## Journal Publications

[J21]. P. Grover, K. Bakshi and E.A. Theodorou. A Mean-Field Game Model for Homogenous Flocking. **Under review, 2018**. (arXiv)

[J20]. Y. Exarhos, E.A. Theodorou and P. Tsiotras. Stochastic Differential Games – A Sampling Approach via FBSDEs. **Under review, 2018**.

[J19]. Y. Exarhos, E.A. Theodorou and P. Tsiotras. L1 Optimal Control using Forward Backward Stochastic Differential Equations. **Under review, 2018**.

[J18]. W. Sun, Y. Pan, E.A. Theodorou, P. Tsiotras. Min-Max Differential Dynamic Program- ming: Continuous and Discrete Time Formulations. **Under review, 2018**.

[J17]. G. Boutselis, Y. Pan G. DeLa Torre, E.A. Theodorou. Stochastic Trajectory Optimization for Mechanical Systems under Parametric Uncertainty. **Under review, 2018** (arXiv)

[J16]. G. Boutselis, E.A. Theodorou. Differential Dynamic Programming on Lie Groups: Derivation, Convergence Analysis and Numerical Examples.**Under review, 2018**.

[J15]. K. Bakshi, E.A. Theodorou. Infinite Dimensional Control of Q-Marked Jump Diffusions: Optimality Principles and Algorithms. **Under review, 2017**.

[J14]. G. Williams, P. Drews, B. Goldfrain, J. Rehg and E.A. Theodorou. Information Theoretic Model Predictive Path Integral Control: Theory and Applications to Aggressive Driving. **Conditionally Accepted to IEEE Transactions on Robotics, 2018 ** (arXiv)

[J13]. Y. Exarchos, E.A. Theodorou. Learning Optimal Control via Forward Backward Stochastic Differential Equations and Importance Sampling. Automatica, 2017.(arXiv) Link

[J12]. Y. Pan, G. Boutselis, E.A. Theodorou. Efficient Reinforcement Learning with Probabilistic Trajectory Optimization. IEEE Transactions on Neural Networks and Learning Systems, 2017. Link

[J11]. G. De La Torre, E.A. Theodorou and E. Johnson. Autonomous Suspended Load Operations via Trajectory Optimization and Variational Integrators. AIAA Journal of Guidance Control and Dynamics. 2016. Link

[J10]. G. Williams , A. Aldrich, E.A. Theodorou. Model Predictive Path Integral Control: From theory to parallel computation. AAIA Journal of Guidance Control and Dynamics, 2016. Link

[J9]. E.A. Theodorou. Nonlinear Stochastic Control and Information Theoretic Dualities: Connections, Interdependencies and Thermodynamic Interpretations. Entropy. 2015; 17(5):3352- 3375. Link

[J8]. M. Mistry, E.A. Theodorou, S. Schaal, and M. Kawato. Optimal Control of Reaching Includes Kinematic Constraints. Journal of Neurophysiology, American Physiological Society, 2013. Link

[J7]. P. Pastor, M. Kalakrishnan, F. Meier , F Stulp , J. Buchli , E. A. Theodorou, and S. Schaal, From Dynamic Movement Primitives to Associative Skill Memories, Journal of Robotics and Autonomous Systems, 61(4):4351-361, 2013. Link

[J6]. E. Rombocas, M. Mathora, E.A. Theodorou and E. Todorov, Y. Matsuoka. Reinforcement Learning and Synergistic Control of the ACT hand. IEEE/ASME Transactions on Mechatronics, 18(2):569-577,2013. Link

[J5]. F. Stulp, J. Buchli, A. Ellmer, M. Mistry, E. A. Theodorou, and S. Schaal. Model-free Reinforcement Learning of Impedance Control in Stochastic Environments. IEEE Transactions of Autonomous Mental Development (TAMD), 4(4):330-341, 2012. Link

[J4]. F. Stulp, E.A. Theodorou and S.Schaal. Reinforcement Learning with Sequences of Motion Primitives for Robust Manipulation. IEEE Transactions on Robotics(TRO), 28(6):1360 -1370, 2012. King-Sun Fu Best Paper Award of the IEEE Transactions on Robotics, for the year 2012. Link

