Algorithmic Human Robot Interaction
Cooperative Motion Planning
This project explores the hypothesis that advances in robot motion planning algorithms will lead to improved intuitiveness, safety, and task performance of human-centered robots such as intelligent vehicles, tele-surgery systems, search-and-rescue robots, and household robots. Existing planning techniques lead to awkward and unintuitive interaction with humans. To bridge this gap, we are developing cooperative motion planning algorithms that reason about users' intended goals and then take control of a robot's low level motion to achieve those goals.
Funding: IU Faculty Research Support Program (FSRP).
K. Hauser. Recognition, Prediction, and Planning for Assisted Teleoperation with Freeform Tasks. In Robotics: Science and Systems, Sydney, Australia, July 2012.
J. Luo and K. Hauser. Interactive Generation of Dynamically Feasible Robot Trajectories from Sketches Using Temporal Mimicking. In IEEE Int'l Conference on Robotics and Automation (ICRA), Minneapolis, May 2012.
K. Hauser. On Responsiveness, Safety, and Completeness in Real-Time Motion Planning. Autonomous Robots, 32(1):35-48, 2012.
E. You and K. Hauser. Assisted Teleoperation Strategies for Aggressively Controlling a Robot Arm with 2D Input. In Robotics: Science and Systems, Los Angeles, July 2011.
Motion Planning and Decision-Making
Integrating Task, Contact, and Motion Planning
We developed the Random-MMP and Multi-Modal-PRM sample-based motion planners for hybrid systems with contact, and have applied them to problems in manipulation and legged locomotion in rough terrain. These algorithms possess formal reliablility and scalablility properties that make them suitable for high-dimensional planning problems with complex constraints.
Funding: NSF Robust Intelligence Grant #1218534.
K. Hauser. The Minimum Constraint Removal Problem with Three Robotics Applications. In Workshop on the Algorithmic Foundations of Robotics, Boston, June 2012.
K. Hauser and V. Ng-Thow-Hing. Randomized Multi-Modal Motion Planning for a Humanoid Robot Manipulation Task. In International Journal of Robotics Research, 30(6):678-698, 2011. doi: 10.1177/0278364910386985.
K. Hauser. Task Planning with Continuous Actions and Nondeterministic Motion Planning Queries. In proceedings of AAAI Workshop on Bridging the Gap between Task and Motion Planning, Atlanta, USA, July 11, 2010.
K. Hauser and J.-C. Latombe. Multi-Modal Motion Planning in Non-Expansive Spaces. In International Journal of Robotics Research, 29(7):897-915, 2010. doi 10.1177/0278364909352098
K. Hauser and J.-C. Latombe. Integrating task and PRM motion planning: Dealing with many infeasible motion planning queries. In proceedings of ICAPS 2009 Workshop on Bridging the Gap Between Task and Motion Planning, Thessaloniki, Greece, Sep. 2009.
K. Hauser and J.-C. Latombe, Multi-Modal Motion Planning for Non-Expansive Spaces. In the Workshop on the Algorithm Foundations of Robotics (WAFR), Guanajuato, Mexico, Dec. 2008.
K. Hauser, Motion Planning for Legged and Humanoid Robots. Ph.D. Thesis, Stanford University, September 2008.
(8.9mb, single sided)
Decision-Making under Uncertainty
Interests include extending POMDP methods to handle high-dimensional continuous observation, state, and action spaces, and meta-planning for finding optimal problem-solving strategies for computational systems. Promising results have been obtained for robot navigation in up to 7D with position uncertainty and target pursuit with sensing constraints.
K. Hauser. Online Planning in Continuous POMDPs with Open-Loop Information-Gathering Plans.. In ICML Workshop on Planning and Acting with Uncertain Models, Seattle, USA, July, 2011.
K. Hauser. Randomized Belief-Space Replanning in Partially-Observable Continuous Spaces. In Workshop on the Algorithmic Foundations of Robotics, Singapore, 2010.
K. Hauser. A Decision-Theoretic Formalism for Belief-Optimal Reasoning. In proceedings of Performance Measurement for Intelligent Systems Workshop (PerMIS), Gaithersburg, MD, Sep. 2009.
K. Hauser, Motion Planning for Legged and Humanoid Robots. Ph.D. Thesis, Stanford University, September 2008.
(8.9mb, single sided)
Dynamic and Real-Time Planning
Planning for Highly Dynamic Systems
Current topics of study are optimal planning under time-varying objective functions, avoiding collisions with dynamic obstacles, and highly dynamic manipulation tasks.
Y. Zhang, J. Luo, and K. Hauser. Sampling-based Motion Planning With Dynamic Intermediate State Objectives: Application to Throwing. In IEEE Int'l Conference on Robotics and Automation (ICRA), Minneapolis, May 2012.
J. Luo and K. Hauser. Interactive Generation of Dynamically Feasible Robot Trajectories from Sketches Using Temporal Mimicking. In IEEE Int'l Conference on Robotics and Automation (ICRA), Minneapolis, May 2012.
