Header logo is


2007


no image
Machine Learning of Motor Skills for Robotics

Peters, J.

University of Southern California, Los Angeles, CA, USA, University of Southern California, Los Angeles, CA, USA, 2007, clmc (phdthesis)

Abstract
Autonomous robots that can assist humans in situations of daily life have been a long standing vision of robotics, artificial intelligence, and cognitive sciences. A first step towards this goal is to create robots that can accomplish a multitude of different tasks, triggered by environmental context or higher level instruction. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s, however, made it clear that an approach purely based on reasoning and human insights would not be able to model all the perceptuomotor tasks that a robot should fulfill. Instead, new hope was put in the growing wake of machine learning that promised fully adaptive control algorithms which learn both by observation and trial-and-error. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this thesis, we investigate the ingredients for a general approach to motor skill learning in order to get one step closer towards human-like performance. For doing so, we study two major components for such an approach, i.e., firstly, a theoretically well-founded general approach to representing the required control structures for task representation and execution and, secondly, appropriate learning algorithms which can be applied in this setting. As a theoretical foundation, we first study a general framework to generate control laws for real robots with a particular focus on skills represented as dynamical systems in differential constraint form. We present a point-wise optimal control framework resulting from a generalization of Gauss' principle and show how various well-known robot control laws can be derived by modifying the metric of the employed cost function. The framework has been successfully applied to task space tracking control for holonomic systems for several different metrics on the anthropomorphic SARCOS Master Arm. In order to overcome the limiting requirement of accurate robot models, we first employ learning methods to find learning controllers for task space control. However, when learning to execute a redundant control problem, we face the general problem of the non-convexity of the solution space which can force the robot to steer into physically impossible configurations if supervised learning methods are employed without further consideration. This problem can be resolved using two major insights, i.e., the learning problem can be treated as locally convex and the cost function of the analytical framework can be used to ensure global consistency. Thus, we derive an immediate reinforcement learning algorithm from the expectation-maximization point of view which leads to a reward-weighted regression technique. This method can be used both for operational space control as well as general immediate reward reinforcement learning problems. We demonstrate the feasibility of the resulting framework on the problem of redundant end-effector tracking for both a simulated 3 degrees of freedom robot arm as well as for a simulated anthropomorphic SARCOS Master Arm. While learning to execute tasks in task space is an essential component to a general framework to motor skill learning, learning the actual task is of even higher importance, particularly as this issue is more frequently beyond the abilities of analytical approaches than execution. We focus on the learning of elemental tasks which can serve as the "building blocks of movement generation", called motor primitives. Motor primitives are parameterized task representations based on splines or nonlinear differential equations with desired attractor properties. While imitation learning of parameterized motor primitives is a relatively well-understood problem, the self-improvement by interaction of the system with the environment remains a challenging problem, tackled in the fourth chapter of this thesis. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and outline both established and novel algorithms for the gradient-based improvement of parameterized policies. We compare these algorithms in the context of motor primitive learning, and show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. In conclusion, in this thesis, we have contributed a general framework for analytically computing robot control laws which can be used for deriving various previous control approaches and serves as foundation as well as inspiration for our learning algorithms. We have introduced two classes of novel reinforcement learning methods, i.e., the Natural Actor-Critic and the Reward-Weighted Regression algorithm. These algorithms have been used in order to replace the analytical components of the theoretical framework by learned representations. Evaluations have been performed on both simulated and real robot arms.

am ei

[BibTex]

2007


[BibTex]


no image
Bacterial flagella-based propulsion and on/off motion control of microscale objects

Behkam, B., Sitti, M.

Applied Physics Letters, 90(2):023902, AIP, 2007 (article)

pi

[BibTex]

[BibTex]


no image
Friction of partially embedded vertically aligned carbon nanofibers inside elastomers

Aksak, B., Sitti, M., Cassell, A., Li, J., Meyyappan, M., Callen, P.

