Takayuki Osa

EDBT 2026 Demo / reviewers in the wild / expert

dblp:27/1571 · DBLP profile ↗

← Back

24ranked-venue papers

11as first author

11since 2021 · last 2025

0000-0002-6895-9088ORCID · verified

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 23 · 10 first-author · 11 since 2021Systems, architecture and hardware · 16 · 6 first-author · 6 since 2021Graphics, computer vision, multimedia, augmented reality and games · 2 · 1 first-author · 1 since 2021Applied, interdisciplinary, general and emerging computing · 1 · 1 first-author

Year	Publication	Venue	Position
2025	Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning abstract For continuous action spaces, actor-critic methods are widely used in online reinforcement learning (RL). However, unlike RL algorithms for discrete actions, which generally model the optimal value function using the Bellman optimality operator, RL algorithms for continuous actions typically model Q-values for the current policy using the Bellman operator. These algorithms for continuous actions rely exclusively on policy updates for improvement, which often results in low sample efficiency. This study examines the effectiveness of incorporating the Bellman optimality operator into actor-critic frameworks. Experiments in a simple environment show that modeling optimal values accelerates learning but leads to overestimation bias. To address this, we propose an annealing approach that gradually transitions from the Bellman optimality operator to the Bellman operator, thereby accelerating learning while mitigating bias. Our method, combined with TD3 and SAC, significantly outperforms existing approaches across various locomotion and manipulation tasks, demonstrating improved performance and robustness to hyperparameters related to optimality. The code for this study is available at https://github.com/motokiomura/annealed-q-learning. Motoki Omura, Kazuki Ota, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada	ICML	3
2025	Uncertainty-aware Motion Planning based on Stochastic Forward/Inverse Kinematics Models for Tensegrity Manipulators abstract Robots whose shape and stiffness are determined by internal forces generally have complex shape-stiffness relationships that depend on their structure. As a result, there are difficulties such as a decrease in shape reproducibility when the robot is not stiff, and a decrease in the range of motion when the robot is stiff. In this study, we propose a motion planning method that balances shape and stiffness by learning forward and inverse kinematics using a stochastic neural network (NN) and using the uncertainty that can be evaluated by the NN. Through experiments using a tensegrity manipulator with 40 actuators and 20 degrees of freedom in bending posture, we verify the validity of the proposed method. Yuhei Yoshimitsu, Takayuki Osa, Heni Ben Amor, Shuhei Ikemoto	IROS	2
2024	Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning abstract In deep reinforcement learning, estimating the value function to evaluate the quality of states and actions is essential. The value function is often trained using the least squares method, which implicitly assumes a Gaussian error distribution. However, a recent study suggested that the error distribution for training the value function is often skewed because of the properties of the Bellman operator, and violates the implicit assumption of normal error distribution in the least squares method. To address this, we proposed a method called Symmetric Q-learning, in which the synthetic noise generated from a zero-mean distribution is added to the target values to generate a Gaussian error distribution. We evaluated the proposed method on continuous control benchmark tasks in MuJoCo. It improved the sample efficiency of a state-of-the-art reinforcement learning method by reducing the skewness of the error distribution. Motoki Omura, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada	AAAI	2