[J3]. J. Buchli, F.Stulp, E.A. Theodorou, and S. Schaal. Variable Stiffness Control: A reinforcement learning approach. International Journal of Robotics Research(IJRR), 30(7):820-833, 2011. Link

[J2]. E.A. Theodorou, J. Buchli , and S. Schaal. Generalized Path Integral Control Approach to Reinforcement Learning (JMLR). Journal of Machine Learning research. 11, 3137-3181, 2010.Link Erratum

[J1]. Valero-Cuevas, F. J., Hoffmann, H., Kurse, M. U., Kutch, J. J., and Theodorou, E. A.. Computational models for neuromuscular function. IEEE Reviews in Biomedical Engineering, 2, 110-135, 2009 (All author have equally contributed) Link

## Conference Publications

[C77]. D. Fan, E.A. Theodorou and John Reeder. Model-Based Stochastic Search for Large Scale Optimization of Multi-Agent UAV Swarms. **Under review, 2018**. (arXiv)

[C76]. H. Brar, Y. Exarchos, Y. Pan, B. Mahmoudi, E.A. Theodorou, Seizure Reduction using Model Predictive Control. **Under review, 2018**.

[C75]. Munzir and E.A. Theodorou, Hierarchical Optimization for Whole-Body Control of Wheeled Inverted Pendulum Humanoids. **Under review, 2018**.

[C74]. M. Periera, D. Fan, G. Nakajima An and E.A Theodorou, MPC-inspired Neural Network Policies for Sequential Decision Making. (arXiv:1802.05803) **Under review, 2018**.

[C73]. G. Williams ,B. Goldfrain, P. Drews, J. Rehg and E.A Theodorou, Tube-Based Model Predictive Path Integral Control. **Under review, 2018**.

[C72]. Y. Pan, K. Saigol, K. Lee, X. Yan, Byron Boots, E.A Theodorou, End-to-End Learning Control for Agile Autonomous Driving. **Under review, 2018**.

[C71]. E. N. Evans, P. Meyer, S. Seifert, D. Mavris, and E. A. Theodorou. An Adaptive Approach to Online Trajectory Optimization in Unknown Environments with RRTs. **Under review, 2018. **

[C70]. E. Evan, W. Haddad and E.A. Theodorou, Fixed structure nonlinear control for stochastic systems, To appear in ACC (2018).

[C69]. G. Williams, B. Goldfrain, J. Rehg and E.A.Theodorou, Best Response Model Predictive Control for Agile Interactions Between Autonomous Ground Vehicles To appear in ICRA (2018).

[C68]. Li W., E. A. Theodorou, and M. Egerstedt Learning Quadrotor Dynamics and Safety Barrier Certificates Using Gaussian Process. To appear in ICRA (2018).

[C67]. Y. Wang, E.A. Theodorou and L. Song, A Stochastic Differential Equation Framework for Guiding Online User Activities in Closed Loop, Accepted to AISTATS 2018.

[C66]. M. Gandhi, Y. Pan and E.A. Theodorou. Pseudospectral Model Predictive Control under Partially Learned Dynamics. Accepted to IEEE Proceedings of ADPRL, 2017.

[C65]. P. Drews, G. Williams, B. Goldfrain, J. Rehg, E.A Theodorou Aggressive Deep Driving: Combining Convolutional Neural Networks and Model Predictive Control. Conference on Robot Learning (CoRL), 2017.

[C64]. Y. Pan, X. Yan, E.A. Theodorou and B. Boots. Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control. Proceedings of the 34th International Conference on Machine Learning (ICML), PMLR Vol 70, pp. 2760-2768, 2017.

[C63]. Y. Wang, G. Williams, E.A. Theodorou and L. Song, Variational Policy for Guiding Point Processes, Proceedings of the 34th International Conference on Machine Learning (ICML), PMLR Vol 70, pp. 3684-3693, 2017.

[C62]. D. Fan, E.A. Theodorou, J. Reeder. Evolving Cost Functions For Model Predictive Control of Multi-Agent UAV Combat Swarms. Proceedings of the Genetic and Evolutionary Compu- tation Conference(GECCO ), pp. 55-56, July 15 – 19, 2017, Berlin, Germany .

[C61]. K. Bakshi, D. Fan, and E.A. Theodorou. Stochastic Optimal Control of Systems with State and Control Multiplicative Noise Using Second Order FBSDEs. In the Proceedings of American Control Conference (ACC), pp. 424-431, May 24-26, 2017, Seattle, WA.