Applied Physics Letters, 91(6):061906, AIP, 2007 (article)

pi

[BibTex]

[BibTex]


no image
Enhanced friction of elastomer microfiber adhesives with spatulate tips

Kim, S., Aksak, B., Sitti, M.

Applied Physics Letters, 91(22):221913, AIP, 2007 (article)

pi

Project Page [BibTex]

Project Page [BibTex]


no image
The new robotics - towards human-centered machines

Schaal, S.

HFSP Journal Frontiers of Interdisciplinary Research in the Life Sciences, 1(2):115-126, 2007, clmc (article)

Abstract
Research in robotics has moved away from its primary focus on industrial applications. The New Robotics is a vision that has been developed in past years by our own university and many other national and international research instiutions and addresses how increasingly more human-like robots can live among us and take over tasks where our current society has shortcomings. Elder care, physical therapy, child education, search and rescue, and general assistance in daily life situations are some of the examples that will benefit from the New Robotics in the near future. With these goals in mind, research for the New Robotics has to embrace a broad interdisciplinary approach, ranging from traditional mathematical issues of robotics to novel issues in psychology, neuroscience, and ethics. This paper outlines some of the important research problems that will need to be resolved to make the New Robotics a reality.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Microscale and nanoscale robotics systems [grand challenges of robotics]

Sitti, M.

IEEE Robotics \& Automation Magazine, 14(1):53-60, IEEE, 2007 (article)

pi

[BibTex]

[BibTex]


no image
A new biomimetic adhesive for therapeutic capsule endoscope applications in the gastrointestinal tract

Glass, P., Sitti, M., Appasamy, R.

Gastrointestinal Endoscopy, 65(5):AB91, Mosby, 2007 (article)

pi

[BibTex]

[BibTex]


no image
Visual servoing-based autonomous 2-D manipulation of microparticles using a nanoprobe

Onal, C. D., Sitti, M.

IEEE Transactions on control systems technology, 15(5):842-852, IEEE, 2007 (article)

pi

[BibTex]

[BibTex]


no image
Adhesion of biologically inspired vertical and angled polymer microfiber arrays

Aksak, B., Murphy, M. P., Sitti, M.

Langmuir, 23(6):3322-3332, ACS Publications, 2007 (article)

pi

Project Page [BibTex]

Project Page [BibTex]


no image
Waalbot: An agile small-scale wall-climbing robot utilizing dry elastomer adhesives

Murphy, M. P., Sitti, M.

IEEE/ASME transactions on Mechatronics, 12(3):330-338, IEEE, 2007 (article)

pi

[BibTex]

[BibTex]


no image
Subfeature patterning of organic and inorganic materials using robotic assembly

Tafazzoli, A., Cheng, C., Pawashe, C., Sabo, E. K., Trofin, L., Sitti, M., LeDuc, P. R.

Journal of materials research, 22(06):1601-1608, Cambridge University Press, 2007 (article)

pi

[BibTex]

[BibTex]


no image
Effect of backing layer thickness on adhesion of single-level elastomer fiber arrays

Kim, S., Sitti, M., Hui, C., Long, R., Jagota, A.

Applied Physics Letters, 91(16):161905, AIP, 2007 (article)

pi

[BibTex]

[BibTex]


no image
Adhesion and anisotropic friction enhancements of angled heterogeneous micro-fiber arrays with spherical and spatula tips

Murphy, M. P., Aksak, B., Sitti, M.

Journal of Adhesion Science and Technology, 21(12-13):1281-1296, Taylor & Francis Group, 2007 (article)

pi

Project Page [BibTex]

Project Page [BibTex]


no image
Surface-tension-driven biologically inspired water strider robots: Theory and experiments

Song, Y. S., Sitti, M.

IEEE Transactions on robotics, 23(3):578-589, IEEE, 2007 (article)

pi

[BibTex]

[BibTex]

2006


no image
Induced Master Motion in Force-Reflecting Teleoperation

Kuchenbecker, K. J., Niemeyer, G.

