Abhishek Jha

I'm computer science graduate student at New York University, Courant. I completed my bachelor's from Delhi Technological University in New Delhi. My interests span computer vision, robotics, bayesian machine learning, and reinforcement learning, with a focus on dexterous manipulation and multi-agent systems with building reliable, interpretable decision-making systems across modalities.

Email  /  CV  /  Scholar  /  Github

Research

I work on building robots and learning agents that can act in the real world. My current focus is dexterous manipulation, where I train robots to perform in-hand skills using reinforcement learning, combining vision and touch with 3D scene understanding and object pose estimation, and I spend a lot of time getting these policies to work on real hardware. I also work on VLA models as planners for visual navigation, where the robot follows open-vocabulary language instructions to move through unstructured environments without a pre-built map. Earlier, I worked on multi-agent coordination, focusing on safe and deadlock-free navigation of large groups of agents without centralized communication. On the theory side, I study reinforcement learning policies and try to understand what makes them sample efficient, robust under distribution shift, and easier to transfer from simulation to real hardware, and I am especially interested in improvements around regret and convergence bounds, exploration in high dimensional spaces, stability of policy gradient methods, and how representation learning shapes the policy space.

Investigates the mammographic phenotypes captured by deep learning breast cancer risk models by clustering patch embeddings from Mirai into soft cluster assignments and performing logistic-regression–based radiomic analysis.

A survey of Social Mini-Games in multi-robot navigation, proposing a unified taxonomy and evaluation framework to classify existing methods and guide future research.

A single decentralized control algorithm using neural ICBFs and gradient optimization that ensures safe, input-constrained, deadlock-free control of 1000+ agents in cluttered environments.

A semi-supervised segmentation model (PV-S3) that detects defects in photovoltaic EL images using only 20% labeled data, outperforming state-of-the-art supervised methods and reducing annotation costs by 80%.

A fine tuned transfer learning model using the SimCLR and SwAV models that predicts autism from resting-state fMRI scans, showcasing the potential of contrastive and non-contrastive models for robust neuroimaging analysis.

Introduced Strategic Pseudo-Goal Perturbation (SPGP), that resolves deadlocks in multi-agent navigation by guiding agents through strategic pseudo-goals, enhancing safety and efficiency in complex scenarios.

A transfer learning model using the Xception ConvNet predicts autism from resting-state fMRI scans, demonstrating the feasibility of early diagnosis through deep learning on brain imaging data.

An integrated ANN and Genetic Algorithm model predicts and optimizes Material Removal Rate and surface roughness in Al 6061 turning operations, enhancing machining precision through simulation-based methods.

Projects

A Benchmark and Survey of Deadlock Resolution in Multi-Robot Navigation in Social Mini-Games

Autonomous navigation and trajectory planning of a robot using Robot Operating System (ROS). A maze is created in gazebo for the robot to determine the best possible trajectory with collison avoidance. Probablistic localization method is used for navigation. Adaptive Monte Carlo Localization(AMCL) node and slam_gmapping package is used for localization of robot and mapping of robot. Rviz interface is used for the simulation of robot and creating the cost map for the travel of robot.

Obstacle avoidance implemented in Robot operating system for Unmanned Aerial Vehicle (UAV) using LiDAR scan data. Hector quadrotor package is used for spawning the drone in the gazebo environment. Readings from SONAR sensor with python script is used for flying the drone to a certain height. LiDAR readings are used to detect obstacles in the surroundings.

Path planning of point robot for finding shortest path between start and goal position. Implemented Informed and Uninformed search algorithms for the path planning problem. A random 2D enivronment is created with obstacles for evealuation of searching algorithms. A* and Dijkstras algorithm is implemented for obtaining the shortest path. Investigated the perofrmance by implementing other search based algorithms such as Best first, Depth First and Breadth First for finding the shortest distance. Given below are the images of search done by the various algorithms.

This website is created upon Jon Barron's template.