# Research The following are projects mostly from my time at the [Boston Dynamics AI Institute](https://www.theaiinstitute.com/). ## Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation John Z. Zhang, Maks Sorokin, Jan Brüdigam, Brandon Hung, Stephen Phillips, Dmitry Yershov, Farzad Niroui, Tong Zhao, Leonor Fermoselle, Xinghao Zhu, Chao Cao, Duy Ta, Tao Pang, Jiuguang Wang, Preston Culbertson, Zachary Manchester, Simon Le Cleac'h To appear in IEEE Transactions on Robot Learning, 2026 [paper](https://arxiv.org/abs/2604.08508) | [website](https://sumo.rai-inst.com/) | [code](https://github.com/rai-opensource/sumo) ![Equivariant Diffusion Policy for Sample-Efficient Robotic Manipulation](https://www.robo.guru/assets/build/equidiff.C3KbQU_2_ZqMOh8.png) ## Equivariant Diffusion Policy for Sample-Efficient Robotic Manipulation Dian Wang, Stephen Hart, David Surovik, Tarik Kelestemur, Haojie Huang, Haibo Zhao, Mark Yeatman, Xupeng Zhu, Boce Hu, Mingxi Jia, Jiuguang Wang, Robin Walters, Robert Platt International Journal of Robotics Research, February 2026 CoRL 2024 Outstanding Paper Award Finalist [paper](https://journals.sagepub.com/doi/10.1177/02783649261424445) | [website](https://equidiff.github.io/) | [code](https://github.com/pointW/equidiff) ![SAGA: Open-World Mobile Manipulation via Structured Affordance Grounding](https://www.robo.guru/assets/build/saga.DBSrTE1z_A6cfq.png) ## SAGA: Open-World Mobile Manipulation via Structured Affordance Grounding Kuan Fang, Yuxin Chen, Xinghao Zhu, Farzad Niroui, Lingfeng Sun, Jiuguang Wang IEEE Robotics and Automation Letters, vol. 11, no. 9, pp. 10361-10368, September 2026 [paper](https://arxiv.org/abs/2512.12842) | [website](https://robot-saga.github.io/) | code (coming soon) ## CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph Yixuan Wang, Leonor Fermoselle, Tarik Kelestemur, Jiuguang Wang, Yunzhu Li IEEE Robotics and Automation Letters, vol. 11, no. 4, pp. 4993-5000, April 2026 [paper](https://arxiv.org/abs/2501.13338) | [website](https://bdaiinstitute.github.io/curiousbot/) | code (coming soon) ## From Pixels to Predicates: Learning Symbolic World Models Via Pretrained VLMs Ashay Athalye, Nishanth Kumar, Tom Silver, Yichao Liang, Jiuguang Wang, Tomás Lozano-Pérez, Leslie Pack Kaelbling IEEE Robotics and Automation Letters, vol. 11, no. 4, pp. 4002-4009, April 2026 [paper](https://arxiv.org/abs/2501.00296) | [website](https://pix2pred.csail.mit.edu/) | [code](https://github.com/Learning-and-Intelligent-Systems/predicators/releases/tag/pix2pred-april2025) ![Generative Models From and for Sampling-Based MPC: A Bootstrapped Approach for Adaptive Contact-Rich Manipulation](https://www.robo.guru/assets/build/smpc.B53GH9sV_Z1nwu3V.png) ## Generative Models From and for Sampling-Based MPC: A Bootstrapped Approach for Adaptive Contact-Rich Manipulation Lara Brudermüller, Brandon Hung, Xinghao Zhu, Jiuguang Wang, Nick Hawes, Preston Culbertson, Simon Le Cleac'h IEEE Robotics and Automation Letters, vol. 11, no. 3, pp. 3478-3485, March 2026 [paper](https://arxiv.org/abs/2510.14643) | website (coming soon) | code (coming soon) ![Judo: A User-Friendly Open-Source Package for Sampling-Based Model Predictive Control](https://www.robo.guru/assets/build/judo.Bwwp-A8__2tu8oE.png) ## Judo: A User-Friendly Open-Source Package for Sampling-Based Model Predictive Control Albert H. Li, Brandon Hung, Jan Brüdigam, Aaron D. Ames, Jiuguang Wang, Simon Le Cleac'h, Preston Culbertson IEEE International Conference on Robotics and Automation (ICRA), Vienna, Austria, June 2026 [paper](https://arxiv.org/abs/2506.17184) | [website](https://bdaiinstitute.github.io/judo/) | [code](https://github.com/bdaiinstitute/judo) ![ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis](https://www.robo.guru/assets/build/ashita.D6YufgSQ_1s9ghU.png) ## ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis Yun Chang, Leonor Fermoselle, Duy Ta, Bernadette Bucher, Luca Carlone, Jiuguang Wang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, pp. 29458-29468, June 2025 [paper](https://arxiv.org/abs/2504.06553) | code (coming soon) ## Physics-Driven Data Generation for Contact-Rich Manipulation via Trajectory Optimization Lujie