Optimization
Efficient solutions to large-scale problems.
Much of MERL's research activity involves formulating scientific and engineering problems as optimizations, which can be solved in an efficient way. We have developed fundamental algorithms to better solve classic problems, such as quadratic programs and minimum-cost paths. Our work also involves developing theoretical bounds to understand performance limits.
Quick Links
-
Researchers
Stefano
Di Cairano
Arvind
Raghunathan
Ankush
Chakrabarty
Toshiaki
Koike-Akino
Daniel N.
Nikovski
Christopher R.
Laughman
Yebin
Wang
Philip V.
Orlik
Abraham P.
Vinod
Ye
Wang
Kieran
Parsons
Scott A.
Bortoff
Avishai
Weiss
Petros T.
Boufounos
Matthew
Brand
Hassan
Mansour
Jianlin
Guo
Pu
(Perry)
Wang
Vedang M.
Deshpande
Hongbo
Sun
Hongtao
Qiao
Dehong
Liu
Bingnan
Wang
Purnanand
Elango
Chungwei
Lin
Yanting
Ma
Gordon
Wichern
Saviz
Mowlavi
William S.
Yerazunis
Nobuyuki
Yoshikawa
Jinyun
Zhang
Abraham
Goldsmith
Alexander
Schperberg
Jordan
Leung
Pedro
Miraldo
Joshua
Rapp
Anoop
Cherian
Radu
Corcodel
Anna
Deza
Kenji
Inomata
Jing
Liu
-
Awards
-
AWARD MERL Team Wins IROS 2026 Humanoid IKEA Assembly Challenge Date: October 1, 2026
Awarded to: Kei Suzuki, Jing Liu, Alexander Schperberg, Toshiaki Koike-Akino, Ye Wang, Harsh Singh, Chak Lam Shek, Maxwell Asselmeier, and Haodi Hu
MERL Contacts: Toshiaki Koike-Akino; Jing Liu; Alexander Schperberg; Kei Suzuki; Ye Wang
Research Areas: Artificial Intelligence, Computer Vision, Control, Machine Learning, Optimization, Robotics, Signal ProcessingBrief- MERL's team MEL-Craft won first place in the Humanoid IKEA Assembly Challenge at IROS 2026, held in Pittsburgh, Pennsylvania. The inaugural competition attracted approximately 34 registered teams worldwide.
The challenge asked teams to develop autonomous robot policies for a Unitree G1 humanoid robot to assemble an IKEA UTTER table from its component parts. The robot had to perform the task autonomously at the competition venue, requiring capabilities including perception, bimanual manipulation, spatial reasoning, planning, and control. Human intervention was penalized, and teams were evaluated based on assembly progress and completion time.
MERL competed as MEL-Craft and achieved first place in the competition. The result demonstrates progress toward reliable humanoid robots capable of performing complex, contact-rich manipulation tasks in real-world environments, an important direction for physical AI and general-purpose robotic systems.
The MERL team members were Kei Suzuki, Jing Liu, Alexander Schperberg, Toshiaki Koike-Akino, and Ye Wang, with contributions from MERL interns Harsh Singh, Chak Lam Shek, Maxwell Asselmeier, and Haodi Hu.
The Humanoid IKEA Assembly Challenge was held as part of IROS 2026, the IEEE/RSJ International Conference on Intelligent Robots and Systems.
- MERL's team MEL-Craft won first place in the Humanoid IKEA Assembly Challenge at IROS 2026, held in Pittsburgh, Pennsylvania. The inaugural competition attracted approximately 34 registered teams worldwide.
-
AWARD Mitsubishi Electric and MERL work recognized with IEEJ Distinguished Paper Award Date: June 1, 2025
Awarded to: Arvind Raghunathan, Daniel Nikovski
MERL Contacts: Daniel N. Nikovski; Arvind Raghunathan
Research Areas: Electric Systems, OptimizationBrief- A publication jointly authored by Mitsubishi Electric Corporation's Advanced Technology Center (ATC) and MERL researchers has been recognized with the 2025 IEEJ Distinguished Paper Award by the Institute of Electrical Engineers Japan. The paper titled "Power Band Model Based on Flow Network and Weekly Unit Commitment Problem Considering Reserve Market" published in the IEEJ Transactions on Power and Energy presents a novel Unit Commitment formulation for scheduling the generator operations. Arvind Raghunathan and Daniel Nikovksi were co-authors on this publication.
