MERL - Mitsubishi Electric Research Laboratories

Devesh K. Jha

Devesh K. Jha
Devesh's Quick Links

  • Biography

    Devesh's PhD Thesis was on decision & control of autonomous systems. He also got a Master's degree in Mathematics from Penn State. His research interests are in the areas of Machine Learning, Time Series Analytics and Robotics. He was a recipient of the best student paper award at the 1st ACM SIGKDD workshop on Machine Learning for Prognostics and Health Management at KDD 2016, San Francisco.

  • Recent News & Events

    •  NEWS    MERL researchers presented 5 papers and an invited workshop talk at ICRA 2022
      Date: May 23, 2022 - May 27, 2022
      Where: International Conference on Robotics and Automation (ICRA)
      MERL Contacts: Ankush Chakrabarty; Stefano Di Cairano; Siddarth Jain; Devesh K. Jha; Pedro Miraldo; Daniel N. Nikovski; Rien Quirynen; Arvind Raghunathan; Diego Romeres; Abraham P. Vinod; Yebin Wang
      Research Areas: Artificial Intelligence, Machine Learning, Robotics
      Brief
      • MERL researchers presented 5 papers at the IEEE International Conference on Robotics and Automation (ICRA) that was held in Philadelphia from May 23-27, 2022. The papers covered a broad range of topics from manipulation, tactile sensing, planning and multi-agent control. The invited talk was presented in the "Workshop on Collaborative Robots and Work of the Future" which covered some of the work done by MERL researchers on collaborative robotic assembly. The workshop was co-organized by MERL, Mitsubishi Electric Automation's North America Development Center (NADC), and MIT.
    •  
    •  TALK    [MERL Seminar Series 2022] Prof. Michael Posa presents talk titled Hybrid robotics and implicit learning
      Date & Time: Tuesday, May 3, 2022; 1:00 PM
      Speaker: Michael Posa, University of Pennsylvania
      MERL Host: Devesh K. Jha
      Research Areas: Control, Optimization, Robotics
      Abstract
      • Machine learning has shown incredible promise in robotics, with some notable recent demonstrations in manipulation and sim2real transfer. These results, however, require either an accurate a priori model (for simulation) or a large amount of data. In contrast, my lab is focused on enabling robots to enter novel environments and then, with minimal time to gather information, accomplish complex tasks. In this talk, I will argue that the hybrid or contact-driven nature of real-world robotics, where a robot must safely and quickly interact with objects, drives this high data requirement. In particular, the inductive biases inherent in standard learning methods fundamentally clash with the non-differentiable physics of contact-rich robotics. Focusing on model learning, or system identification, I will show both empirical and theoretical results which demonstrate that contact stiffness leads to poor training and generalization, leading to some healthy skepticism of simulation experiments trained on artificially soft environments. Fortunately, implicit learning formulations, which embed convex optimization problems, can dramatically reshape the optimization landscape for these stiff problems. By carefully reasoning about the roles of stiffness and discontinuity, and integrating non-smooth structures, we demonstrate dramatically improved learning performance. Within this family of approaches, ContactNets accurately identifies the geometry and dynamics of a six-sided cube bouncing, sliding, and rolling across a surface from only a handful of sample trajectories. Similarly, a piecewise-affine hybrid system with thousands of modes can be identified purely from state transitions. Time permitting, I'll discuss how these learned models can be deployed for control via recent results in real-time, multi-contact MPC.
    •  

    See All News & Events for Devesh

  • Awards

    •  AWARD    MERL Researcher Devesh Jha Wins the Rudolf Kalman Best Paper Award 2019
      Date: October 10, 2019
      Awarded to: Devesh Jha, Nurali Virani, Zhenyuan Yuan, Ishana Shekhawat and Asok Ray
      MERL Contact: Devesh K. Jha
      Research Areas: Artificial Intelligence, Control, Data Analytics, Machine Learning, Robotics
      Brief
      • MERL researcher Devesh Jha has won the Rudolf Kalman Best Paper Award 2019 for the paper entitled "Imitation of Demonstrations Using Bayesian Filtering With Nonparametric Data-Driven Models". This paper, published in a Special Commemorative Issue for Rudolf E. Kalman in the ASME JDSMC in March 2018, uses Bayesian filtering for imitation learning in Hidden Mode Hybrid Systems. This award is given annually by the Dynamic Systems and Control Division of ASME to the authors of the best paper published in the ASME Journal of Dynamic Systems Measurement and Control during the preceding year.
    •  
    See All Awards for MERL

