About

Kris Hauser is a Professor in the Department of Computer Science, the Department of Electrical and Computer Engineering, and the Department of Mechanical Science and Engineering at the University of Illinois at Urbana-Champaign. His research interests lie in robot planning and control, a field devoted to providing the decision-making capabilities needed for robots and other intelligent agents to perform complex physical tasks. His research builds upon the theoretical foundations of state space dynamics and optimality, but attempts to overcome the shortcomings of classical theory when faced the complexities of real-world systems, such as high dimensionality, uncertain dynamics, bounded computation, and integration with perception and learning. The methodologies at the foundation of this work include optimization, probabilistic methods, AI, control theory, and physics simulation, and theory is bridged with practice on real-world physical robots in the context of a diverse range of applications with social impact, including robot locomotion and manipulation, medical robots, human-operated robots, warehouse automation, and intelligent vehicles. Prof. Hauser received his PhD in Computer Science from Stanford University in 2008, bachelor's degrees in Computer Science and Mathematics from UC Berkeley in 2003, and worked as a postdoctoral fellow at UC Berkeley. He then joined the faculty at Indiana University from 2009-2014, where he started the Intelligent Motion Lab, and then joined the faculty of Duke University from 2014-2019. He is a recipient of a Stanford Graduate Fellowship, Siebel Scholar Fellowship, Best Paper Award at IEEE International Conference on Humanoid Robots 2015, the NSF CAREER award, and two Amazon Research Awards. He also works as a consultant for Google's autonomous driving company, Waymo.

Research topics

• Computer Science
• Artificial Intelligence
• Engineering
• Computer vision
• Biomedical engineering
• Medicine
• Distributed computing
• Operating system
• Embedded system
• Radiology
• Surgery
• Physics
• Human–computer interaction
• Ophthalmology
• Optics
• Mathematical optimization
• Systems engineering
• Mathematics
• Algorithm
• Programming language
• Real-time computing
• Medical physics

Selected publications

• 376 Cadaveric, Ovine, and Pilot User Evaluations for Low Cost, Real-Time Articulated Arm Surgical Navigation

  Neurosurgery · 2026-03-26

  article
  PublisherDOI

• Simulation-Ready Cluttered Scene Estimation via Physics-aware Joint Shape and Pose Optimization

  arXiv (Cornell University) · 2026-02-23

  preprintOpen accessSenior author

  Estimating simulation-ready scenes from real-world observations is crucial for downstream planning and policy learning tasks. Regretfully, existing methods struggle in cluttered environments, often exhibiting prohibitive computational cost, poor robustness, and restricted generality when scaling to multiple interacting objects. We propose a unified optimization-based formulation for real-to-sim scene estimation that jointly recovers the shapes and poses of multiple rigid objects under physical constraints. Our method is built on two key technical innovations. First, we leverage the recently introduced shape-differentiable contact model, whose global differentiability permits joint optimization over object geometry and pose while modeling inter-object contacts. Second, we exploit the structured sparsity of the augmented Lagrangian Hessian to derive an efficient linear system solver whose computational cost scales favorably with scene complexity. Building on this formulation, we develop an end-to-end Simulation-ready Physics-Aware Reconstruction for Cluttered Scenes (SPARCS) pipeline, which integrates learning-based object initialization, physics-constrained joint shape-pose optimization, and differentiable texture refinement. Experiments on cluttered scenes with up to 5 objects and 22 convex hulls demonstrate that our approach robustly reconstructs physically valid, simulation-ready object shapes and poses. Project webpage: https://rory-weicheng.github.io/SPARCS/.

  PublisherDOI

• Simulation-Ready Cluttered Scene Estimation via Physics-aware Joint Shape and Pose Optimization

  ArXiv.org · 2026-01-01

  articleOpen accessSenior author

  Estimating simulation-ready scenes from real-world observations is crucial for downstream planning and policy learning tasks. Regretfully, existing methods struggle in cluttered environments, often exhibiting prohibitive computational cost, poor robustness, and restricted generality when scaling to multiple interacting objects. We propose a unified optimization-based formulation for real-to-sim scene estimation that jointly recovers the shapes and poses of multiple rigid objects under physical constraints. Our method is built on two key technical innovations. First, we leverage the recently introduced shape-differentiable contact model, whose global differentiability permits joint optimization over object geometry and pose while modeling inter-object contacts. Second, we exploit the structured sparsity of the augmented Lagrangian Hessian to derive an efficient linear system solver whose computational cost scales favorably with scene complexity. Building on this formulation, we develop an end-to-end real-to-sim scene estimation pipeline that integrates learning-based object initialization, physics-constrained joint shape-pose optimization, and differentiable texture refinement. Experiments on cluttered scenes with up to 5 objects and 22 convex hulls demonstrate that our approach robustly reconstructs physically valid, simulation-ready object shapes and poses.