2024	Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning abstract Recent studies on online reinforcement learning (RL) have demonstrated the advantages of learning multiple behaviors from a single task, as in the case of few-shot adaptation to a new environment. Although this approach is expected to yield similar benefits in offline RL, appropriate methods for learning multiple solutions have not been fully investigated in previous studies. In this study, we therefore addressed the problem of finding multiple solutions from a single task in offline RL. We propose algorithms that can learn multiple solutions in offline RL, and empirically investigate their performance. Our experimental results show that the proposed algorithm learns multiple qualitatively and quantitatively distinctive solutions in offline RL. Takayuki Osa, Tatsuya Harada	ICML	1
2024	Touch-Based Manipulation with Multi-Fingered Robot using Off-policy RL and Temporal Contrastive Learning abstract Tactile information holds promise for enhancing the manipulation capabilities of multi-fingered robots. In tasks such as in-hand manipulation, where robots frequently switch between contact and non-contact states, it is important to address the partial observability of tactile sensors and to properly consider the history of observations and actions. Previous studies have shown that Recurrent Neural Network (RNN) can be used to learn latent representations for handling observation and action histories. However, this approach is usually combined with on-policy reinforcement learning (RL) and suffers from low sample efficiency. Integrating RNN with off-policy RL could enhance sample efficiency, but this often compromises stability and robustness, especially as the dimensions of observation and action increase. This paper presents a time-contrastive learning approach tailored for off-policy RL. Our method incorporates a temporal contrastive model and introduces a surrogate loss to extract task-related latent representations, enhancing the pursuit of the optimal policy. Simulations and real robot experiments demonstrate that our proposed method outperforms RNN-based approaches. Naoki Morihira, Pranav Deo, Manoj Bhadu, Akinobu Hayashi, Tadaaki Hasegawa, Satoshi Otsubo, Takayuki Osa	ICRA	7
2024	Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration abstract Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x.github.io. Abigail O'Neill, Abhiram Maddukuri, Abhishek Gupta 0004, Abhishek Padalkar, Abraham Lee, Acorn Pooley, Agrim Gupta, Ajay Mandlekar, Ajinkya Jain, Albert Tung, Alex Bewley, Alex Irpan, Alexander Khazatsky, Anant Rai, Anchit Gupta, Andrew E. Wang, Anikait Singh, Animesh Garg, Aniruddha Kembhavi, Annie Xie, Anthony Brohan, Antonin Raffin, Archit Sharma, Arefeh Yavary, Arhan Jain, Ashwin Balakrishna, Ayzaan Wahid, Ben Burgess-Limerick, Bernhard Schölkopf, Blake Wulfe, Brian Ichter, Cewu Lu, Charles Xu 0003, Charlotte Le, Chelsea Finn, Chen Wang 0053, Chenfeng Xu, Cheng Chi 0001, Chenguang Huang, Christine Chan, Christopher Agia, Chuer Pan, Chuyuan Fu, Coline Devin, Danfei Xu, Daniel Morton, Danny Drieß, Daphne Chen, Deepak Pathak, Dhruv Shah, Dieter Büchler, Dinesh Jayaraman, Dmitry Kalashnikov, Dorsa Sadigh, Edward Johns, Ethan Paul Foster, Fangchen Liu, Federico Ceola, Fei Xia 0002, Feiyu Zhao, Freek Stulp, Gaoyue Zhou, Gaurav S. Sukhatme, Gautam Salhotra, Gilbert Feng, Giulio Schiavi, Glen Berseth, Gregory Kahn, Guanzhi Wang, Hao Su 0001, Haoshu Fang, Henghui Bao, Heni Ben Amor, Henrik I. Christensen, Hiroki Furuta, Homer Walke, Hongjie Fang, Huy Ha, Igor Mordatch, Ilija Radosavovic, Isabel Leal, Jacky Liang, Jad Abou-Chakra, Jaehyung Kim 0001, Jaimyn Drake, Jan Peters 0001, Jan Schneider 0007, Jasmine Hsu, Jeannette Bohg, Jeffrey T. Bingham, Jensen Gao, Jiaheng Hu, Jiajun Wu 0001, Jiankai Sun, Jianlan Luo, Jiayuan Gu, Jie Tan 0001, Jihoon Oh, Jimmy Wu, Jingpei Lu, Jitendra Malik, João Silvério, Joey Hejna, Jonathan Booher, Jonathan Tompson, Jonathan Yang, Jordi Salvador, Joseph J. Lim, Junhyek Han, Kanishka Rao, Karl Pertsch, Karol Hausman, Keegan Go, Keerthana Gopalakrishnan, Kenneth Y. Goldberg, Kendra Byrne, Kenneth Oslund, Kento Kawaharazuka, Kevin Black, Kevin Zhang 0002, Kiana Ehsani, Kiran Lekkala, Kirsty Ellis, Krishan Rana, Krishnan Srinivasan, Kuan Fang, Kunal Pratap Singh, Kuo-Hao Zeng, Kyle Hatch, Kyle Hsu, Laurent Itti, Yunliang Chen 0001, Lerrel Pinto, Li Fei-Fei 0001, Liam Tan, Linxi Fan, Lionel Ott, Lisa Lee, Luca Weihs, Magnum Chen, Marion Lepert, Marius Memmel, Masayoshi Tomizuka, Masha Itkina, Mateo Guaman Castro, Max Spero, Maximilian Du, Michael