Header logo is


2019


no image
On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset

Gondal, M. W., Wuthrich, M., Miladinovic, D., Locatello, F., Breidt, M., Volchkov, V., Akpo, J., Bachem, O., Schölkopf, B., Bauer, S.

Advances in Neural Information Processing Systems 32, pages: 15714-15725, (Editors: H. Wallach and H. Larochelle and A. Beygelzimer and F. d’Alché-Buc and E. Fox and R. Garnett), Curran Associates, Inc., 33rd Annual Conference on Neural Information Processing Systems, December 2019 (conference)

am ei sf

link (url) [BibTex]

2019


link (url) [BibTex]


Learning to Explore in Motion and Interaction Tasks
Learning to Explore in Motion and Interaction Tasks

Bogdanovic, M., Righetti, L.

Proceedings 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages: 2686-2692, IEEE, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), November 2019, ISSN: 2153-0866 (conference)

Abstract
Model free reinforcement learning suffers from the high sampling complexity inherent to robotic manipulation or locomotion tasks. Most successful approaches typically use random sampling strategies which leads to slow policy convergence. In this paper we present a novel approach for efficient exploration that leverages previously learned tasks. We exploit the fact that the same system is used across many tasks and build a generative model for exploration based on data from previously solved tasks to improve learning new tasks. The approach also enables continuous learning of improved exploration strategies as novel tasks are learned. Extensive simulations on a robot manipulator performing a variety of motion and contact interaction tasks demonstrate the capabilities of the approach. In particular, our experiments suggest that the exploration strategy can more than double learning speed, especially when rewards are sparse. Moreover, the algorithm is robust to task variations and parameter tuning, making it beneficial for complex robotic problems.

mg

DOI [BibTex]

DOI [BibTex]


no image
Robust Humanoid Locomotion Using Trajectory Optimization and Sample-Efficient Learning

Yeganegi, M. H., Khadiv, M., Moosavian, S. A. A., Zhu, J., Prete, A. D., Righetti, L.

Proceedings International Conference on Humanoid Robots, IEEE, 2019 IEEE-RAS International Conference on Humanoid Robots, October 2019 (conference)

Abstract
Trajectory optimization (TO) is one of the most powerful tools for generating feasible motions for humanoid robots. However, including uncertainties and stochasticity in the TO problem to generate robust motions can easily lead to intractable problems. Furthermore, since the models used in TO have always some level of abstraction, it can be hard to find a realistic set of uncertainties in the model space. In this paper we leverage a sample-efficient learning technique (Bayesian optimization) to robustify TO for humanoid locomotion. The main idea is to use data from full-body simulations to make the TO stage robust by tuning the cost weights. To this end, we split the TO problem into two phases. The first phase solves a convex optimization problem for generating center of mass (CoM) trajectories based on simplified linear dynamics. The second stage employs iterative Linear-Quadratic Gaussian (iLQG) as a whole-body controller to generate full body control inputs. Then we use Bayesian optimization to find the cost weights to use in the first stage that yields robust performance in the simulation/experiment, in the presence of different disturbance/uncertainties. The results show that the proposed approach is able to generate robust motions for different sets of disturbances and uncertainties.

mg

https://arxiv.org/abs/1907.04616 link (url) [BibTex]

https://arxiv.org/abs/1907.04616 link (url) [BibTex]


How do people learn how to plan?
How do people learn how to plan?

Jain, Y. R., Gupta, S., Rakesh, V., Dayan, P., Callaway, F., Lieder, F.

Conference on Cognitive Computational Neuroscience, September 2019 (conference)

Abstract
How does the brain learn how to plan? We reverse-engineer people's underlying learning mechanisms by combining rational process models of cognitive plasticity with recently developed empirical methods that allow us to trace the temporal evolution of people's planning strategies. We find that our Learned Value of Computation model (LVOC) accurately captures people's average learning curve. However, there were also substantial individual differences in metacognitive learning that are best understood in terms of multiple different learning mechanisms-including strategy selection learning. Furthermore, we observed that LVOC could not fully capture people's ability to adaptively decide when to stop planning. We successfully extended the LVOC model to address these discrepancies. Our models broadly capture people's ability to improve their decision mechanisms and represent a significant step towards reverse-engineering how the brain learns increasingly effective cognitive strategies through its interaction with the environment.

re

How do people learn to plan? How do people learn to plan? [BibTex]

How do people learn to plan? How do people learn to plan? [BibTex]


no image
Testing Computational Models of Goal Pursuit

Mohnert, F., Tosic, M., Lieder, F.

CCN2019, September 2019 (conference)

Abstract
Goals are essential to human cognition and behavior. But how do we pursue them? To address this question, we model how capacity limits on planning and attention shape the computational mechanisms of human goal pursuit. We test the predictions of a simple model based on previous theories in a behavioral experiment. The results show that to fully capture how people pursue their goals it is critical to account for people’s limited attention in addition to their limited planning. Our findings elucidate the cognitive constraints that shape human goal pursuit and point to an improved model of human goal pursuit that can reliably predict which goals a person will achieve and which goals they will struggle to pursue effectively.

re

link (url) DOI Project Page [BibTex]


no image
Measuring How People Learn How to Plan

Jain, Y. R., Callaway, F., Lieder, F.