[C60]. Y. Pan, K. Saigol and E.A. Theodorou, Belief Space Path Integral Control, In the Pro- ceedings of American Control Conference (ACC), pp. 3764-3770, May 24-26, 2017, Seattle, WA.

[C59]. G. Williams, N. Wagener, B. Goldfain, P. Drews, J. M. Rehg, B. Boots, and E. A. Theodorou, Information Theoretic MPC for Model-Based Reinforcement Learning (ICRA), pp , May 29- June 3, 2017, Singapore. (Finalist for Best Paper Award)

[C58]. D. Fan, E.A. Theodorou, Differential Dynamic Programming for time-delayed systems, In the Proceedings of IEEE 55th Conference on Decision and Control (CDC), pp. 573-579, Dec 12-14, 2016, Las Vegas, NV.

[C57]. Y. Exarhos, E.A. Theodorou and P. Tsiotras, Game-theoretic and risk-sensitive stochastic optimal control via forward and backward stochastic differential equations, In the Proceedings of IEEE 55th Conference on Decision and Control (CDC), pp. 6154-6160, Dec 12-14, 2016, Las Vegas, NV.

[C56]. K. Bakshi, E.A. Theodorou, Infinite dimensional control of doubly stochastic Jump Dif- fusions, In the Proceedings of IEEE 55th Conference on Decision and Control (CDC), pp. 1145-1152, Dec 12-14, 2016, Las Vegas, NV,.

[C55]. W. Sun, E.A. Theodorou and P. Tsiotras, Stochastic Game Theoretic trajectory optimiza- tion in continuous time, In the Proceedings of IEEE 55th Conference on Decision and Control (CDC), pp. 6167-6172, Dec 12-14, 2016, Las Vegas, NV.

[C54]. G. Boutselis, E.A. Theodorou, Spectral variational integrators for trajectory optimization under parametric uncertainties and stochastic disturbances, In the Proceedings of IEEE 55th Conference on Decision and Control (CDC), pp. 2016-2022, Dec 12-14, 2016, Las Vegas, NV.

[C53]. Y. Pan, X. Yan, E. Theodorou, B. Boots. Solving the Linear Bellman Equation via Kernel Embeddings and Stochastic Gradient Descent. NIPS Workshop (2016) on Adaptive and Scalable Nonparametric Methods in ML.

[C52]. Harleen Brar, Yunpeng Pan and E.A. Theodorou, Cross Entropy Optimization for Neuro- modulation, Accepted in the IEEE conference in Engineering in Medicine and Biology Society, Orlando, 2016.

[C51]. Y. Pan, X. Yan, E.A. Theodorou and B. Boots. Scalable Reinforcement Learning via Trajec- tory Optimization and Approximate Gaussian Process Regression. Advances in Approximate Bayesian Inference, NIPS Workshop, Dec 7-12, 2015, Montreal, Canada.

[C50]. Tanmay Rajpurohit, Wassim M. Haddad E.A. Theodorou. Nonlinear-Nonquadratic Opti- mal and Inverse Optimal Control for Stochastic Dynamical Systems. In the Proceedings of the American Control Conference (ACC), pp:6568-6573, July 6-8, 2016. Boston, MA, USA.

[C49]. G. Boutselis, G. DeLa Torre, E.A. Theodorou. Stochastic Optimal Control using Polynomial Chaos based Variational Integrators. In the Proceedings of the American Control Conference (ACC), pp:6586 – 659, July 6-8, 2016. Boston, MA, USA.

[C48]. Y. Exarchos, E.A. Theodorou. Optimal Control using Forward Backward Stochastic Dif- ferential Equations. In the Proceedings of the American Control Conference (ACC), pp: 2155-2161, July 6-8, 2016. Boston, MA, USA.

[C47]. G. Williams, P. Drews, B. Goldfain, J. Regh and E.A. Theodorou. Aggressive driving with model predictive path integral control. In the Proceedings of the International Conference on Robotics and Automation (ICRA), pp:1433 – 1440, May 16-21, 2016, Stockholm, Sweden.