Ahn, Michael C. Yip, Mingtong Zhang 0003, Mingyu Ding, Minho Heo, Mohan Kumar Srirama, Mohit Sharma 0001, Moo Jin Kim, Naoaki Kanazawa, Nicklas Hansen 0001, Nicolas Heess, Nikhil J. Joshi, Niko Sünderhauf, Norman Di Palo, Nur Muhammad Shafiullah, Oier Mees, Oliver Kroemer, Osbert Bastani, Pannag R. Sanketi, Patrick Tree Miller, Patrick Yin, Paul Wohlhart, Peng Xu 0010, Peter David Fagan, Peter Mitrano, Pierre Sermanet, Pieter Abbeel, Priya Sundaresan, Qiuyu Chen, Rafael Rafailov, Ria Doshi, Roberto Martin Martin, Rohan Baijal, Rosario Scalise, Rose Hendrix, Roy Lin, Runjia Qian, Russell Mendonca, Rutav Shah, Ryan Hoque, Ryan Julian, Samuel Bustamante-Gomez, Sean Kirmani, Sergey Levine, Sherry Moore, Shikhar Bahl, Shivin Dass, Shubham D. Sonawani, Shuran Song, Sichun Xu, Siddhant Haldar, Siddharth Karamcheti, Simeon Adebola, Simon Guist, Soroush Nasiriany, Stefan Schaal, Stefan Welker, Stephen Tian, Subramanian Ramamoorthy, Sudeep Dasari, Suneel Belkhale, Sungjae Park, Suraj Nair 0003, Suvir Mirchandani, Takayuki Osa, Tanmay Gupta, Tatsuya Harada, Tatsuya Matsushima, Ted Xiao, Thomas Kollar, Tianhe Yu, Tianli Ding, Todor Davchev, Tony Z. Zhao, Travis Armstrong, Trevor Darrell, Trinity Chung, Vidhi Jain, Vincent Vanhoucke, Wolfram Burgard, Xiaolong Wang 0004, Xinghao Zhu, Xinyang Geng, Liangwei Xu, Yecheng Jason Ma 0001, Yejin Kim 0003, Yevgen Chebotar, Yilin Wu 0003, Yonatan Bisk, Yoonyoung Cho, Youngwoon Lee, Yuchen Cui, Yueh-Hua Wu, Yujin Tang, Yuke Zhu, Yunchu Zhang, Yunfan Jiang 0001, Yunshuang Li, Yunzhu Li, Yusuke Iwasawa, Yutaka Matsuo, Zehan Ma, Zichen Jeff Cui, Zichen Zhang 0016, Zipeng Lin	ICRA	227
2024	Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks abstract Autonomous assistance of people with motor impairments is one of the most promising applications of autonomous robotic systems. Recent studies have reported encouraging results using deep reinforcement learning (RL) in the healthcare domain. Previous studies showed that assistive tasks can be formulated as multi-agent RL, wherein there are two agents: a caregiver and a care-receiver. However, policies trained in multi-agent RL are often sensitive to the policies of other agents. In such a case, a trained caregiver’s policy may not work for different care-receivers. To alleviate this issue, we propose a framework that learns a robust caregiver’s policy by training it for diverse care-receiver responses. In our framework, diverse care-receiver responses are autonomously learned through trials and errors. In addition, to robustify the care-giver’s policy, we propose a strategy for sampling a care-receiver’s response in an adversarial manner during the training. We evaluated the proposed method using tasks in an Assistive Gym. We demonstrate that policies trained with a popular deep RL method are vulnerable to changes in policies of other agents and that the proposed framework improves the robustness against such changes. Takayuki Osa, Tatsuya Harada	ICRA	1
2024	Active Learning for Forward/Inverse Kinematics of Redundantly-driven Flexible Tensegrity Manipulator abstract In flexible redundantly-driven multi-DOF systems, like living beings, the representation of redundant kinematics including the diversity of solutions, is crucial for leveraging its distinctive characteristics. This paper proposes an active learning framework for forward and inverse modeling of complex kinematics that improves expressions of control space, task space, and null space. It consists of a Variational Auto Encoder (VAE)-type network that internally holds expressions of control space, task space, and null space, and an algorithm for selecting new data using the cross-entropy method. The validity of the proposed system was verified using a tensegrity manipulator driven by 40 pneumatic cylinders. As a result, it was confirmed that active learning contributed to achieving the entire range of motion covered and a well-organized representation of the null space. Yuhei Yoshimitsu, Takayuki Osa, Heni Ben Amor, Shuhei Ikemoto	IROS	2