Proceedings 41st Annual Meeting of the Cognitive Science Society, pages: 1956-1962, CogSci2019, 41st Annual Meeting of the Cognitive Science Society, July 2019 (conference)

Abstract
The human mind has an unparalleled ability to acquire complex cognitive skills, discover new strategies, and refine its ways of thinking and decision-making; these phenomena are collectively known as cognitive plasticity. One important manifestation of cognitive plasticity is learning to make better–more far-sighted–decisions via planning. A serious obstacle to studying how people learn how to plan is that cognitive plasticity is even more difficult to observe than cognitive strategies are. To address this problem, we develop a computational microscope for measuring cognitive plasticity and validate it on simulated and empirical data. Our approach employs a process tracing paradigm recording signatures of human planning and how they change over time. We then invert a generative model of the recorded changes to infer the underlying cognitive plasticity. Our computational microscope measures cognitive plasticity significantly more accurately than simpler approaches, and it correctly detected the effect of an external manipulation known to promote cognitive plasticity. We illustrate how computational microscopes can be used to gain new insights into the time course of metacognitive learning and to test theories of cognitive development and hypotheses about the nature of cognitive plasticity. Future work will leverage our computational microscope to reverse-engineer the learning mechanisms enabling people to acquire complex cognitive skills such as planning and problem solving.

re

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


no image
Extending Rationality

Pothos, E. M., Busemeyer, J. R., Pleskac, T., Yearsley, J. M., Tenenbaum, J. B., Goodman, N. D., Tessler, M. H., Griffiths, T. L., Lieder, F., Hertwig, R., Pachur, T., Leuker, C., Shiffrin, R. M.

Proceedings of the 41st Annual Conference of the Cognitive Science Society, pages: 39-40, CogSci 2019, July 2019 (conference)

re

Proceedings of the 41st Annual Conference of the Cognitive Science Society [BibTex]

Proceedings of the 41st Annual Conference of the Cognitive Science Society [BibTex]


How should we incentivize learning? An optimal feedback mechanism for educational games and online courses
How should we incentivize learning? An optimal feedback mechanism for educational games and online courses

Xu, L., Wirzberger, M., Lieder, F.

41st Annual Meeting of the Cognitive Science Society, July 2019 (conference)

Abstract
Online courses offer much-needed opportunities for lifelong self-directed learning, but people rarely follow through on their noble intentions to complete them. To increase student retention educational software often uses game elements to motivate students to engage in and persist in learning activities. However, gamification only works when it is done properly, and there is currently no principled method that educational software could use to achieve this. We develop a principled feedback mechanism for encouraging good study choices and persistence in self-directed learning environments. Rather than giving performance feedback, our method rewards the learner's efforts with optimal brain points that convey the value of practice. To derive these optimal brain points, we applied the theory of optimal gamification to a mathematical model of skill acquisition. In contrast to hand-designed incentive structures, optimal brain points are constructed in such a way that the incentive system cannot be gamed. Evaluating our method in a behavioral experiment, we find that optimal brain points significantly increased the proportion of participants who instead of exploiting an inefficient skill they already knew-attempted to learn a difficult but more efficient skill, persisted through failure, and succeeded to master the new skill. Our method provides a principled approach to designing incentive structures and feedback mechanisms for educational games and online courses. We are optimistic that optimal brain points will prove useful for increasing student retention and helping people overcome the motivational obstacles that stand in the way of self-directed lifelong learning.

re

link (url) Project Page [BibTex]


no image
Measuring How People Learn How to Plan

Jain, Y. R., Callaway, F., Lieder, F.

RLDM 2019, July 2019 (conference)

re

[BibTex]

[BibTex]


no image
What’s in the Adaptive Toolbox and How Do People Choose From It? Rational Models of Strategy Selection in Risky Choice

Mohnert, F., Pachur, T., Lieder, F.

41st Annual Meeting of the Cognitive Science Society, July 2019 (conference)

Abstract
Although process data indicates that people often rely on various (often heuristic) strategies to choose between risky options, our models of heuristics cannot predict people's choices very accurately. To address this challenge, it has been proposed that people adaptively choose from a toolbox of simple strategies. But which strategies are contained in this toolbox? And how do people decide when to use which decision strategy? Here, we develop a model according to which each person selects decisions strategies rationally from their personal toolbox; our model allows one to infer which strategies are contained in the cognitive toolbox of an individual decision-maker and specifies when she will use which strategy. Using cross-validation on an empirical data set, we find that this rational model of strategy selection from a personal adaptive toolbox predicts people's choices better than any single strategy (even when it is allowed to vary across participants) and better than previously proposed toolbox models. Our model comparisons show that both inferring the toolbox and rational strategy selection are critical for accurately predicting people's risky choices. Furthermore, our model-based data analysis reveals considerable individual differences in the set of strategies people are equipped with and how they choose among them; these individual differences could partly explain why some people make better choices than others. These findings represent an important step towards a complete formalization of the notion that people select their cognitive strategies from a personal adaptive toolbox.

re

link (url) [BibTex]


no image
A Cognitive Tutor for Helping People Overcome Present Bias

Lieder, F., Callaway, F., Jain, Y. R., Krueger, P. M., Das, P., Gul, S., Griffiths, T. L.