ASME Journal of Dynamic Systems, Measurement, and Control, 128(4):800-810, December 2006 (article)

hi

[BibTex]

2006


[BibTex]


no image
Improving Contact Realism Through Event-Based Haptic Feedback

Kuchenbecker, K. J., Fiene, J. P., Niemeyer, G.

IEEE Transactions on Visualization and Computer Graphics, 12(2):219-230, March 2006 (article)

hi

[BibTex]

[BibTex]


no image
An ultrasonic standing-wave-actuated nano-positioning walking robot: piezoelectric-metal composite beam modeling

Son, K. J., Kartik, V., Wickert, J. A., Sitti, M.

Journal of vibration and control, 12(12):1293-1309, Sage Publications, 2006 (article)

pi

[BibTex]

[BibTex]


no image
IEEE TRANSACTIONS ON ROBOTICS

VOLZ, RICHARD A, TARN, TJ, MACIEJEWSKI, ANTHONY A, LEE, SUKHAN, BICCHI, ANTONIO, DE LUCA, ALESSANDRO, LUH, PETER B, TAYLOR, RUSSELL H, BEKEY, GEORGE A, ARAI, HIROHIKO, others

2006 (article)

pi

[BibTex]

[BibTex]


no image
Design methodology for biomimetic propulsion of miniature swimming robots

Behkam, B., Sitti, M.

Trans.-ASME Journal of Dynamic Systems Measurement and Control, 128(1):36, ASME, 2006 (article)

pi

Project Page [BibTex]

Project Page [BibTex]


no image
Augmented reality user interface for an atomic force microscope-based nanorobotic system

Vogl, W., Ma, B. K., Sitti, M.

IEEE transactions on nanotechnology, 5(4):397-406, IEEE, 2006 (article)

pi

[BibTex]

[BibTex]


no image
Friction enhancement via micro-patterned wet elastomer adhesives on small intestinal surfaces

Kwon, J., Cheung, E., Park, S., Sitti, M.

Biomedical Materials, 1(4):216, IOP Publishing, 2006 (article)

pi

[BibTex]

[BibTex]


no image
Compliant and low-cost humidity nanosensors using nanoporous polymer membranes

Yang, B., Aksak, B., Lin, Q., Sitti, M.

Sensors and Actuators B: Chemical, 114(1):254-262, Elsevier, 2006 (article)

pi

[BibTex]

[BibTex]


no image
Task-based and stable telenanomanipulation in a nanoscale virtual environment

Kim, S., Sitti, M.

IEEE Transactions on automation science and engineering, 3(3):240-247, IEEE, 2006 (article)

pi

[BibTex]

[BibTex]


no image
Drawing suspended polymer micro-/nanofibers using glass micropipettes

Nain, A. S., Wong, J. C., Amon, C., Sitti, M.

Applied Physics Letters, 89(18):183105, AIP, 2006 (article)

pi

[BibTex]

[BibTex]


no image
Biologically inspired polymer microfibers with spatulate tips as repeatable fibrillar adhesives

Kim, S., Sitti, M.

Applied Physics Letters, 89(26):261911-261911, AIP, 2006 (article)

pi

Project Page [BibTex]


no image
Two-dimensional vision-based autonomous microparticle manipulation using a nanoprobe

Pawashe, C., Sitti, M.

Journal of Micromechatronics, 3(3):285-306, Brill, 2006 (article)

pi

[BibTex]

[BibTex]


no image
A biomimetic climbing robot based on the gecko

Menon, C., Sitti, M.

Journal of Bionic Engineering, 3(3):115-125, 2006 (article)

pi

[BibTex]

[BibTex]


no image
Proximal probes based nanorobotic drawing of polymer micro/nanofibers

Nain, A. S., Amon, C., Sitti, M.

IEEE transactions on nanotechnology, 5(5):499-510, IEEE, 2006 (article)

pi

[BibTex]

[BibTex]