2023	Forward/Inverse Kinematics Modeling for Tensegrity Manipulator Based on Goal-Conditioned Variational Autoencoder abstract This paper uses a data-driven approach to model a highly redundantly driven tensegrity manipulator's forward and inverse kinematics. The tensegrity manipulator is based on a class-1 tensegrity with 20 struts and bends by 40 pneumatic actuators whose internal pressures are independently controlled. Based on the data obtained through random trials with the robot, a VAE-based kinematics model is trained. The forward model, inverse model, and null space of kinematics are simultaneously acquired as subnetworks of the VAE-based kinematics model. Experiments confirmed that the subnetworks representing forward and inverse kinematics could be used for the end position estimation and control, respectively. In addition, the subnetwork representing null space can generate different target pressures that achieve the same end position, which was confirmed to mean variable stiffness properties similar to musculoskeletal robots. Yuhei Yoshimitsu, Takayuki Osa, Shuhei Ikemoto	IROS	2
2022	Discovering diverse solutions in deep reinforcement learning by maximizing state-action-based mutual information Takayuki Osa, Voot Tangkaratt, Masashi Sugiyama	Neural Networks	1
2021	Meta-Model-Based Meta-Policy Optimization abstract Model-based meta-reinforcement learning (RL) methods have recently been shown to be a promising approach to improving the sample efficiency of RL in multi-task settings. However, the theoretical understanding of those methods is yet to be established, and there is currently no theoretical guarantee of their performance in a real-world environment. In this paper, we analyze the performance guarantee of model-based meta-RL methods by extending the theorems proposed by Janner et al. (2019). On the basis of our theoretical results, we propose Meta-Model-Based Meta-Policy Optimization (M3PO), a model-based meta-RL method with a performance guarantee. We demonstrate that M3PO outperforms existing meta-RL methods in continuous-control benchmarks. Takuya Hiraoka, Takahisa Imagawa, Voot Tangkaratt, Takayuki Osa, Takashi Onishi, Yoshimasa Tsuruoka	ACML	4
2019	Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization Takayuki Osa, Voot Tangkaratt, Masashi Sugiyama	ICLR (Poster)	1
2018	Hierarchical Policy Search via Return-Weighted Density Estimation abstract Learning an optimal policy from a multi-modal reward function is a challenging problem in reinforcement learning (RL). Hierarchical RL (HRL) tackles this problem by learning a hierarchicalpolicy, where multiple option policies are in charge of different strategies corresponding to modes of a reward function and a gating policy selects the best option for a given context. Although HRL has been demonstrated to be promising, current state-of-the-art methods cannot still perform well in complex real-world problems due to the difficulty of identifying modes of the reward function. In this paper, we propose a novel method called hierarchical policy search via return-weighted density estimation (HPSDE), which can efficiently identify the modes through density estimation with return-weighted importance sampling. Our proposed method finds option policies corresponding to the modes of the return function and automatically determines the number and the location of option policies, which significantly reduces the burden of hyper-parameters tuning. Through experiments, we demonstrate that the proposed HPSDE successfully learns option policies corresponding to modes of the return function and that it can be successfully applied to a motion planning problem of a redundant robotic manipulator. Takayuki Osa, Masashi Sugiyama	AAAI	1
2018	Sample and Feedback Efficient Hierarchical Reinforcement Learning from Human Preferences abstract While reinforcement learning has led to promising results in robotics, defining an informative reward function is challenging. Prior work considered including the human in the loop to jointly learn the reward function and the optimal policy. Generating samples from a physical robot and requesting human feedback are both taxing efforts for which efficiency is critical. We propose to learn reward functions from both the robot and the human perspectives to improve on both efficiency metrics. Learning a reward function from the human perspective increases feedback efficiency by assuming that humans rank trajectories according to a low-dimensional outcome space. Learning a reward function from the robot perspective circumvents the need for a dynamics model while retaining the sample efficiency of model-based approaches. We provide an algorithm that incorporates bi-perspective reward learning into a general hierarchical reinforcement learning framework and demonstrate the merits of our approach on a toy task and a simulated robot grasping task. Robert Pinsler, Riad Akrour, Takayuki Osa, Jan Peters 0001, Gerhard Neumann	ICRA	3
