Published in: Conference on Robot Learning (CoRL), 2025 Christopher Agia, Rohan Sinha, Jingyun Yang, Rika Antonova, Marco Pavone, Haruki Nishimura, Masha Itkina, Jeannette Bohg[Link to PDF][Link to Publisher Site][Link to Code] In robot imi…
Modern generative models have enabled robots to acquire challenging dexterous skills directly from human demonstrations. Yet, even the state-of-the-art learned policies, such as TRI’s Large Behavior Model (LBM), often suffer unexpected fail…
Published in: Robotics: Science and Systems (RSS), 2025 Chen Xu, Tony Khuong Nguyen, Emma Dixon, Christopher Rodriguez, Patrick Miller, Robert Lee, Paarth Shah, Rares Andrei Ambrus, Haruki Nishimura, Masha Itkina[Link to PDF][Link to Publis…
Published in: Robotics: Science and Systems (RSS), 2025 David Snyder, Asher Hancock, Apurva Badithela, Emma Dixon, Patrick Miller, Rares Ambrus, Anirudha Majumdar, Masha Itkina, Haruki Nishimura[Link to PDF][Link to Publisher Site][Link to
Published in: IEEE Robotics and Automation Letters (RA-L), 2024 Joseph A. Vincent, Haruki Nishimura, Masha Itkina, Paarth Shah, Mac Schwager, Thomas Kollar[Link to PDF][Link to Publisher Site][Link to Code] With the rise of stochastic gener…
Published in: Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023 Chenran Li*, Chen Tang*, Haruki Nishimura, Jean Mercat, Masayoshi Tomizuka, Wei Zhan[Link to PDF][Link to Publisher Site] Imitation Learning (I…
Published in: 5th Annual Learning for Dynamics & Control Conference (L4DC), 2023 Fernando Castañeda, Haruki Nishimura, Rowan McAllister, Koushil Sreenath, Adrien Gaidon[Link to PDF][Link to Publisher Site] Learning-based control approaches
Published in: 2022 Conference on Robot Learning (CoRL), 2022 Haruki Nishimura*, Jean Mercat*, Blake Wulfe, Rowan McAllister, Adrien Gaidon[Link to PDF][Link to Publisher Site] Robust planning in interactive scenarios requires predicting the…
Safe planning is critical for human-robot interaction where robot error can cause injury. Risk measures (e.g., CVaR) promote safety of robot plans, whose evaluation is possible in principle using probabilistic forecasts of human motion. Unf…
Published in: Ph.D. Dissertation, Stanford University, 2021 Haruki Nishimura[Link to PDF][Link to Publisher Site] Recent advances in perception, planning, and control have enabled mobile robots to perform complex human-level tasks in many i…
Published in: The International Journal of Robotics Research (IJRR), 2021 Haruki Nishimura, Mac Schwager[Link to PDF][Link to Publisher Site][Link to Code] We propose a novel belief space planning technique for continuous dynamics by viewin…
[Link to Slides][Link to Event] Recent advances in perception, planning, and control have enabled mobile robots to perform complex human-level tasks in many industrial domains. However, most of the robots still lack the capability to consid…