[C46]. M. Kontitsis, P. Tsiotras and E.A. Theodorou. An Information-Theoretic Active Localiza- tion Approach during Relative Circumnavigation in Orbit. In the Proceedings of American Institute of Aeronautics and Astronautics (AIAA) SciTech Conference, San Diego, 2016.

[C45]. M. Gandhi, E.A. Theodorou. Comparison between Trajectory Optimization Methods: Dif- ferential Dynamic Programming and Pseudospectral Optimal Control. In the proceedings of American Institute of Aeronautics and Astronautics (AIAA) SciTech Conference, San Diego, 2016

[C44]. Y. Pan, E.A. Theodorou. Sample Efficient Path Integral Control under Uncertainty. Ad- vances in Neural Information Processing Systems Conference (NIPS) 28, pp: 2305-2313, Dec 7-12, 2015, Montreal, Canada. Preprint version arXiv:1509.01846.

[C43]. G. De La Torre and E.A Theodorou. Stochastic Variational Integrators for System Propa- gation and Linearization. In the Proceedings of IMA Conference on Mathematics of Robotics, 9-11 September 2015, St Anne’s College, University of Oxford, England.

[C42]. Y.Pan, K. Bakshi and E.A. Theodorou. Robust Trajectory Optimization: A Cooperative Stochastic Game Theoretic Approach. In Proceedings of Robotics: Science and Systems (RSS), 13-17 July, 2015, Rome Italy.

[C41]. W. Sun, E.A. Theodorou and P. Tsiotras. Game Theoretic Continuous Time Differential Dynamic Programming. In the Proceedings of American Control Conference(ACC), pp:5593 – 5598, 1-3 July 2015, Chicago,IL.

[C40]. Y. Pan and E.A. Theodorou. Data Driven Differential Dynamic Programming Using Gaus- sian Processes. In the Proceedings of American Control Conference(ACC), pp:4467 – 4472, 1-3 July 2015, Chicago,IL.

[C39]. Y. Pan, E.A. Theodorou. Model-based Path Integral Stochastic Control: A Bayesian Non- parametric Approach. In Autonomous Learning Robots (NIPS) Workshop, 8-13 Dec, 2014, Montreal, Canada.

[C38]. A. Oktay, E.A. Theodorou and P. Tsiotras. Information-Theoretic Stochastic Optimal Control via Incremental Sampling-based Algorithms. In the Proceeding Adaptive Dynamic Programming and Reinforcement Learning (ADRPL) Symposium, pp:1-8, 9-12 Dec 2014, Orlando, Florida

[C37]. W. Sun, E.A. Theodorou and P. Tsiotras. Continuous Time Differential Dynamic Program- ming. In the Proceeding of Adaptive Dynamic Programming and Reinforcement Learning (ADRPL) Symposium, pp:1-6,9-12 Dec. 2014, Orlando, Florida.

[C36]. Y. Pan, E.A. Theodorou. Probabilistic Differential Dynamic Programming. Advances in Neural Information Processing Systems 27 (NIPS), pp:1907-1915, 8-13 Dec, 2014, Montreal, Canada.

[C35]. Y. Pan, E.A. Theodorou. Nonparametric Infinite Horizon Kullback Leibler Stochastic Con- trol In the Proceeding of Adaptive Dynamic Programming and Reinforcement Learning (ADRPL) Symposium, pp:1-8,9-12 Dec. 2014, Orlando, Florida.

[C34]. G. De La Torre, E. Johnson and E.A. Theodorou. Guidance for Slung Load Operations through Differential Dynamic Programming. American Helicopter Society(AHS), 2014.

[C33]. K. Dvijotham E.A. Theodorou, E. Todorov, M. Fazel. Convexity of Optimal Control Design. In the proceedings of Decision and Control Conference (CDC), pp: 2477 – 2482, 10-13 Dec. 2013, Firenze, Italy.

[C32]. E.A. Theodorou, K. Dvijotham, J. Najemnik, and E. Todorov. Time Varying Nonlinear Policy Gradients. In the proceedings of Decision and Control Conference (CDC), pp: 7765- 7770, 10-13 Dec. 2013, Firenze, Italy.

[C31]. E.A. Theodorou, K. Dvijotham, and E. Todorov. From Information theoretic dualities to Path Integral and Kullback Leibler control: Continuous and Discrete Time Formulations. In the 16th Yale workshop on Adaptive and Learning systems, 2013.