J. Johnson and K. Hauser. Optimal Acceleration-Bounded Trajectory Planning in Dynamic Environments Along a Specified Path. In IEEE Int'l Conference on Robotics and Automation (ICRA), Minneapolis, May 2012.
J. Johnson and K. Hauser. Optimal Longitudinal Control Planning with Moving Obstacles. In proceedings of IEEE Int’l Intelligent Vehicles Symposium, May 2013. (oral presentation)
Example videos for temporal mimicking of human sketches (ICRA 2012).
Example videos for exact, optimal trajectory planning with dozens of moving obstacles (ICRA 2012).
Example videos for generalized trajectory planning with moving obstacles (IVS 2012).
Adaptive Time Stepping in Real-Time Planning
Real-time replanning systems induce an inherent completeness-responsiveness-safety tradeoff induced by bounded computational resources. We introduces an adaptive time-stepping architecture that is proven to be asymptotically complete in a deterministic environment with changing goals. Empirical results also demonstrate that it achieves safer motion in unpredictably dynamic environments than other state-of-the-art techniques. The scheme has been applied to assisted teleoperation of a 6DOF robot arm, as well as navigation amongst unpredictable moving obstacles.
K. Hauser. On Responsiveness, Safety, and Completeness in Real-Time Motion Planning. Autonomous Robots, 32(1):35-48, 2012.
E. You and K. Hauser. Assisted Teleoperation Strategies for Aggressively Controlling a Robot Arm with 2D Input. In Robotics: Science and Systems, Los Angeles, July 2011.
K. Hauser. Adaptive Time Stepping in Real-Time Motion Planning. In Workshop on the Algorithmic Foundations of Robotics, Singapore, 2010.
Fast Smoothing of Manipulator Trajectories
A second project addresses the fact that sample-based motion planners are fast, but they typically output jerky paths. A new fast postprocessing technique uses time-optimal bounded-acceleration "shortcuts" to smooth paths with little overhead. It is particularly effective for on-line smoothing during execution. (A software library is available)
K. Hauser and V. Ng-Thow-Hing. Fast Smoothing of Manipulator Trajectories using Optimal Bounded-Acceleration Shortcuts. To appear in IEEE Int'l Conference on Robotics and Automation (ICRA) 2010.
A grasping motion before smoothing
MPEG, 0.8mb
A grasping motion after smoothing
MPEG, 0.5mb
A PUMA760 manipulator smoothly picking and placing cups.
MPEG, 9.4mb
Leaving Flatland: Real-Time 3D Perception and Motion Planning (inactive)
R. B. Rusu, A. Sundaresan, B. Morisset, K. Hauser, M. Agrawal, J.-C. Latombe, M. Beetz. Leaving Flatland: Efficient real-time three-dimensional perception and motion planning. In Journal of Field Robotics, 26(10):841-862, 2009.
B. Morisset, R.B. Rusu, A. Sundaresan, K. Hauser, M. Agrawal, J.-C. Latombe, and M. Beetz, Leaving Flatland. Toward Real-Time 3D Navigation. In proceedings of IEEE Intl. Conf. of Robotics and Automation (ICRA), Kobe, Japan, May 2009.
A 3D model of outdoor terrain captured using real time stereo vision.
Windows Media, 11.4 mb
Motion plan for the RHex robot climbing two stairs
Windows Media, 1.7 mb
Medical and Biological Applications
Clinical Decision Support
The explosion in the amount of medical data available in Electronic Medical Records (EMRs) provides an opportunity for computers to aid clinicians in providing effective, affordable healthcare. We are investigating Markov Decision Process techniques that are able to recommend patient-specific treatment plans in the presence of noisy and incomplete observations. Like a real doctor, the system is able to reason in the space of belief states, integrating uncertainties and contingencies into its plans. Results on a 5,807 patient dataset involving clinical depression as well as co-occuring conditions suggest that the decisions made by an AI system can improve patient outcomes from 30-35% while reducing costs by 50-55%.
C. Bennett and K. Hauser. Artificial Intelligence Framework for Simulating Clinical Decision-Making: A Markov Decision Process Approach. In Artificial Intelligence in Medicine, 2012. doi: 10.1016/j.artmed.2012.12.003.
Protein loop conformation sampling
Protein loops are flexible structures that are intimately tied to function, but understanding loop motion and generating loop conformation ensembles remain significant computational challenges. We have developed a new Markov chain Monte Carlo algorithm, Sub-Loop Inverse Kinematics Monte Carlo (SLIKMC), for generating conformations of closed loops according to experimentally available, heterogeneous structural preferences. Our simulation experiments demonstrate that the method computes high-scoring conformations of large loops (>10 residues) orders of magnitude faster than standard Monte Carlo and discrete search techniques. Protein conformations with 100+ residues are sampled on standard PC hardware in seconds. Application to proteins involved in ion-binding demonstrate its potential as a tool for loop ensemble generation and missing structure completion.
Y. Zhang and K. Hauser. Unbiased, scalable sampling of protein loop conformations from probabilistic priors. To appear in BMC Structural Biology, 2013.
Y. Zhang, K. Hauser, and J. Luo. Unbiased, Scalable Sampling of Closed Kinematic Chains. In proceedings of IEEE Int'l Conference on Robotics and Automation (ICRA), Karlsruhe, Germany, May 2013.
