Siddarth Jain
Siddarth is a Principal Research Scientist at Mitsubishi Electric Research Laboratories (MERL). His research spans computer vision, machine learning, and robotics, with a focus on enabling autonomous systems to perceive, understand, and act in the physical world. He develops data-driven and geometric approaches for perception, manipulation, learning, and decision-making, with applications in human-robot collaboration and real-world automation. He also serves as an Associate Editor for IEEE Robotics and Automation Letters (RA-L).
He received his Ph.D. in Computer Science from Northwestern University in 2019. In collaboration with the Shirley Ryan AbilityLab, his doctoral research focused on perception and shared autonomy for assistive systems.
In his spare time, he pursues amateur astrophotography, blending science and artistry with a particular interest in deep-sky imaging.
Contact: sjain {at} merl[dot]com
news
selected publications
-
EARL: Eye-on-hand Reinforcement Learner for Dynamic Grasping with Active Pose EstimationIn Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023: Dynamic Grasping | Reinforcement Learning | Pose Estimation | Closed-Loop Control | Visual Servoing -
SplatCtrl: Perception-Action Coupling via Gaussian Scene Representations and Reactive Robot ControlIn Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2026: Gaussian Splatting | Collision Avoidance | Reactive Control | Motion Planning | Scene Reconstruction | HRI -
Insert-One: One-shot Robust Visual-Force Servoing for Novel Object Insertion with 6-DoF TrackingIn Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024: Assembly | Robotic Insertion | Visual-Force Servoing | Robust Manipulation | Visual Tracking