[C30]. E.A. Theodorou and E. Todorov. The δ- sensitivity and its application to stochastic optimal control of nonlinear markov diffusions. In the proceedings of American Control Conference (ACC), pp:0743-1619, 17-19 June 2013, Washington, DC.

[C29]. M. Kontitsis, E.A. Theodorou and E. Todorov. Multi-Robot Active Slam with Relative Entropy Optimization. In the proceedings of American Control Conference (ACC), pp:2757 – 2764, 17-19 June 2013, Washington, DC.

[C28]. E.A. Theodorou, Jiri Najemnik and E. Todorov. Free Energy Based Policy Gradients. In the proceedings of Adaptive Dynamic Programming And Reinforcement Learning (ADPRL) Symposium, pp: 124 – 131, 16-19 April 2013, Singapore.

[C27]. E.A. Theodorou and E. Todorov. Information Theoretic views of Path Integral Control and Applications to Robotics. In the workshop of Information in Perception and Action – Advances in Neural Information Processing Systems, 2012, Lake Tahoe, Nevada, USA

[C26]. E.A. Theodorou and E. Todorov. Relative Entropy Free Energy Dualities: Connections to Path Integral and KL control. In the proceedings of Conference on Decision and Control (CDC), pp: 1466 – 1473, 10-13 Dec. 2012, Maui, HI.

[C25]. E.A. Theodorou and E. Todorov. Stochastic Optimal control of Markov Jump Diffusion processes. In the proceedings of American Control Conference (ACC), pp:1633 – 1639, 27-29 June 2012, Montreal, QC, Canada.

[C24]. E. Rombokas, M. Malhotra, E. A. Theodorou, Todorov and Y. Matsuoka. Tendon Driven Variable stiffness Control with Reinforcement Learning. In the proceedings of Robotic Systems Sciences (RSS), July 2012, Sydney, Australia.

[C23]. M Malhotra, E. Rombokas, E.A. Theodorou, E. Todorov and Y. Matsuoka Reduced di- mensionality control for the ACT hand. In the International Conference of Robotics and Automation (ICRA), pp:5117 – 5122, 14-18 May 2012, Minneapolis, USA.

[C22]. E. Rombokas, E. A. Theodorou, M. Malhotra, E. Todorov and Y. Matsuoka. Tendon- driven control of biomechanical and robotic systems: A path-integral reinforcement learning approach. In the International Conference of Robotics and Automation (ICRA), pp:208 – 214, 14-18 May 2012, Minneapolis, USA.

[C21]. F. Meyer, E. A. Theodorou, S. Schaal. Movement Segmentation and Recognition for Im- itation Learning. Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS),pp: 761-769, 21-23 21-23 April, 2012, La Palma, Canary Islands.

[C20]. F. Stulp, E.A. Theodorou, S. Schaal. Learning Motion Primitive Goals for Robust Manipu- lations. In the International Conference on Intelligent Robotic Systems, pp: 325 – 331, 25-30 Sept. 2011, San Francisco, CA.

[C19]. E.A. Theodorou, F. Stulp, S. Schaal. Path Integral Reinforcement Learning. In the proceedings of the 15th Yale Workshop on Adaptive and Learning Systems, 2011.

[C18]. F. Meyer E.A. Theodorou, F. Stulp, J. Buchli, S. Schaal. Movement segmentation using a library of primitives. In the International Conference on Intelligent Robotic Systems (IROS), pp: 3407 – 3412, 25-30 Sept. 2011, San Francisco, CA.

[C17]. F. Stulp, J. Buchli, A. Ellmer, M. Mistry, E.A. Theodorou, S. Schaal. Reinforcement Learning of Impedance Control in Stochastic Force Fields. In International Conference on Development and Learning, and Epigenetic Robotics, pp:1-6, 24-27 Aug. 2011, Frakfurt, Germany.

[C16]. E.A. Theodorou, F. Stulp, J. Buchli and S. Schaal. Iterative Path Integral Stochastic Optimal Control for Learning Robotic Tasks. In the 18th World Congress of The International Federation of Automatic Control, pp:11594-11601, Aug. 28 – Sept 2, 2011 Milan, Italy.

