformations.

source