2018	Online Trajectory Planning and Force Control for Automation of Surgical Tasks abstract Automation of surgical tasks is expected to improve the quality of surgery. In this paper, we address two issues that must be resolved for automation of robotic surgery: online trajectory planning and force control under dynamic conditions. By leveraging demonstrations under various conditions, we model the conditional distribution of the trajectories given the task condition. This scheme enables generalization of the trajectories of spatial motion and contact force to new conditions in real time. In addition, we propose a force tracking controller that robustly and stably tracks the planned profile of the contact force by learning the spatial motion and contact force simultaneously. The proposed scheme was tested with bimanual tasks emulating surgical tasks that require online trajectory planning and force tracking control, such as tying knots and cutting soft tissues. Experimental results show that the proposed scheme enables planning of the task trajectory under dynamic conditions in real time. In addition, the performance of the force control schemes was verified in the experiments. Takayuki Osa, Naohiko Sugita, Mamoru Mitsuishi	IEEE Trans Autom. Sci. Eng.	1
2017	A learning-based shared control architecture for interactive task execution abstract Shared control is a key technology for various robotic applications in which a robotic system and a human operator are meant to collaborate efficiently. In order to achieve efficient task execution in shared control, it is essential to predict the desired behavior for a given situation or context in order to simplify the control task for the human operator. This prediction is obtained by exploiting Learning from Demonstration (LfD), which is a popular approach for transferring human skills to robots. We encode the demonstrated behavior as trajectory distributions and generalize the learned distributions to new situations. The goal of this paper is to present a shared control framework that uses learned expert distributions to gain more autonomy. Our approach controls the balance between the controller's autonomy and the human preference based on the distributions of the demonstrated trajectories. Moreover, the learned distributions are autonomously refined from collaborative task executions, resulting in a master-slave system with increasing autonomy that requires less user input with an increasing number of task executions. We experimentally validated that our shared control approach enables efficient task executions. Moreover, the conducted experiments demonstrated that the developed system improves its performances through interactive task executions with our shared control. Firas Abi-Farraj, Takayuki Osa, Nicolo Pedemonte, Jan Peters 0001, Gerhard Neumann, Paolo Robuffo Giordano	ICRA	2
2014	Autonomous penetration detection for bone cutting tool using demonstration-based learning abstract In orthopedic surgery, bone-cutting procedures are frequently performed. However, bone-cutting procedures are very risky in cases where vital organs or nerves exist beneath the target bones. In such cases, surgeons are required to determine the depth of the penetration into the bone by using only their haptic senses. Thus, we developed a handheld bone-cutting-tool system that detects the penetration of the cutting material. The developed system autonomously detects the penetration before total penetration and stops the actuation of the cutting tool, leaving a very thin remnant of work material. The developed system estimates the cutting resistance by using its motor's current and rotational speed. On the basis of data collected preoperatively, the system estimates the cutting state by using a support vector machine (SVM). According to the SVM outputs, the system detects the penetration of the work material and autonomously stops the actuation of the cutting tool. The proposed method was verified through experiments, and the results showed that the developed system successfully detected the penetrations of work materials and stopped autonomously immediately before total penetration. This study showed that the autonomous detection of bone penetration with a hand-held bone-cutting tool is feasible by using the proposed scheme. Takayuki Osa, Christian Farid Abawi, Naohiko Sugita, Hirotaka Chikuda, Shurei Sugita, Hideya Ito, Toru Moro, Yoshio Takatori, Sakae Tanaka, Mamoru Mitsuishi	ICRA	1