RLDM 2019, July 2019, Falk Lieder and Frederick Callaway contributed equally to this publication. (conference)

Abstract
People's reliance on suboptimal heuristics gives rise to a plethora of cognitive biases in decision-making including the present bias, which denotes people's tendency to be overly swayed by an action's immediate costs/benefits rather than its more important long-term consequences. One approach to helping people overcome such biases is to teach them better decision strategies. But which strategies should we teach them? And how can we teach them effectively? Here, we leverage an automatic method for discovering rational heuristics and insights into how people acquire cognitive skills to develop an intelligent tutor that teaches people how to make better decisions. As a proof of concept, we derive the optimal planning strategy for a simple model of situations where people fall prey to the present bias. Our cognitive tutor teaches people this optimal planning strategy by giving them metacognitive feedback on how they plan in a 3-step sequential decision-making task. Our tutor's feedback is designed to maximally accelerate people's metacognitive reinforcement learning towards the optimal planning strategy. A series of four experiments confirmed that training with the cognitive tutor significantly reduced present bias and improved people's decision-making competency: Experiment 1 demonstrated that the cognitive tutor's feedback can help participants discover far-sighted planning strategies. Experiment 2 found that this training effect transfers to more complex environments. Experiment 3 found that these transfer effects are retained for at least 24 hours after the training. Finally, Experiment 4 found that practicing with the cognitive tutor can have additional benefits over being told the strategy in words. The results suggest that promoting metacognitive reinforcement learning with optimal feedback is a promising approach to improving the human mind.

re

DOI [BibTex]

DOI [BibTex]


no image
Introducing the Decision Advisor: A simple online tool that helps people overcome cognitive biases and experience less regret in real-life decisions

Iwama, G., Greenberg, S., Moore, D., Lieder, F.

40th Annual Meeting of the Society for Judgement and Decision Making, June 2019 (conference)

re

[BibTex]

[BibTex]


no image
The Goal Characteristics (GC) questionannaire: A comprehensive measure for goals’ content, attainability, interestingness, and usefulness

Iwama, G., Wirzberger, M., Lieder, F.

40th Annual Meeting of the Society for Judgement and Decision Making, June 2019 (conference)

Abstract
Many studies have investigated how goal characteristics affect goal achievement. However, most of them considered only a small number of characteristics and the psychometric properties of their measures remains unclear. To overcome these limitations, we developed and validated a comprehensive questionnaire of goal characteristics with four subscales - measuring the goal’s content, attainability, interestingness, and usefulness respectively. 590 participants completed the questionnaire online. A confirmatory factor analysis supported the four subscales and their structure. The GC questionnaire (https://osf.io/qfhup) can be easily applied to investigate goal setting, pursuit and adjustment in a wide range of contexts.

re

DOI [BibTex]


Accurate Vision-based Manipulation through Contact Reasoning
Accurate Vision-based Manipulation through Contact Reasoning

Kloss, A., Bauza, M., Wu, J., Tenenbaum, J. B., Rodriguez, A., Bohg, J.

In International Conference on Robotics and Automation, May 2019 (inproceedings) Accepted

Abstract
Planning contact interactions is one of the core challenges of many robotic tasks. Optimizing contact locations while taking dynamics into account is computationally costly and in only partially observed environments, executing contact-based tasks often suffers from low accuracy. We present an approach that addresses these two challenges for the problem of vision-based manipulation. First, we propose to disentangle contact from motion optimization. Thereby, we improve planning efficiency by focusing computation on promising contact locations. Second, we use a hybrid approach for perception and state estimation that combines neural networks with a physically meaningful state representation. In simulation and real-world experiments on the task of planar pushing, we show that our method is more efficient and achieves a higher manipulation accuracy than previous vision-based approaches.

am

Video link (url) [BibTex]

Video link (url) [BibTex]


no image
Efficient Humanoid Contact Planning using Learned Centroidal Dynamics Prediction

Lin, Y., Ponton, B., Righetti, L., Berenson, D.

International Conference on Robotics and Automation (ICRA), pages: 5280-5286, IEEE, May 2019 (conference)

mg

DOI [BibTex]

DOI [BibTex]


Learning Latent Space Dynamics for Tactile Servoing
Learning Latent Space Dynamics for Tactile Servoing

Sutanto, G., Ratliff, N., Sundaralingam, B., Chebotar, Y., Su, Z., Handa, A., Fox, D.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2019, IEEE, International Conference on Robotics and Automation, May 2019 (inproceedings) Accepted

am

pdf video [BibTex]

pdf video [BibTex]


Leveraging Contact Forces for Learning to Grasp
Leveraging Contact Forces for Learning to Grasp

Merzic, H., Bogdanovic, M., Kappler, D., Righetti, L., Bohg, J.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2019, IEEE, International Conference on Robotics and Automation, May 2019 (inproceedings)

Abstract
Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it is crucial that it continuously takes sensor feedback into account. While visual feedback is important for inferring a grasp pose and reaching for an object, contact feedback offers valuable information during manipulation and grasp acquisition. In this paper, we use model-free deep reinforcement learning to synthesize control policies that exploit contact sensing to generate robust grasping under uncertainty. We demonstrate our approach on a multi-fingered hand that exhibits more complex finger coordination than the commonly used two- fingered grippers. We conduct extensive experiments in order to assess the performance of the learned policies, with and without contact sensing. While it is possible to learn grasping policies without contact sensing, our results suggest that contact feedback allows for a significant improvement of grasping robustness under object pose uncertainty and for objects with a complex shape.

am mg

video arXiv [BibTex]

video arXiv [BibTex]


no image
Remediating cognitive decline with cognitive tutors

Das, P., Callaway, F., Griffiths, T., Lieder, F.