-
AWARD Mitsubishi Electric Team Wins Awards at GalFer Contest Date: June 23, 2025
Awarded to: Bingnan Wang, Tatsuya Yamamoto, Yusuke Sakamoto, Siyuan Sun, Toshiaki Koike-Akino, and Ye Wang
MERL Contacts: Toshiaki Koike-Akino; Bingnan Wang; Ye Wang
Research Areas: Machine Learning, Multi-Physical Modeling, OptimizationBrief- The MELSUR (Mitsubishi Electric SURrogate) team, consisting of a group of MERL and Mitsubishi Electric researchers, ranked first in two out of three categories in the GalFer Contest.
The GalFer (Galileo Ferraris) contest aims to compare the accuracy and efficiency of data-driven methodologies for the multi-physics simulation of traction electric machines. A total of 26 teams worldwide participated in the contest, which consists of three categories. The MELSUR team, including MERL staff Bingnan Wang, Toshiaki Koike-Akino, Ye Wang, MERL intern Siyuan Sun, Mitsubishi Electric researchers Tatsuya Yamamoto and Yusuke Sakamoto, ranked first for the category of "Novelty" and "Interpolation". The results were announced during an award ceremony at the COMPUMAG 2025 conference in Naples, Italy.
- The MELSUR (Mitsubishi Electric SURrogate) team, consisting of a group of MERL and Mitsubishi Electric researchers, ranked first in two out of three categories in the GalFer Contest.
See All Awards for Optimization -
-
News & Events
-
NEWS MERL contributes to IROS 2026 Date: September 27, 2026 - October 1, 2026
Where: The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
MERL Contacts: Siddarth Jain; Toshiaki Koike-Akino; Jing Liu; Daniel N. Nikovski; Arvind Raghunathan; Alexander Schperberg; Kei Suzuki; Ye Wang
Research Areas: Artificial Intelligence, Computer Vision, Control, Machine Learning, Optimization, Robotics, Signal ProcessingBrief- MERL made broad contributions to the technical program and robotics community at the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026), held in Pittsburgh, Pennsylvania. MERL researchers presented one main-conference paper and five workshop papers, participated in an editorial board meeting, competed in the Humanoid IKEA Assembly Challenge, and contributed to the organization of an IROS workshop.
Main Conference Paper
- ORIGAMI: Object Representation Inferred Geometrically for Articulated ManIpulation, Yunfu Deng and Daniel N. Nikovski (TR2026-141)
The work introduces a geometric representation for articulated-object manipulation, enabling robots to infer compact representations of previously unknown articulated mechanisms for downstream learning and control.
Workshop Papers
- Deliberate Practice: Learning Robot Skills under a Budget Shivam Vats, Sudarshan Harithas, Mete Akbulut, Arvind Raghunathan, and George Konidaris (TR2026-147)
- ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies, Haodi Hu, Chung-Ta Huang, Jing Liu, Ye Wang, Kei Suzuki, Matthew Brand, and Toshiaki Koike-Akino (TR2026-148)
- Test-Time Attention: Can Robots Better Follow Commands? Jing Liu, Ye Wang, Kei Suzuki, and Toshiaki Koike-Akino (TR2026-142)
- Read the Manual: Grounding Behavior Tree Synthesis for Multi-Machine Factory Operation, Chak Lam Shek, Ye Wang, Jing Liu, Kei Suzuki, Pratap Tokekar, and Toshiaki Koike-Akino (TR2026-149)
- DYNAMIT: Dynamic Zero-Shot Manipulation via Instruction-Grounded Visual Tracking and Interception in Industrial Conveyor Environments, Harsh Singh, Kei Suzuki, Ye Wang, Jing Liu, Paola Cascante-Bonilla, and Toshiaki Koike-Akino (TR2026-146)
Together, these works address a range of challenges in modern robotics, including articulated-object manipulation, efficient robot skill learning, vision-language-action policies, test-time adaptation, autonomous factory operation, and dynamic manipulation. The paper on ReCoVLA was nominated as a spotlight talk.
Robotics Community Contributions
MERL Principal Research Scientist Dr. Siddarth Jain participated in the IEEE Robotics and Automation Letters (RA-L) editorial board meeting at IROS. Dr. Jain serves as an Associate Editor of RA-L, contributing to the peer-review and editorial activities of the robotics research community.
Former MERL scientist Dr. Diego Romeres was also among the organizers of the 1st International Workshop on Industrial Applications of Robot Learning (IARL 2026). The workshop brought together researchers from academia and industry to discuss how advances in robot learning can be translated into reliable and scalable real-world industrial robotic systems.
Humanoid IKEA Assembly Challenge
MERL also participated in the IROS 2026 Humanoid IKEA Assembly Challenge with Team MEL-Craft. The team achieved first place in the competition, demonstrating autonomous humanoid manipulation capabilities for a challenging furniture-assembly task. The MEL-Craft team included MERL researchers Kei Suzuki, Jing Liu, Alexander Schperberg, Toshiaki Koike-Akino, and Ye Wang, with contributions from MERL interns Haodi Hu, Harsh Singh, Chak Lam Shek, and Maxwell Asselmeier. The competition achievement is highlighted separately in MERL's related award announcement.