  • MERL Publications

    •  Raghunathan, A., Jha, D.K., Romeres, D., "PYROBOCOP: Python-based Robotic Control & Optimization Package for Manipulation", IEEE International Conference on Robotics and Automation (ICRA), May 2022.
      BibTeX TR2022-057 PDF Software
      • @inproceedings{Raghunathan2022may,
      • author = {Raghunathan, Arvind and Jha, Devesh K. and Romeres, Diego},
      • title = {PYROBOCOP: Python-based Robotic Control & Optimization Package for Manipulation},
      • booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
      • year = 2022,
      • month = may,
      • url = {https://www.merl.com/publications/TR2022-057}
      • }
    •  Shirai, Y., Jha, D.K., Raghunathan, A., Romeres, D., "Robust Pivoting: Exploiting Frictional Stability Using Bilevel Optimization", IEEE International Conference on Robotics and Automation (ICRA), May 2022.
      BibTeX TR2022-045 PDF
      • @inproceedings{Shirai2022may,
      • author = {Shirai, Yuki and Jha, Devesh K. and Raghunathan, Arvind and Romeres, Diego},
      • title = {Robust Pivoting: Exploiting Frictional Stability Using Bilevel Optimization},
      • booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
      • year = 2022,
      • month = may,
      • url = {https://www.merl.com/publications/TR2022-045}
      • }
    •  Jha, D.K., Romeres, D., Jain, S., Yerazunis, W.S., Nikovski, D., "Design of Adaptive Compliance Controllers for Safe Robotic Assembly", arXiv, April 2022.
      BibTeX arXiv
      • @article{Jha2022apr,
      • author = {Jha, Devesh K. and Romeres, Diego and Jain, Siddarth and Yerazunis, William S. and Nikovski, Daniel},
      • title = {Design of Adaptive Compliance Controllers for Safe Robotic Assembly},
      • journal = {arXiv},
      • year = 2022,
      • month = apr,
      • url = {https://arxiv.org/abs/2204.10447}
      • }
    •  Rosen, E., Rammohan, S., Jha, D.K., "Learning robot motor skills with mixed reality", International Workshop on Virtual, Augmented, and Mixed-Reality for Human-Robot Interactions ACM/IEEEE International Conference on Human-Robot Collaboration 2022, March 2022.
      BibTeX TR2022-032 PDF
      • @inproceedings{Rosen2022mar,
      • author = {Rosen, Eric and Rammohan, Sreehari and Jha, Devesh K.},
      • title = {Learning robot motor skills with mixed reality},
      • booktitle = {International Workshop on Virtual, Augmented, and Mixed-Reality for Human-Robot Interactions ACM/IEEEE International Conference on Human-Robot Collaboration 2022},
      • year = 2022,
      • month = mar,
      • url = {https://www.merl.com/publications/TR2022-032}
      • }
    •  Shirai, Y., Jha, D.K., Raghunathan, A., Romeres, D., "Chance-Constrained Optimization in Contact-Rich Systems for Robust Manipulation", arXiv, March 2022.
      BibTeX
      • @article{Shirai2022mar,
      • author = {Shirai, Yuki and Jha, Devesh K. and Raghunathan, Arvind and Romeres, Diego},
      • title = {Chance-Constrained Optimization in Contact-Rich Systems for Robust Manipulation},
      • journal = {arXiv},
      • year = 2022,
      • month = mar
      • }
    See All Publications for Devesh

  • Software Downloads

  • Videos

  • MERL Issued Patents

    • Title: "System and Method for Automatic Error Recovery in Robotic Assembly"
      Inventors: Nikovski, Daniel N.; Jha, Devesh; Romeres, Diego
      Patent No.: 11,161,244
      Issue Date: Nov 2, 2021
    • Title: "Predictive Classification of Future Operations"
      Inventors: Jha, Devesh; Zhang, Wenyu; Laftchiev, Emil; Nikovski, Daniel N.
      Patent No.: 10,996,664
      Issue Date: May 4, 2021
    • Title: "System and Method for Control Constrained Operation of Machine with Partially Unmodeled Dynamics"
      Inventors: Chakrabarty, Ankush; Jha, Devesh; Wang, Yebin
      Patent No.: 10,895,854
      Issue Date: Jan 19, 2021
    • Title: "Compact Photonic Devices"
      Inventors: Kojima, Keisuke; Tahersima, Mohammad; Koike-Akino, Toshiaki; Jha, Devesh; Wang, Bingnan; Lin, Chungwei; Parsons, Kieran
      Patent No.: 10,859,769
      Issue Date: Dec 8, 2020
    • Title: "Vehicle Automated Parking System and Method"
      Inventors: Wang, Yebin; Jha, Devesh
      Patent No.: 9,969,386
      Issue Date: May 15, 2018
    See All Patents for MERL