RLDM 2019, 2019 (conference)

re

[BibTex]

[BibTex]

2011


no image
STOMP: Stochastic trajectory optimization for motion planning

Kalakrishnan, M., Chitta, S., Theodorou, E., Pastor, P., Schaal, S.

In IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China, May 9-13, 2011, clmc (inproceedings)

Abstract
We present a new approach to motion planning using a stochastic trajectory optimization framework. The approach relies on generating noisy trajectories to explore the space around an initial (possibly infeasible) trajectory, which are then combined to produced an updated trajectory with lower cost. A cost function based on a combination of obstacle and smoothness cost is optimized in each iteration. No gradient information is required for the particular optimization algorithm that we use and so general costs for which derivatives may not be available (e.g. costs corresponding to constraints and motor torques) can be included in the cost function. We demonstrate the approach both in simulation and on a dual-arm mobile manipulation system for unconstrained and constrained tasks. We experimentally show that the stochastic nature of STOMP allows it to overcome local minima that gradient-based optimizers like CHOMP can get stuck in.

am

link (url) Project Page [BibTex]

2011


link (url) Project Page [BibTex]


no image
Path Integral Control and Bounded Rationality

Braun, D. A., Ortega, P. A., Theodorou, E., Schaal, S.

In IEEE Symposium on Adaptive Dynamic Programming And Reinforcement Learning (ADPRL), 2011, clmc (inproceedings)

Abstract
Path integral methods [7], [15],[1] have recently been shown to be applicable to a very general class of optimal control problems. Here we examine the path integral formalism from a decision-theoretic point of view, since an optimal controller can always be regarded as an instance of a perfectly rational decision-maker that chooses its actions so as to maximize its expected utility [8]. The problem with perfect rationality is, however, that finding optimal actions is often very difficult due to prohibitive computational resource costs that are not taken into account. In contrast, a bounded rational decision-maker has only limited resources and therefore needs to strike some compromise between the desired utility and the required resource costs [14]. In particular, we suggest an information-theoretic measure of resource costs that can be derived axiomatically [11]. As a consequence we obtain a variational principle for choice probabilities that trades off maximizing a given utility criterion and avoiding resource costs that arise due to deviating from initially given default choice probabilities. The resulting bounded rational policies are in general probabilistic. We show that the solutions found by the path integral formalism are such bounded rational policies. Furthermore, we show that the same formalism generalizes to discrete control problems, leading to linearly solvable bounded rational control policies in the case of Markov systems. Importantly, Bellman?s optimality principle is not presupposed by this variational principle, but it can be derived as a limit case. This suggests that the information- theoretic formalization of bounded rationality might serve as a general principle in control design that unifies a number of recently reported approximate optimal control methods both in the continuous and discrete domain.

am

PDF [BibTex]

PDF [BibTex]


no image
Skill learning and task outcome prediction for manipulation

Pastor, P., Kalakrishnan, M., Chitta, S., Theodorou, E., Schaal, S.

In IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China, May 9-13, 2011, clmc (inproceedings)

Abstract
Learning complex motor skills for real world tasks is a hard problem in robotic manipulation that often requires painstaking manual tuning and design by a human expert. In this work, we present a Reinforcement Learning based approach to acquiring new motor skills from demonstration. Our approach allows the robot to learn fine manipulation skills and significantly improve its success rate and skill level starting from a possibly coarse demonstration. Our approach aims to incorporate task domain knowledge, where appropriate, by working in a space consistent with the constraints of a specific task. In addition, we also present an approach to using sensor feedback to learn a predictive model of the task outcome. This allows our system to learn the proprioceptive sensor feedback needed to monitor subsequent executions of the task online and abort execution in the event of predicted failure. We illustrate our approach using two example tasks executed with the PR2 dual-arm robot: a straight and accurate pool stroke and a box flipping task using two chopsticks as tools.

am

link (url) Project Page Project Page [BibTex]

link (url) Project Page Project Page [BibTex]


no image
An Iterative Path Integral Stochastic Optimal Control Approach for Learning Robotic Tasks

Theodorou, E., Stulp, F., Buchli, J., Schaal, S.