2014	Trajectory planning under different initial conditions for surgical task automation by learning from demonstration abstract The automation of surgical tasks has great potential for improving the performance of robotic surgery. The learning-from-demonstration approach has thus far been employed by many researchers when planning the trajectories of robotic instruments for automated surgical tasks. However, previous methods are applicable only when the demonstrations and trajectory generation are performed under the same initial conditions. In this paper, we propose an algorithm that learns through demonstrations and generates a trajectory regardless of the initial conditions. The variance of the demonstrated trajectories over the initial conditions is modeled and learned using a statistical method, and the learned trajectories are generalized and used to generate a trajectory. As an example, the bi-manual looping task of a surgical thread was demonstrated by changing the initial positions of the robot arms, and a trajectory was then planned given these initial arbitrary positions. The proposed algorithm was verified through simulations and experiments using an actual robotic surgical system. Takayuki Osa, Kanako Harada, Naohiko Sugita, Mamoru Mitsuishi	ICRA	1
2014	Hybrid control of master-slave velocity control and admittance control for safe remote surgery abstract Remote surgery has attracted great interest in recent decades because it has the potential to improve equality of access to health care. However, remote surgery has not been approved in any country, since patient safety cannot be guaranteed. In this paper, we present a hybrid control system for master-slave velocity control and admittance control for safe remote robotic surgery. The proposed controller switches between these two controls adaptively and stably and avoids excessive contact force between the robotic surgical instrument and the patient's organs. Through the proposed scheme, the contact force between the robotic instrument and objects at the slave site can be bounded by a set upper limit regardless of the motion the operator inputs at the master site. The performance of the proposed system was verified analytically. The proposed control scheme was implemented in a robotic surgical system and its performance was verified through simulations and experiments. The results of the simulations and experiments showed that the system autonomously switches stably between master-slave velocity control and admittance control and avoids excessive contact force. Takayuki Osa, Satoshi Uchida, Naohiko Sugita, Mamoru Mitsuishi	IROS	1
2013	Perforation risk detector using demonstration-based learning for teleoperated robotic surgery abstract Loss of haptic sensation in a master-slave system is one of the open problems in robotic surgery, and recognition of surgical situations through haptic sensation is a challenge. In this paper we propose an autonomous risk-detection system for a master-slave surgical robotic system in order to estimate a property of an object (i.e., contact impedance) using a force sensor mounted on a surgical robotic instrument. The system autonomously detects the risk based on the estimated contact impedance and accordingly activates the motion at the slave unit as well as the force feedback at the master unit. We implemented the proposed method in a teleoperated master-slave system to detect the perforation risk of a membranous object. The performance of the system was evaluated through experiments. The classification accuracy for perforation risk was about 98.5 % in fourfold cross-validation. The experiments verified that the risk detection system accurately detected the perforation risk and improved the safety of the master-slave system. Takayuki Osa, Takuto Haniu, Kanako Harada, Naohiko Sugita, Mamoru Mitsuishi	IROS	1