Yang, H. J. Terry Suh, Tong Zhao, Bernhard Paus Graesdal, Tarik Kelestemur, Jiuguang Wang, Tao Pang, Russ Tedrake Robotics: Science and Systems (RSS), Los Angeles, CA, USA, June 2025 [paper](https://arxiv.org/abs/2502.20382) | [website](https://lujieyang.github.io/physicsgen/) | code (coming soon) ## Versatile Loco-Manipulation through Flexible Interlimb Coordination Xinghao Zhu, Yuxin Chen, Lingfeng Sun, Farzad Niroui, Simon Le Cleac'h, Jiuguang Wang, Kuan Fang Conference on Robot Learning (CoRL), Seoul, Korea, PMLR vol. 305, pp. 610-632, September 2025 [paper](https://arxiv.org/abs/2506.07876) | [website](https://relic-locoman.rai-inst.com/) | [code](https://github.com/bdaiinstitute/relic) ![Should We Learn Contact-Rich Manipulation Policies from Sampling-Based Planners?](https://www.robo.guru/assets/build/learncrm.CK7wwS8e_1mHvD9.png) ## Should We Learn Contact-Rich Manipulation Policies from Sampling-Based Planners? Huaijiang Zhu, Tong Zhao, Xinpei Ni, Jiuguang Wang, Kuan Fang, Ludovic Righetti, Tao Pang IEEE Robotics and Automation Letters, vol. 10, no. 6, pp. 6248-6255, June 2025 2025 IEEE Robotics and Automation Letters Best Paper Award [paper](https://arxiv.org/abs/2412.09743) ## Is Linear Feedback on Smoothed Dynamics Sufficient for Stabilizing Contact-Rich Plans? Yuki Shirai, Tong Zhao, H. J. Terry Suh, Huaijiang Zhu, Xinpei Ni, Jiuguang Wang, Max Simchowitz, Tao Pang IEEE International Conference on Robotics and Automation (ICRA), Atlanta, GA, USA, pp. 11926-11932, May 2025 [paper](https://arxiv.org/abs/2411.06542) ![EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomy](https://www.robo.guru/assets/build/evora.BLQMnfqD_1WApca.png) ## EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomy Xiaoyi Cai, Siddharth Ancha, Lakshay Sharma, Philip R. Osteen, Bernadette Bucher, Stephen Phillips, Jiuguang Wang, Michael Everett, Nicholas Roy, Jonathan P. How IEEE Transactions on Robotics, vol. 40, pp. 3756-3777, 2024 [paper](https://arxiv.org/abs/2311.06234) | [website](https://xiaoyi-cai.github.io/evora/) | [code](https://github.com/mit-acl/mppi_numba) ## VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation Naoki Yokoyama, Sehoon Ha, Dhruv Batra, Jiuguang Wang, Bernadette Bucher IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan, pp. 42-48, May 2024 Best Paper Award in Cognitive Robotics [paper](https://arxiv.org/abs/2312.03275) | [website](https://naoki.io/portfolio/vlfm) | [code](https://github.com/bdaiinstitute/vlfm) ## GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy Yixuan Wang, Guang Yin, Binghao Huang, Tarik Kelestemur, Jiuguang Wang, Yunzhu Li Conference on Robot Learning (CoRL), Munich, Germany, PMLR vol. 270, pp. 4866-4878, November 2024 [paper](https://arxiv.org/abs/2410.17488) | [website](https://robopil.github.io/GenDP/) | [code](https://github.com/WangYixuan12/gendp) ## Jacta: A Versatile Planner for Learning Dexterous and Whole-body Manipulation Jan Brüdigam, Ali Adeeb Abbas, Maks Sorokin, Kuan Fang, Brandon Hung, Maya Guru, Stefan Georg Sosnowski, Jiuguang Wang, Sandra Hirche, Simon Le Cleac'h Conference on Robot Learning (CoRL), Munich, Germany, PMLR vol. 270, pp. 994-1020, November 2024 [paper](https://arxiv.org/abs/2408.01258) | [website](https://jacta-manipulation.github.io/) | [code](https://github.com/bdaiinstitute/jacta-manipulation) ## Continuously Improving Mobile Manipulation with Autonomous Real-World RL Russell Mendonca, Emmanuel Panov, Bernadette Bucher, Jiuguang Wang, Deepak Pathak Conference on Robot Learning (CoRL), Munich, Germany, PMLR vol. 270, pp. 5204-5219, November 2024 [paper](https://arxiv.org/abs/2409.20568) | [website](https://continual-mobile-manip.github.io/) ![Equivariant Diffusion Policy](https://www.robo.guru/assets/build/equidiff.C3KbQU_2_ZqMOh8.png) ## Equivariant Diffusion Policy Dian Wang, Stephen Hart, David Surovik, Tarik Kelestemur, Haojie Huang, Haibo Zhao, Mark Yeatman, Jiuguang Wang, Robin Walters, Robert Platt Conference on Robot Learning (CoRL), Munich, Germany, PMLR vol. 270, pp. 48-69, November 2024 CoRL 2024 Outstanding Paper Award Finalist [paper](https://arxiv.org/abs/2407.01812) | [website](https://equidiff.github.io/) | [code](https://github.com/pointW/equidiff)