In Proceedings of the 18th World Congress of the International Federation of Automatic Control, 2011, clmc (inproceedings)

Abstract
Recent work on path integral stochastic optimal control theory Theodorou et al. (2010a); Theodorou (2011) has shown promising results in planning and control of nonlinear systems in high dimensional state spaces. The path integral control framework relies on the transformation of the nonlinear Hamilton Jacobi Bellman (HJB) partial differential equation (PDE) into a linear PDE and the approximation of its solution via the use of the Feynman Kac lemma. In this work, we are reviewing the generalized version of path integral stochastic optimal control formalism Theodorou et al. (2010a), used for optimal control and planing of stochastic dynamical systems with state dependent control and diffusion matrices. Moreover we present the iterative path integral control approach, the so called Policy Improvement with Path Integrals or (PI2 ) which is capable of scaling in high dimensional robotic control problems. Furthermore we present a convergence analysis of the proposed algorithm and we apply the proposed framework to a variety of robotic tasks. Finally with the goal to perform locomotion the iterative path integral control is applied for learning nonlinear limit cycle attractors with adjustable land scape.

am

PDF [BibTex]

PDF [BibTex]


no image
Learning Force Control Policies for Compliant Manipulation

Kalakrishnan, M., Righetti, L., Pastor, P., Schaal, S.

In 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 4639-4644, IEEE, San Francisco, USA, sep 2011 (inproceedings)

Abstract
Developing robots capable of fine manipulation skills is of major importance in order to build truly assistive robots. These robots need to be compliant in their actuation and control in order to operate safely in human environments. Manipulation tasks imply complex contact interactions with the external world, and involve reasoning about the forces and torques to be applied. Planning under contact conditions is usually impractical due to computational complexity, and a lack of precise dynamics models of the environment. We present an approach to acquiring manipulation skills on compliant robots through reinforcement learning. The initial position control policy for manipulation is initialized through kinesthetic demonstration. We augment this policy with a force/torque profile to be controlled in combination with the position trajectories. We use the Policy Improvement with Path Integrals (PI2) algorithm to learn these force/torque profiles by optimizing a cost function that measures task success. We demonstrate our approach on the Barrett WAM robot arm equipped with a 6-DOF force/torque sensor on two different manipulation tasks: opening a door with a lever door handle, and picking up a pen off the table. We show that the learnt force control policies allow successful, robust execution of the tasks.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Control of legged robots with optimal distribution of contact forces

Righetti, L., Buchli, J., Mistry, M., Schaal, S.

In 2011 11th IEEE-RAS International Conference on Humanoid Robots, pages: 318-324, IEEE, Bled, Slovenia, 2011 (inproceedings)

Abstract
The development of agile and safe humanoid robots require controllers that guarantee both high tracking performance and compliance with the environment. More specifically, the control of contact interaction is of crucial importance for robots that will actively interact with their environment. Model-based controllers such as inverse dynamics or operational space control are very appealing as they offer both high tracking performance and compliance. However, while widely used for fully actuated systems such as manipulators, they are not yet standard controllers for legged robots such as humanoids. Indeed such robots are fundamentally different from manipulators as they are underactuated due to their floating-base and subject to switching contact constraints. In this paper we present an inverse dynamics controller for legged robots that use torque redundancy to create an optimal distribution of contact constraints. The resulting controller is able to minimize, given a desired motion, any quadratic cost of the contact constraints at each instant of time. In particular we show how this can be used to minimize tangential forces during locomotion, therefore significantly improving the locomotion of legged robots on difficult terrains. In addition to the theoretical result, we present simulations of a humanoid and a quadruped robot, as well as experiments on a real quadruped robot that demonstrate the advantages of the controller.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Learning Motion Primitive Goals for Robust Manipulation

Stulp, F., Theodorou, E., Kalakrishnan, M., Pastor, P., Righetti, L., Schaal, S.

In IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 325-331, IEEE, San Francisco, USA, sep 2011 (inproceedings)

Abstract
Applying model-free reinforcement learning to manipulation remains challenging for several reasons. First, manipulation involves physical contact, which causes discontinuous cost functions. Second, in manipulation, the end-point of the movement must be chosen carefully, as it represents a grasp which must be adapted to the pose and shape of the object. Finally, there is uncertainty in the object pose, and even the most carefully planned movement may fail if the object is not at the expected position. To address these challenges we 1) present a simplified, computationally more efficient version of our model-free reinforcement learning algorithm PI2; 2) extend PI2 so that it simultaneously learns shape parameters and goal parameters of motion primitives; 3) use shape and goal learning to acquire motion primitives that are robust to object pose uncertainty. We evaluate these contributions on a manipulation platform consisting of a 7-DOF arm with a 4-DOF hand.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Inverse Dynamics Control of Floating-Base Robots with External Constraints: a Unified View

Righetti, L., Buchli, J., Mistry, M., Schaal, S.

In 2011 IEEE International Conference on Robotics and Automation, pages: 1085-1090, IEEE, Shanghai, China, 2011 (inproceedings)

Abstract
Inverse dynamics controllers and operational space controllers have proved to be very efficient for compliant control of fully actuated robots such as fixed base manipulators. However legged robots such as humanoids are inherently different as they are underactuated and subject to switching external contact constraints. Recently several methods have been proposed to create inverse dynamics controllers and operational space controllers for these robots. In an attempt to compare these different approaches, we develop a general framework for inverse dynamics control and show that these methods lead to very similar controllers. We are then able to greatly simplify recent whole-body controllers based on operational space approaches using kinematic projections, bringing them closer to efficient practical implementations. We also generalize these controllers such that they can be optimal under an arbitrary quadratic cost in the commands.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Movement segmentation using a primitive library

Meier, F., Theodorou, E., Stulp, F., Schaal, S.