About IROS
The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) is a major international robotics conference bringing together researchers, engineers, and industry practitioners working across intelligent robots and systems. IROS 2026 took place in Pittsburgh from September 27 to October 1, 2026.
- MERL made broad contributions to the technical program and robotics community at the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026), held in Pittsburgh, Pennsylvania. MERL researchers presented one main-conference paper and five workshop papers, participated in an editorial board meeting, competed in the Humanoid IKEA Assembly Challenge, and contributed to the organization of an IROS workshop.
-
NEWS MERL Presents Five Papers at IEEE Quantum Week 2026 Date: September 13, 2026 - September 18, 2026
Where: Toronto, Canada
MERL Contact: Toshiaki Koike-Akino
Research Areas: Applied Physics, Artificial Intelligence, Machine Learning, Optimization, Signal ProcessingBrief- MERL is pleased to announce that five papers have been accepted to the 2026 IEEE International Conference on Quantum Computing and Engineering (QCE), also known as IEEE Quantum Week 2026, held September 13–18, 2026, in Toronto, Canada.
The papers highlight MERL’s recent advances in quantum computing, spanning hardware-efficient quantum state preparation, quantum low-density parity-check (QLDPC) code design, graph-cover-based code construction, machine-learning-assisted code search, and reinforcement-learning-guided quantum error correction. Together, these works address important challenges toward more efficient and reliable quantum computing systems.
The five papers are:
- “Near-Lower-Bound Approximate Quantum State Preparation with Hardware-Efficient Circuits” — Toshiaki Koike-Akino (TR2026-131)
- “Reinforcement-Learning-Guided Multi-Branch Decoding of Quantum LDPC Codes” — Vahid Nourozi, Toshiaki Koike-Akino, and David Mitchell (TR2026-130)
- “Q-Learning Base Search Voltage-Labeled Covers for Weight-Six Bivariate-Bicycle Quantum LDPC Codes” — Vahid Nourozi, David Mitchell, and Toshiaki Koike-Akino (TR2026-132)
- “Collision-Voltage Design of Directional Covers for Bivariate Bicycle Quantum LDPC Codes” — Vahid Nourozi, David Mitchell, and Toshiaki Koike-Akino (TR2026-133)
- “Base-Preserving APM/Voltage Lifts of Bivariate Bicycle Quantum LDPC Codes” — Vahid Nourozi, David Mitchell, and Toshiaki Koike-Akino (TR2026-129)
- MERL is pleased to announce that five papers have been accepted to the 2026 IEEE International Conference on Quantum Computing and Engineering (QCE), also known as IEEE Quantum Week 2026, held September 13–18, 2026, in Toronto, Canada.
See All News & Events for Optimization -
-
Research Highlights
-
Internships
-
OR0330: Internship - EMT Simulation of Data-Center Power Systems
-
MS0259: Internship - Multi-Fidelity Dynamic Models for Energy Systems
-
CI0314: Internship - Embodied AI & Humanoid Robotics
See All Internships for Optimization -
-
Openings
-
SA0297: Postdoctoral Research Fellow - AI for Science
-
MS0268: Research Scientist - Plasma Modeling and Control
-
CI0177: Postdoctoral Research Fellow - Agentic AI
See All Openings at MERL -
-
Recent Publications
- , "Deliberate Practice: Learning Robot Skills under a Budget", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Workshop, October 2026.BibTeX TR2026-147 PDF
- @inproceedings{Vats2026oct,
- author = {Vats, Shivam and Harithas, Sudarshan and Akbulut, Mete and Raghunathan, Arvind and Konidaris, George},
- title = {{Deliberate Practice: Learning Robot Skills under a Budget}},
- booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Workshop},
- year = 2026,
- month = oct,
- url = {https://www.merl.com/publications/TR2026-147}
- }
- , "Spatio-temporal monitoring using energy-constrained, sensing robots", IEEE Transactions on Automation Science and Engineering, September 2026.BibTeX TR2026-144 PDF Video
- @article{Buyukkocak2026sep,
- author = {Buyukkocak, Ali and {Di Cairano}, Stefano and Vinod, Abraham P.},
- title = {{Spatio-temporal monitoring using energy-constrained, sensing robots}},
- journal = {IEEE Transactions on Automation Science and Engineering},
- year = 2026,
- month = sep,