Y. Zhang and K. Hauser. Unbiased, Scalable Sampling of Constrained Kinematic Loops. In BIBM 2012 Computational Structural Biology Workshop. October, 2012.
Simulation and Control of Steerable Needles in Deformable Tissue (inactive)
Using imaging feedback we can control a new type of steerable needles with high accuracy in deformable tissue. New interactive simulators and motion planners can also be used for training medical personnel to use these new medical devices.
N. Chentanez, R. Alterovitz, D. Richie, J. Cho, K. Hauser, K. Goldberg, J.R. Shewchuk, and J. O'Brien, Interactive Simulation of Surgical Needle Insertion and Steering. In ACM SIGGRAPH, New Orleans, LA, 2009.
K. Hauser, R. Alterovitz, N. Chentanez, A. Okamura, and K. Goldberg, Feedback Control for Steering Needles Through 3D Deformable Tissue Using Helical Paths. In Robotics: Science and Systems, Seattle, WA, 2009.
Needle steering controller in "rigid" tissue.
Windows Media, 0.4 mb
Needle steering controller in deformable tissue.
Windows Media, 0.4 mb
FEM simulations of steerable needle insertions (link)
Planning and Control of Soft Tissue Manipulation (inactive)
Tissue manipulation tasks in robotic laparoscopic surgery can be automated to help relieve surgeon fatigue and enable new medical procedures that involve the simultaneous control of many hands. Tissue manipulation can also be used in conjunction with needle insertion procedures to improve targeting accuracy. Preoperative planning algorithms use finite element models of deformable tissue to select contact points that achieve the desired task robustly while avoiding tissue damage.
R. Jansen, K. Hauser, N. Chentanez, F. van der Stappen, and K. Goldberg, Surgical Retraction of Non-Uniform Deformable Layers of Tissue: 2D Robot Grasping and Path Planning. In proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), St. Louis, Oct. 2009.
M. Torabi, K. Hauser, R. Alterovitz, V. Duindam, and K. Goldberg, Guiding Medical Needles Using Single-Point Tissue Manipulation. In proceedings of IEEE Intl. Conf. of Robotics and Automation (ICRA), Kobe, Japan, May 2009. Best Medical Robotics Paper Finalist
Example video
Windows Media, 2.9 mb
Robotic Manipulation and Legged Locomotion
Agile Locomotion for Disaster Relief Humanoids
Funding: DARPA Robotics Challenge (Track A)
Y. Zhang, J. Luo, K. Hauser, R. Ellenberg, P. Oh, H.A. Park, M. Paldhe, and C.S.G. Lee. Motion Planning of Ladder Climbing for Humanoid Robots. To appear in IEEE Conf. on Technologies for Practical Robot Applications (TePRA), 2013.
Precise Pushing on the Asimo Humanoid (inactive)
K. Hauser and V. Ng-Thow-Hing. Multi-Modal Motion Planning for Precision Pushing on a Humanoid Robot. In K. Harada, E. Yoshida, and K. Yokoi (eds), Motion Planning for Humanoid Robots, Springer, 2010.
V. Ng-Thowhing, E. Drumwright, K. Hauser, Q. Wu, and J. Wormer, Expanding Task Functionality in Established Humanoid Robots. In proceedings of IEEE Conference on Humanoid Robots, 2007.
K. Hauser, V. Ng-Thow-Hing, H. Gonzalez-Banos, Multi-Modal Motion Planning for a Humanoid Manipulation Task. In proceedings of the International Symposium on Robotics Research (ISRR) 2007.
Legged Locomotion in Rough Terrain (inactive)
K. Hauser. On the Connectivity of Motion Spaces for Biologically-Inspired Legged Robots. In proceedings of IROS 2009 Workshop on Biologically-Inspired Robots, St. Louis, Oct. 2009.
K. Hauser, Motion Planning for Legged and Humanoid Robots. Ph.D. Thesis, Stanford University, September 2008.
(8.9mb, single sided)
K. Hauser, T. Bretl, J.-C. Latombe, Motion planning for legged robots on varied terrain. In Intl. J. of Robotics Research 27(11-12):1325-1349, 2008.
K. Hauser, T. Bretl, J.-C. Latombe, Using Motion Primitives in Probabilistic Sample-Based Planning for Humanoid Robots. In proceedings of the Workshop on the Algorithmic Foundations of Robotics (WAFR) 2006
K. Hauser, T. Bretl, J.-C. Latombe, B. Wilcox, Motion Planning for a Six-Legged Lunar Robot. In proceedings of the Workshop on the Algorithmic Foundations of Robotics (WAFR) 2006
K. Hauser, T. Bretl, J.-C. Latombe, Non-gaited Humanoid Locomotion Planning. In proceedings of IEEE Intl. Conf. of Humanoid Robots 2005
K. Hauser, T. Bretl, J.-C. Latombe, Learning-Assisted Multi-Step Planning. In proceedings of IEEE Intl. Conf. of Robotics and Automation (ICRA), 2005