In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), Sept. 25-30, San Francisco, CA, 2011, clmc (inproceedings)

Abstract
Segmenting complex movements into a sequence of primitives remains a difficult problem with many applications in the robotics and vision communities. In this work, we show how the movement segmentation problem can be reduced to a sequential movement recognition problem. To this end, we reformulate the orig-inal Dynamic Movement Primitive (DMP) formulation as a linear dynamical sys-tem with control inputs. Based on this new formulation, we develop an Expecta-tion-Maximization algorithm to estimate the duration and goal position of a par-tially observed trajectory. With the help of this algorithm and the assumption that a library of movement primitives is present, we present a movement seg-mentation framework. We illustrate the usefulness of the new DMP formulation on the two applications of online movement recognition and movement segmen-tation.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Operational Space Control of Constrained and Underactuated Systems

Mistry, M., Righetti, L.

In Proceedings of Robotics: Science and Systems, Los Angeles, CA, USA, June 2011 (inproceedings)

Abstract
The operational space formulation (Khatib, 1987), applied to rigid-body manipulators, describes how to decouple task-space and null-space dynamics, and write control equations that correspond only to forces at the end-effector or, alternatively, only to motion within the null-space. We would like to apply this useful theory to modern humanoids and other legged systems, for manipulation or similar tasks, however these systems present additional challenges due to their underactuated floating bases and contact states that can dynamically change. In recent work, Sentis et al. derived controllers for such systems by implementing a task Jacobian projected into a space consistent with the supporting constraints and underactuation (the so called "support consistent reduced Jacobian"). Here, we take a new approach to derive operational space controllers for constrained underactuated systems, by first considering the operational space dynamics within "projected inverse-dynamics" (Aghili, 2005), and subsequently resolving underactuation through the addition of dynamically consistent control torques. Doing so results in a simplified control solution compared with previous results, and importantly yields several new insights into the underlying problem of operational space control in constrained environments: 1) Underactuated systems, such as humanoid robots, cannot in general completely decouple task and null-space dynamics. However, 2) there may exist an infinite number of control solutions to realize desired task-space dynamics, and 3) these solutions involve the addition of dynamically consistent null-space motion or constraint forces (or combinations of both). In light of these findings, we present several possible control solutions, with varying optimization criteria, and highlight some of their practical consequences.

mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Online movement adaptation based on previous sensor experiences

Pastor, P., Righetti, L., Kalakrishnan, M., Schaal, S.

In 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 365-371, IEEE, San Francisco, USA, sep 2011 (inproceedings)

Abstract
Personal robots can only become widespread if they are capable of safely operating among humans. In uncertain and highly dynamic environments such as human households, robots need to be able to instantly adapt their behavior to unforseen events. In this paper, we propose a general framework to achieve very contact-reactive motions for robotic grasping and manipulation. Associating stereotypical movements to particular tasks enables our system to use previous sensor experiences as a predictive model for subsequent task executions. We use dynamical systems, named Dynamic Movement Primitives (DMPs), to learn goal-directed behaviors from demonstration. We exploit their dynamic properties by coupling them with the measured and predicted sensor traces. This feedback loop allows for online adaptation of the movement plan. Our system can create a rich set of possible motions that account for external perturbations and perception uncertainty to generate truly robust behaviors. As an example, we present an application to grasping with the WAM robot arm.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Additional DOFs and sensors for bio-inspired locomotion: Towards active spine, ankle joints, and feet for a quadruped robot

Kuehn, D., Grimminger, F., Beinersdorf, F., Bernhard, F., Burchardt, A., Schilling, M., Simnofske, M., Stark, T., Zenzes, M., Kirchner, F.

In 2011 IEEE International Conference on Robotics and Biomimetics, pages: 2780-2786, December 2011 (inproceedings)

am

DOI [BibTex]

DOI [BibTex]


no image
Learning to grasp under uncertainty

Stulp, F., Theodorou, E., Buchli, J., Schaal, S.

In Robotics and Automation (ICRA), 2011 IEEE International Conference on, Shanghai, China, May 9-13, 2011, clmc (inproceedings)

Abstract
We present an approach that enables robots to learn motion primitives that are robust towards state estimation uncertainties. During reaching and preshaping, the robot learns to use fine manipulation strategies to maneuver the object into a pose at which closing the hand to perform the grasp is more likely to succeed. In contrast, common assumptions in grasp planning and motion planning for reaching are that these tasks can be performed independently, and that the robot has perfect knowledge of the pose of the objects in the environment. We implement our approach using Dynamic Movement Primitives and the probabilistic model-free reinforcement learning algorithm Policy Improvement with Path Integrals (PI2 ). The cost function that PI2 optimizes is a simple boolean that penalizes failed grasps. The key to acquiring robust motion primitives is to sample the actual pose of the object from a distribution that represents the state estimation uncertainty. During learning, the robot will thus optimize the chance of grasping an object from this distribution, rather than at one specific pose. In our empirical evaluation, we demonstrate how the motion primitives become more robust when grasping simple cylindrical objects, as well as more complex, non-convex objects. We also investigate how well the learned motion primitives generalize towards new object positions and other state estimation uncertainty distributions.

am

link (url) [BibTex]

link (url) [BibTex]

1998


no image
Programmable pattern generators

Schaal, S., Sternad, D.