  PublisherOA PDF

• Flexible Multitask Learning With Factorized Diffusion Policy

  IEEE Robotics and Automation Letters · 2026-02-13

  articleOpen access

  Multitask learning poses significant challenges due to the highly multimodal and diverse nature of robot action distributions. However, effectively fitting policies to these complex task distributions is often difficult, and existing monolithic models often underfit the action distribution and lack the flexibility required for efficient adaptation. We introduce a novel modular diffusion policy framework that factorizes complex action distributions into a composition of specialized diffusion models, each capturing a distinct sub-mode of the behavior space for a more effective overall policy. In addition, this modular structure enables flexible policy adaptation to new tasks by adding or fine-tuning components, which inherently mitigates catastrophic forgetting. Empirically, across both simulation and real-world robotic manipulation settings, we illustrate how our method consistently outperforms strong modular and monolithic baselines. Website: factorized-diffusion-policy.github.io.

  PublisherDOI

• Map Space Belief Prediction for Manipulation-Enhanced Mapping

  ArXiv.org · 2025-02-28

  preprintOpen accessSenior author

  Searching for objects in cluttered environments requires selecting efficient viewpoints and manipulation actions to remove occlusions and reduce uncertainty in object locations, shapes, and categories. In this work, we address the problem of manipulation-enhanced semantic mapping, where a robot has to efficiently identify all objects in a cluttered shelf. Although Partially Observable Markov Decision Processes~(POMDPs) are standard for decision-making under uncertainty, representing unstructured interactive worlds remains challenging in this formalism. To tackle this, we define a POMDP whose belief is summarized by a metric-semantic grid map and propose a novel framework that uses neural networks to perform map-space belief updates to reason efficiently and simultaneously about object geometries, locations, categories, occlusions, and manipulation physics. Further, to enable accurate information gain analysis, the learned belief updates should maintain calibrated estimates of uncertainty. Therefore, we propose Calibrated Neural-Accelerated Belief Updates (CNABUs) to learn a belief propagation model that generalizes to novel scenarios and provides confidence-calibrated predictions for unknown areas. Our experiments show that our novel POMDP planner improves map completeness and accuracy over existing methods in challenging simulations and successfully transfers to real-world cluttered shelves in zero-shot fashion.

  PublisherOA PDFDOI

• Memory-Efficient Real Time Many-Class 3D Metric-Semantic Mapping

  2025-10-19

  articleSenior author

  Metric-semantic 3D mapping is the process of creating class-labeled 3D maps by fusing the information from images captured by a moving camera. The memory usage required by standard solutions grows linearly with the number of semantic classes being considered, which can pose a bottleneck in large and many-class scenes. This paper proposes two novel methods for compressing the memory used by semantic fusion: calibrated top-k histogram and encoded fusion. The first method maintains, for each voxel, only the counts of the k most likely classes, while the second method uses a neural network to encode all-class probability vectors into a k-dimensional latent space in which per-voxel fusion is performed. The fused result is then decoded, at query time, using another neural network. Experiments show that both methods preserve map accuracy and calibration even at low values of k, and per-voxel memory usage is linear in k. The proposed methods can achieve real-time semantic fusion with 150 classes on commodity GPUs in building-scale scenes where prior approaches run out of memory.

  PublisherDOI

• UnityEyes 2: Open source robust synthetic eye generation for camera-based eye tracking with machine learning

  2025-05-24 · 1 citations

  articleSenior author
  PublisherDOI

• Particle-Grid Neural Dynamics for Learning Deformable Object Models from RGB-D Videos