2010	Automation of tissue piercing using circular needles and vision guidance for computer aided laparoscopic surgery abstract Despite the fact that minimally invasive robotic surgery provides many advantages for patients, such as reduced tissue trauma and shorter hospitalization, complex tasks (e.g. tissue piercing or knot-tying) are still time-consuming, error-prone and lead to quicker fatigue of the surgeon. Automating these recurrent tasks could greatly reduce total surgery time for patients and disburden the surgeon while he can focus on higher level challenges. This work tackles the problem of autonomous tissue piercing in robot-assisted laparoscopic surgery with a circular needle and general purpose surgical instruments. To command the instruments to an incision point, the surgeon utilizes a laser pointer to indicate the stitching area. A precise positioning of the needle is obtained by means of a switching visual servoing approach and the subsequent stitch is performed in a circular motion. Christoph Staub, Takayuki Osa, Alois C. Knoll, Robert Bauernschmitt	ICRA	2
2010	Asynchronous force and visual feedback in teleoperative laparoscopic surgical system abstract Force feedback systems have been developed to improve the user-friendliness of robotic surgery systems. In teleoperative surgery, one of the major problems is the delay of the transmission of the information from the operation site to the surgery site. The transmission delays of the control signal and force information are less than the that of the image signal. In many cases, the visual information is synchronized with the force information in order to avoid a time gap between them. In this paper, we propose that force information be presented earlier than the visual information. This approach reduces the damage to the organs in surgical operations even though there is a time gap between the delay of force information and visual information. In addition, we propose a method to present predicted force information to avoid damage to the organs due to time delays in teleoperative surgery. The liver can be treated with a contact force of less than 0.8 N and a grasping force of less than 1.1 N by applying the proposed method. The method can realize a teleoperative surgery without damaging the patient's organs. Kazushi Onda, Takayuki Osa, Naohiko Sugita, Makoto Hashizume, Mamoru Mitsuishi	IROS	2
2010	Framework of automatic robot surgery system using Visual servoing abstract The use of technology for automation of surgical tasks has great potential in the field of robotic surgery. Automation of surgical robots essentially involves designing a control scheme for precise and automatic positioning of robotic manipulators. This objective can be achieved by the use of Visual servoing. We have developed a visual-servoing-based robotic laparoscopic surgery system. The visual servoing system enables autonomous control of a robot arm in a surgical set-up. In this paper, we propose algorithms for the automatic positioning of the laparoscope and the surgical instruments under small incisions of skin. We have verified the performance of the system theoretically and experimentally. Takayuki Osa, Christoph Staub, Alois C. Knoll	IROS	1
2008	Deformation analysis and active compensation of surgical milling robot based on system error evaluation abstract The increase of precision and minimal invasiveness is an important current issue in orthopedic surgery. The femur and the tibia must be shaped to fit an artificial joint for successful knee arthroplasty. The recent trend towards MIS (Minimally Invasive Surgery) to decrease the length of the required incision has increased surgical difficulty, since the open access area is small. In this paper, registration and cutting error were analyzed with a robotic surgery system being developed first as an example, and a method of active compensation of robot deformation by gravity and cutting force was proposed and tried based on the error map with the expectation that the precision will increase. Naohiko Sugita, Takayuki Osa, Yoshikazu Nakajima, Mamoru Mitsuishi	ICRA	2