In 3rd International Conference on Computational Intelligence in Neuroscience, pages: 48-51, Research Triangle Park, NC, Oct. 24-28, October 1998, clmc (inproceedings)

Abstract
This paper explores the idea to create complex human-like arm movements from movement primitives based on nonlinear attractor dynamics. Each degree-of-freedom of an arm is assumed to have two independent abilities to create movement, one through a discrete dynamic system, and one through a rhythmic system. The discrete system creates point-to-point movements based on internal or external target specifications. The rhythmic system can add an additional oscillatory movement relative to the current position of the discrete system. In the present study, we develop appropriate dynamic systems that can realize the above model, motivate the particular choice of the systems from a biological and engineering point of view, and present simulation results of the performance of such movement primitives. Implementation results on a Sarcos Dexterous Arm are discussed.

am

link (url) [BibTex]

1998


link (url) [BibTex]


no image
Robust local learning in high dimensional spaces

Vijayakumar, S., Schaal, S.

In 5th Joint Symposium on Neural Computation, pages: 186-193, Institute for Neural Computation, University of California, San Diego, San Diego, CA, 1998, clmc (inproceedings)

Abstract
Incremental learning of sensorimotor transformations in high dimensional spaces is one of the basic prerequisites for the success of autonomous robot devices as well as biological movement systems. So far, due to sparsity of data in high dimensional spaces, learning in such settings requires a significant amount of prior knowledge about the learning task, usually provided by a human expert. In this paper, we suggest a partial revision of this view. Based on empirical studies, we observed that, despite being globally high dimensional and sparse, data distributions from physical movement systems are locally low dimensional and dense. Under this assumption, we derive a learning algorithm, Locally Adaptive Subspace Regression, that exploits this property by combining a dynamically growing local dimensionality reduction technique as a preprocessing step with a nonparametric learning technique, locally weighted regression, that also learns the region of validity of the regression. The usefulness of the algorithm and the validity of its assumptions are illustrated for a synthetic data set, and for data of the inverse dynamics of human arm movements and an actual 7 degree-of-freedom anthropomorphic robot arm.

am

[BibTex]

[BibTex]


no image
Local dimensionality reduction

Schaal, S., Vijayakumar, S., Atkeson, C. G.

In Advances in Neural Information Processing Systems 10, pages: 633-639, (Editors: Jordan, M. I.;Kearns, M. J.;Solla, S. A.), MIT Press, Cambridge, MA, 1998, clmc (inproceedings)

Abstract
If globally high dimensional data has locally only low dimensional distributions, it is advantageous to perform a local dimensionality reduction before further processing the data. In this paper we examine several techniques for local dimensionality reduction in the context of locally weighted linear regression. As possible candidates, we derive local versions of factor analysis regression, principle component regression, principle component regression on joint distributions, and partial least squares regression. After outlining the statistical bases of these methods, we perform Monte Carlo simulations to evaluate their robustness with respect to violations of their statistical assumptions. One surprising outcome is that locally weighted partial least squares regression offers the best average results, thus outperforming even factor analysis, the theoretically most appealing of our candidate techniques.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Biomimetic gaze stabilization based on a study of the vestibulocerebellum

Shibata, T., Schaal, S.

In European Workshop on Learning Robots, pages: 84-94, Edinburgh, UK, 1998, clmc (inproceedings)

Abstract
Accurate oculomotor control is one of the essential pre-requisites for successful visuomotor coordination. In this paper, we suggest a biologically inspired control system for learning gaze stabilization with a biomimetic robotic oculomotor system. In a stepwise fashion, we develop a control circuit for the vestibulo-ocular reflex (VOR) and the opto-kinetic response (OKR), and add a nonlinear learning network to allow adaptivity. We discuss the parallels and differences of our system with biological oculomotor control and suggest solutions how to deal with nonlinearities and time delays in the control system. In simulation and actual robot studies, we demonstrate that our system can learn gaze stabilization in real time in only a few seconds with high final accuracy.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Towards biomimetic vision

Shibata, T., Schaal, S.

In International Conference on Intelligence Robots and Systems, pages: 872-879, Victoria, Canada, 1998, clmc (inproceedings)

Abstract
Oculomotor control is the foundation of most biological visual systems, as well as an important component in the entire perceptual-motor system. We review some of the most basic principles of biological oculomotor systems, and explore their usefulness from both the biological and computational point of view. As an example of biomimetic oculomotor control, we present the state of our implementations and experimental results using the vestibulo-ocular-reflex and opto-kinetic-reflex paradigm

am

link (url) [BibTex]

link (url) [BibTex]

1995


no image
A kendama learning robot based on a dynamic optimization theory

Miyamoto, H., Gandolfo, F., Gomi, H., Schaal, S., Koike, Y., Osu, R., Nakano, E., Kawato, M.