  ArXiv.org · 2025-06-18

  preprintOpen access

  Modeling the dynamics of deformable objects is challenging due to their diverse physical properties and the difficulty of estimating states from limited visual information. We address these challenges with a neural dynamics framework that combines object particles and spatial grids in a hybrid representation. Our particle-grid model captures global shape and motion information while predicting dense particle movements, enabling the modeling of objects with varied shapes and materials. Particles represent object shapes, while the spatial grid discretizes the 3D space to ensure spatial continuity and enhance learning efficiency. Coupled with Gaussian Splattings for visual rendering, our framework achieves a fully learning-based digital twin of deformable objects and generates 3D action-conditioned videos. Through experiments, we demonstrate that our model learns the dynamics of diverse objects -- such as ropes, cloths, stuffed animals, and paper bags -- from sparse-view RGB-D recordings of robot-object interactions, while also generalizing at the category level to unseen instances. Our approach outperforms state-of-the-art learning-based and physics-based simulators, particularly in scenarios with limited camera views. Furthermore, we showcase the utility of our learned models in model-based planning, enabling goal-conditioned object manipulation across a range of tasks. The project page is available at https://kywind.github.io/pgnd .

  PublisherOA PDFDOI

• A Low-Cost Articulated Arm Navigation System for External Ventricular Drain Placement

  IEEE Transactions on Medical Robotics and Bionics · 2025-05-26

  articleOpen accessSenior author

  Objective: This paper proposes a low-cost real-time navigation system to assist a surgeon in placing external ventricular drains. Methods: In our approach, the base of an articulated arm coordinate measuring machine is bolted to the patient's skull, and a graphical user interface quickly guides the operator through the image registration and 3D navigation to place an external ventricular drain at a desired target specified relative to preoperative imaging. The method can be employed in workflows with and without fiducials embedded in the preoperative imaging. Results: The proposed system is evaluated using precise registration instruments, human phantom models, and ex vivo ovine models, demonstrating less than 2 mm of error with fiducials and less than 4 mm of error without fiducials. Conclusion: The registration procedure takes less than one minute and can be performed intuitively by a single operator without an assistant. Significance: Our proposed system enables real-time image-guided navigation to be used in bedside external ventricular drain placement, with potential to expand access to this procedure.

  PublisherDOI

• The EYESIGHT Robotic Eye Examination System for Nonmydriatic Indirect Retinal Imaging on Unconstrained Individuals

  Journal of Medical Robotics Research · 2025-12-06

  articleSenior author

  This paper presents an automated, contactless posterior eye examination system that can perform nonmydriatic retinal examinations at safe distances from unconstrained individuals. The system operates in a dimly lit room, tracking the patient’s face and anatomy using infrared cameras, collecting screening-quality visible light images using flash photography when the patient’s pupil is aligned. The sensor system is mounted on a robot arm, which tracks the center of the patient’s head motion, locks onto the pupil, and captures images of the retina. The behavior control system completes an examination of both eyes and ensures that images are captured with minimal artifact. Feasibility studies on a phantom and users from the research team indicate that the system completes screening-quality bilateral retinal imaging in under 2[Formula: see text]min.

  PublisherDOI

Recent grants

• NRI: INT: Customizing Semi-Autonomous Nursing Robots Using Human Expertise

  NSF · $963k · 2018–2020

• RI: Small: Discovery and Reuse of Domain Knowledge in Large Motion Planning Systems

  NSF · $381k · 2012–2015

• CAREER: Cooperative Motion Planning for Human-Operated Robots

  NSF · $284k · 2013–2015

• RI: Small: Pose and Trajectory Optimization with Pervasive Contact

  NSF · $500k · 2019–2025

• RI: Small: Exploiting Global Structure in Robot Decision Problems

  NSF · $349k · 2018–2020

Frequent coauthors

• Gao Tang

  University of Illinois Urbana-Champaign

  19 shared

• Anthony N. Kuo

  Duke University

  18 shared

• Philip Hahnfeldt

  16 shared

• Joseph A. Izatt

  Duke University

  16 shared

• Mark Draelos

  University of Michigan–Ann Arbor

  14 shared

• Zherong Pan

  13 shared

• Christian Schwager

  12 shared

• Peter E. Huber

  Heidelberger Institut für Radioonkologie

  12 shared

Education

• Ph.D., Computer Science

  University of Illinois at Urbana-Champaign

  2000

• M.S., Computer Science

  University of Illinois at Urbana-Champaign

  1996

• B.S., Computer Science

  University of Illinois at Urbana-Champaign

  1994

Awards & honors

• Stanford Graduate Fellowship
• Siebel Scholar Fellowship
• Best Paper Award at IEEE International Conference on Humanoi…
• NSF CAREER award
• Amazon Research Awards (two)