[C15]. Daniel A. Braun, Pedro A. Ortega, E.A. Theodorou, and S. Schaal. Path Integral Con- trol and Bounded Rationality. In the Proceeding of Adaptive Dynamic Programming and Reinforcement Learning (ADRPL) Symposium, pp:202 – 209, 11-15 April 2011, Paris, France.

[C14]. P. Pastor, M. Kalakrishnan, S. Chitta, E.A. Theodorou, S. Schaal. Skill Learning and Performance Prediction for Manipulation. In the International Conference of Robotics and Automation (ICRA), pp:3828 – 3834, 9-13 May 2011, Shanghai, China. Best paper award in Cognitive Robotics.

[C13]. M. Kalakrishnan, Sachin Chitta, E. A. Theodorou, P. Pastor, S. Schaal. STOMP: Stochastic Trajectory Optimization for Motion Planning. In the International Conference of Robotics and Automation (ICRA), pp:4569 – 4574, 9-13 May 2011, Shanghai, China.

[C12]. F. Stulp, Evangelos Theodorou, Jonas Buchli, Stefan Schaal. Learning to Grasp under Uncertainty. In the International Conference of Robotics and Automation (ICRA), pp:5703 – 5708, 9-13 May 2011, Shanghai, China

[C11]. E.A. Theodorou, E. Todorov, and Francisco J.Valero-Cuevas. Neuromuscular Stochastic Optimal Control of a Tendon Driven Index Finger. In the proceedings of American Control Conference (ACC), pp:348 – 355, June 29 -July 1 2011, San Francisco, CA.

[C10]. F. Stulp, J. Buchli, E.A. Theodorou and S. Schaal. Reinforcement Learning of Full-body Hu- manoid Motor Skills. In proceedings of the International Conference on Humanoid Robotics, pp: 405 – 410, 6-8 Dec. 2010,Nashville, TN. Finalist for the best paper award.

[C9]. E.A. Theodorou and Francisco J.Valero-Cuevas. Optimality in Neuromuscular Systems. In proceedings of the International Conference of the Engineering in Medicine and Biology Society, pp: 4510 – 4516, Aug. 31 -Sept. 4, 2010, Buenos Aires, Argentina.

[C8]. J. Buchli E.A. Theodorou, F. Stulp, and S. Schaal. Variable Impedance Control – A Rein- forcement Learning Approach. In the proceedings of Robotic Sciences and Systems (RSS), June 2010, Zaragoza, Spain.

[C7]. E.A. Theodorou, E. Todorov, and Francisco J.Valero-Cuevas. A first optimal control solu- tion for complex nonlinear, tendon driven neuromuscular finger model. In the proceedings of the American Society of Mechanical Engineering, June 16-19, 2010, Naples, Florida.

[C6]. E.A. Theodorou, J. Buchli , and S. Schaal. Learning Policy Improvement with Path Inte- grals. In the proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS),pp: 828-835, May 13-15, 2010, Sardinia, Italy.

[C5]. E.A. Theodorou, J. Buchli , and S. Schaal. Reinforcement Learning of Motor Skills in high dimensions: A path integral approach. In the International Conference of Robotics and Automation (ICRA), pp:2397 – 2403, 3-7 May 2010, Anchorage, AK.

[C4]. E.A. Theodorou, Y. Tassa and E. Todorov. Stochastic Differential Dynamic Programming. In the proceedings of American Control Conference (ACC), pp:1125 – 1132, June 30-July 2 2010, Baltimore, MD.

[C3]. E.A. Theodorou, J. Buchli , and S. Schaal. Path Integral Stochastic Optimal Control for Rigid Body Dynamics.In the Proceeding of Adaptive Dynamic Programming and Reinforce- ment Learning (ADRPL) Symposium, pp:219 – 225, March 30-April 2 2009, Nashville, TN.

[C2]. J. Ting, E.A. Theodorou, and S. Schaal. Learning an Outlier – Robust Kalman Filter. In European Conference on Machine Learning (ECML) pp:219 – 225, 17-21 Sept. 2007, Warsaw, Poland,.

[C1]. J. Ting, E.A. Theodorou, and S. Schaal. Kalman Filter for Robust Outlier Detection. In the International Conference on Intelligent Robotic Systems (IROS), pp: 1514 – 1519,Oct. 29-Nov. 2 2007, San Diego, CA.