Nishad Gothoskar

I am a research engineer at Vicarious AI where I work on Robotics and AI. By combining insights from neuroscience and probabilistic generative modeling, we seek to design algorithms that can match humans' ability to learn and generalize.

From 2014-2017 I was an undergraduate at CMU SCS, where I studied Math and Computer Science. I did summer internships at zSpace, Google, and Uber ATG. I did research on mobile privacy, activity recognition, and search-based planning algorithms.

I was an engineer at Uber ATG, where I built prediction systems for autonomous vehicles, advised by Jeff Schneider and Ian Dewancker. My contributions were in predicting interactions between vehicles/bikers/pedestrains.

I was a visiting research associate at MIT CSAIL in the Learning and Intelligent Systems Group. I was advised by Leslie Pack Kaelbling and Tomas Lozano Perez. I implemented a Task and Motion Planning system that can learn primitives and plan.

Research
Learning a generative model for robot control using visual feedback
N. Gothoskar, M. Lazaro-Gredilla, A. Agarwal, Y. Bekiroglul, D. George
arXiv

We introduce a novel formulation for incorporating visual feedback in controlling robots. We define a generative model from actions to image observations of features on the end-effector. Inference in the model allows us to infer the robot state corresponding to target locations of the features. This, in turn, guides motion of the robot and allows for matching the target locations of the features in significantly fewer steps than state-of-the-art visual servoing methods.

Learning cognitive maps from vicarious trial and error
R. Rikhye, N. Gothoskar, S. Guntupalli, A. Dedieu, M. Lazaro-Gredilla, D. George
bioRxiv

Cognitive maps enable us to learn the layout of environments, encode and retrieve episodic memories, and navigate vicariously for mental evaluation of options.

Learning higher-order sequential structure with cloned HMMs
A. Dedieu, N. Gothoskar, S. Swingle, W. Lehrach, M. Lazaro-Gredilla, D. George
arXiv

CHMMs are a constrained version of HMMs with a simple sparsity structure that enforces many hidden states to map deterministically to the same emission state. We demonstrate the effectiveness of this model in various data domains.

Predicting interactions for autonomous vehicles
Uber Advanced Technologies Group

Worked on road user trajectory prediction to enable planning. I built system for modeling interactions between road users.

Does this App Really Need My Location?
S. Chitkara, N. Gothoskar, S. Harish, J. Hong, Y. Agarwal
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (ACM IMWUT)
[Website] [Press] [Interview]

Mobile applications prey on user's sensitive data. We developed an application that monitors the flow of private information and protects their data from being leaked.


Template from here.