In Preceedings of the 4th IEEE International Workshop on Robot and Human Communication (RO-MAN’95), pages: 327-332, Tokyo, July 1995, clmc (inproceedings)

am

[BibTex]

1995


[BibTex]

1994


no image
Robot learning by nonparametric regression

Schaal, S., Atkeson, C. G.

In Proceedings of the International Conference on Intelligent Robots and Systems (IROS’94), pages: 478-485, Munich Germany, 1994, clmc (inproceedings)

Abstract
We present an approach to robot learning grounded on a nonparametric regression technique, locally weighted regression. The model of the task to be performed is represented by infinitely many local linear models, i.e., the (hyper-) tangent planes at every query point. Such a model, however, is only generated when a query is performed and is not retained. This is in contrast to other methods using a finite set of linear models to accomplish a piecewise linear model. Architectural parameters of our approach, such as distance metrics, are also a function of the current query point instead of being global. Statistical tests are presented for when a local model is good enough such that it can be reliably used to build a local controller. These statistical measures also direct the exploration of the robot. We explicitly deal with the case where prediction accuracy requirements exist during exploration: By gradually shifting a center of exploration and controlling the speed of the shift with local prediction accuracy, a goal-directed exploration of state space takes place along the fringes of the current data support until the task goal is achieved. We illustrate this approach by describing how it has been used to enable a robot to learn a challenging juggling task: Within 40 to 100 trials the robot accomplished the task goal starting out with no initial experiences.

am

[BibTex]

1994


[BibTex]


no image
Assessing the quality of learned local models

Schaal, S., Atkeson, C. G.

In Advances in Neural Information Processing Systems 6, pages: 160-167, (Editors: Cowan, J.;Tesauro, G.;Alspector, J.), Morgan Kaufmann, San Mateo, CA, 1994, clmc (inproceedings)

Abstract
An approach is presented to learning high dimensional functions in the case where the learning algorithm can affect the generation of new data. A local modeling algorithm, locally weighted regression, is used to represent the learned function. Architectural parameters of the approach, such as distance metrics, are also localized and become a function of the query point instead of being global. Statistical tests are given for when a local model is good enough and sampling should be moved to a new area. Our methods explicitly deal with the case where prediction accuracy requirements exist during exploration: By gradually shifting a "center of exploration" and controlling the speed of the shift with local prediction accuracy, a goal-directed exploration of state space takes place along the fringes of the current data support until the task goal is achieved. We illustrate this approach with simulation results and results from a real robot learning a complex juggling task.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Memory-based robot learning

Schaal, S., Atkeson, C. G.

In IEEE International Conference on Robotics and Automation, 3, pages: 2928-2933, San Diego, CA, 1994, clmc (inproceedings)

Abstract
We present a memory-based local modeling approach to robot learning using a nonparametric regression technique, locally weighted regression. The model of the task to be performed is represented by infinitely many local linear models, the (hyper-) tangent planes at every query point. This is in contrast to other methods using a finite set of linear models to accomplish a piece-wise linear model. Architectural parameters of our approach, such as distance metrics, are a function of the current query point instead of being global. Statistical tests are presented for when a local model is good enough such that it can be reliably used to build a local controller. These statistical measures also direct the exploration of the robot. We explicitly deal with the case where prediction accuracy requirements exist during exploration: By gradually shifting a center of exploration and controlling the speed of the shift with local prediction accuracy, a goal-directed exploration of state space takes place along the fringes of the current data support until the task goal is achieved. We illustrate this approach by describing how it has been used to enable a robot to learn a challenging juggling task: within 40 to 100 trials the robot accomplished the task goal starting out with no initial experiences.

am

[BibTex]

[BibTex]


no image
Nonparametric regression for learning

Schaal, S.

In Conference on Adaptive Behavior and Learning, Center of Interdisciplinary Research (ZIF) Bielefeld Germany, also technical report TR-H-098 of the ATR Human Information Processing Research Laboratories, 1994, clmc (inproceedings)

Abstract
In recent years, learning theory has been increasingly influenced by the fact that many learning algorithms have at least in part a comprehensive interpretation in terms of well established statistical theories. Furthermore, with little modification, several statistical methods can be directly cast into learning algorithms. One family of such methods stems from nonparametric regression. This paper compares nonparametric learning with the more widely used parametric counterparts and investigates how these two families differ in their properties and their applicability. 

am

link (url) [BibTex]

link (url) [BibTex]

1993


no image
Roles for memory-based learning in robotics

Atkeson, C. G., Schaal, S.

In Proceedings of the Sixth International Symposium on Robotics Research, pages: 503-521, Hidden Valley, PA, 1993, clmc (inproceedings)

am

[BibTex]

1993


[BibTex]


no image
Open loop stable control strategies for robot juggling

Schaal, S., Atkeson, C. G.

In IEEE International Conference on Robotics and Automation, 3, pages: 913-918, Piscataway, NJ: IEEE, Georgia, Atlanta, May 2-6, 1993, clmc (inproceedings)

Abstract
In a series of case studies out of the field of dynamic manipulation (Mason, 1992), different principles for open loop stable control are introduced and analyzed. This investigation may provide some insight into how open loop control can serve as a useful foundation for closed loop control and, particularly, what to focus on in learning control. 

am

link (url) [BibTex]

link (url) [BibTex]