- url = {https://www.merl.com/publications/TR2026-144}
- }
- , "BEACON: A Bayesian Optimization Inspired Strategy for Efficient Novelty Search", Digital Discovery, DOI: 10.1039/d6dd00123h, Vol. 5, No. 7, September 2026.BibTeX TR2026-151 PDF
- @article{Tang2026sep,
- author = {Tang, Wei-Ting and Chakrabarty, Ankush and Paulson, Joel A.},
- title = {{BEACON: A Bayesian Optimization Inspired Strategy for Efficient Novelty Search}},
- journal = {Digital Discovery},
- year = 2026,
- volume = 5,
- number = 7,
- month = sep,
- doi = {10.1039/d6dd00123h},
- url = {https://www.merl.com/publications/TR2026-151}
- }
- , "Fast Adaptive Planning for Autonomous Tractor-Trailer Systems via Iterative LQR Steering", IEEE Conference on Automation and Science Engineering, August 2026.BibTeX TR2026-118 PDF
- @inproceedings{Zhou2026aug,
- author = {Zhou, Tianyu and Wang, Yebin and Umat, Akhil and Tiwari, Astha and {Di Cairano}, Stefano},
- title = {{Fast Adaptive Planning for Autonomous Tractor-Trailer Systems via Iterative LQR Steering}},
- booktitle = {IEEE Conference on Automation and Science Engineering},
- year = 2026,
- month = aug,
- url = {https://www.merl.com/publications/TR2026-118}
- }
- , "Nonlinear Model Predictive Control for High-Thrust Geostationary Station Keeping using Averaged Dynamics", World Congress of the International Federation of Automatic Control (IFAC), August 2026.BibTeX TR2026-117 PDF
- @inproceedings{Pavlasek2026aug,
- author = {Pavlasek, Natalia and Acikmese, Behcet and {Di Cairano}, Stefano and Weiss, Avishai},
- title = {{Nonlinear Model Predictive Control for High-Thrust Geostationary Station Keeping using Averaged Dynamics}},
- booktitle = {World Congress of the International Federation of Automatic Control (IFAC)},
- year = 2026,
- month = aug,
- url = {https://www.merl.com/publications/TR2026-117}
- }
- , "Coordinated Energy-Aware Job Scheduling and Flexibility Provisioning in Distributed Data Centers", IEEE PES General Meeting, July 2026.BibTeX TR2026-113 PDF
- @inproceedings{Kar2026jul,
- author = {Kar, Aditya Shankar and Sun, Hongbo and Raghunathan, Arvind and Guo, Jianlin},
- title = {{Coordinated Energy-Aware Job Scheduling and Flexibility Provisioning in Distributed Data Centers}},
- booktitle = {IEEE PES General Meeting},
- year = 2026,
- month = jul,
- url = {https://www.merl.com/publications/TR2026-113}
- }
- , "Scalable DAE-Constrained PINODE Framework for Vapor-Compression HVAC Systems", International Refrigeration and Air Conditioning Conference at Purdue, July 2026.BibTeX TR2026-111 PDF
- @inproceedings{Zhai2026jul,
- author = {Zhai, Hanfeng and Qiao, Hongtao and Mansour, Hassan and Laughman, Christopher R.},
- title = {{Scalable DAE-Constrained PINODE Framework for Vapor-Compression HVAC Systems}},
- booktitle = {International Refrigeration and Air Conditioning Conference at Purdue},
- year = 2026,
- month = jul,
- url = {https://www.merl.com/publications/TR2026-111}
- }
- , "On State Selection for Vapor Compression Cycle Models with Zeotropic Refrigerant Mixtures", Purdue Air-Conditioning and Refrigeration Conference, July 2026.BibTeX TR2026-109 PDF
- @inproceedings{Laughman2026jul,
- author = {{Laughman, Christopher R. and Qiao, Hongtao and Bortoff, Scott A. and Deshpande, Vedang M.}},
- title = {{On State Selection for Vapor Compression Cycle Models with Zeotropic Refrigerant Mixtures}},
- booktitle = {Purdue Air-Conditioning and Refrigeration Conference},
- year = 2026,
- month = jul,
- url = {https://www.merl.com/publications/TR2026-109}
- }
- , "Deliberate Practice: Learning Robot Skills under a Budget", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Workshop, October 2026.
-
Videos
-
Software & Data Downloads
-
ROS 2 Cooperative Aerial Robots Inspection Challenge -
SAmple Consensus for Adaptive Graduated Non-Convexity -
Optimal Recursive McCormick Linearization of MultiLinear Programs -
Convex sets in Python -
Physics-Informed Neural ODE -
Meta-Learning State Space Models -
Python-based Robotic Control & Optimization Package -
Template Embeddings for Adiabatic Quantum Computation -
Quasi-Newton Trust Region Policy Optimization -
Convergent Inverse Scattering using Optimization and Regularization
-