34 results

2017


Thumb md fig toyex lqr1kernel 1
On the Design of LQR Kernels for Efficient Controller Learning

Marco, A., Hennig, P., Schaal, S., Trimpe, S.

Proceedings of the 56th IEEE Conference on Decision and Control, December 2017 (conference) Accepted

Abstract
Finding optimal feedback controllers for nonlinear dynamic systems from data is hard. Recently, Bayesian optimization (BO) has been proposed as a powerful framework for direct controller tuning from experimental trials. For selecting the next query point and finding the global optimum, BO relies on a probabilistic description of the latent objective function, typically a Gaussian process (GP). As is shown herein, GPs with a common kernel choice can, however, lead to poor learning outcomes on standard quadratic control problems. For a first-order system, we construct two kernels that specifically leverage the structure of the well-known Linear Quadratic Regulator (LQR), yet retain the flexibility of Bayesian nonparametric learning. Simulations of uncertain linear and nonlinear systems demonstrate that the LQR kernels yield superior learning performance.

Project Page [BibTex]

2017

Project Page [BibTex]


Thumb md octo turned
Real-time Perception meets Reactive Motion Generation

Kappler, D., Meier, F., Issac, J., Mainprice, J., Garcia Cifuentes, C., Wüthrich, M., Berenz, V., Schaal, S., Ratliff, N., Bohg, J.

https://arxiv.org/abs/1703.03512, ArXiv, 2017 (article)

Abstract
We address the challenging problem of robotic grasping and manipulation in the presence of uncertainty. This uncertainty is due to noisy sensing, inaccurate models and hard-to-predict environment dynamics. Our approach emphasizes the importance of continuous, real-time perception and its tight integration with reactive motion generation methods. We present a fully integrated system where real-time object and robot tracking as well as ambient world modeling provides the necessary input to feedback controllers and continuous motion optimizers. Specifically, they provide attractive and repulsive potentials based on which the controllers and motion optimizer can online compute movement policies at different time intervals. We extensively evaluate the proposed system on a real robotic platform in four scenarios that exhibit either challenging workspace geometry or a dynamic environment. We compare the proposed integrated system with a more traditional sense-plan-act approach that is still widely used. In 333 experiments, we show the robustness and accuracy of the proposed system.

arxiv video video Project Page [BibTex]


Thumb md mf es
Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization

Marco, A., Berkenkamp, F., Hennig, P., Schoellig, A. P., Krause, A., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 1557-1563, IEEE International Conference on Robotics and Automation, May 2017 (inproceedings)

PDF arXiv DOI Project Page [BibTex]

PDF arXiv DOI Project Page [BibTex]


Thumb md fig  quali  arm
Probabilistic Articulated Real-Time Tracking for Robot Manipulation

(Finalist of Best Robotic Vision Paper Award of ICRA 2017)

Garcia Cifuentes, C., Issac, J., Wüthrich, M., Schaal, S., Bohg, J.

IEEE Robotics and Automation Letters (RA-L), 2(2):577-584, April 2017 (article)

Abstract
We propose a probabilistic filtering method which fuses joint measurements with depth images to yield a precise, real-time estimate of the end-effector pose in the camera frame. This avoids the need for frame transformations when using it in combination with visual object tracking methods. Precision is achieved by modeling and correcting biases in the joint measurements as well as inaccuracies in the robot model, such as poor extrinsic camera calibration. We make our method computationally efficient through a principled combination of Kalman filtering of the joint measurements and asynchronous depth-image updates based on the Coordinate Particle Filter. We quantitatively evaluate our approach on a dataset recorded from a real robotic platform, annotated with ground truth from a motion capture system. We show that our approach is robust and accurate even under challenging conditions such as fast motion, significant and long-term occlusions, and time-varying biases. We release the dataset along with open-source code of our approach to allow for quantitative comparison with alternative approaches.

arXiv video code and dataset video PDF DOI Project Page [BibTex]


Thumb md screen shot 2016 01 19 at 14.48.37
Automatic LQR Tuning Based on Gaussian Process Global Optimization

Marco, A., Hennig, P., Bohg, J., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), IEEE International Conference on Robotics and Automation, May 2016 (inproceedings)

Abstract
This paper proposes an automatic controller tuning framework based on linear optimal control combined with Bayesian optimization. With this framework, an initial set of controller gains is automatically improved according to a pre-defined performance objective evaluated from experimental data. The underlying Bayesian optimization algorithm is Entropy Search, which represents the latent objective as a Gaussian process and constructs an explicit belief over the location of the objective minimum. This is used to maximize the information gain from each experimental evaluation. Thus, this framework shall yield improved controllers with fewer evaluations compared to alternative approaches. A seven-degree- of-freedom robot arm balancing an inverted pole is used as the experimental demonstrator. Results of a two- and four- dimensional tuning problems highlight the method’s potential for automatic controller tuning on robotic platforms.

Video PDF DOI Project Page Project Page [BibTex]

Video PDF DOI Project Page Project Page [BibTex]

2015


Policy Search for Imitation Learning

Doerr, A.

University of Stuttgart, January 2015 (thesis)

link (url) Project Page [BibTex]

2015


Thumb md mt cover
Gaussian Process Optimization for Self-Tuning Control

Marco, A.

Polytechnic University of Catalonia (BarcelonaTech), October 2015 (mastersthesis)

PDF Project Page Project Page [BibTex]

PDF Project Page Project Page [BibTex]


Thumb md screenshot from 2015 09 14 11 58 36
Predicting Human Reaching Motion in Collaborative Tasks Using Inverse Optimal Control and Iterative Re-planning

Mainprice, J., Hayne, R., Berenson, D.

In Proceedings of the IEEE International Conference on Robotics and Automation, 2015 (inproceedings)

Project Page [BibTex]

Project Page [BibTex]


Thumb md posterior
Automatic LQR Tuning Based on Gaussian Process Optimization: Early Experimental Results

Marco, A., Hennig, P., Bohg, J., Schaal, S., Trimpe, S.

Machine Learning in Planning and Control of Robot Motion Workshop at the IEEE/RSJ International Conference on Intelligent Robots and Systems, September 2015 (conference)

Abstract
This paper proposes an automatic controller tuning framework based on linear optimal control combined with Bayesian optimization. With this framework, an initial set of controller gains is automatically improved according to a pre-defined performance objective evaluated from experimental data. The underlying Bayesian optimization algorithm is Entropy Search, which represents the latent objective as a Gaussian process and constructs an explicit belief over the location of the objective minimum. This is used to maximize the information gain from each experimental evaluation. Thus, this framework shall yield improved controllers with fewer evaluations compared to alternative approaches. A seven-degree-of-freedom robot arm balancing an inverted pole is used as the experimental demonstrator. Preliminary results of a low-dimensional tuning problem highlight the method’s potential for automatic controller tuning on robotic platforms.

PDF Project Page Project Page [BibTex]

PDF Project Page Project Page [BibTex]


Thumb md climbing steps
Trajectory generation for multi-contact momentum-control

Herzog, A., Rotella, N., Schaal, S., Righetti, L.

In IEEE-RAS International Conference on Humanoid Robots (Humanoids), November 2015 (inproceedings)

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


Understanding the Geometry of Workspace Obstacles in Motion Optimization

Ratliff, N., Toussaint, M., Schaal, S.

In Proceedings of the IEEE International Conference on Robotics and Automation, March 2015 (inproceedings)

PDF Video Project Page [BibTex]

PDF Video Project Page [BibTex]


Data-Driven Online Decision Making for Autonomous Manipulation

Kappler, D., Pastor, P., Kalakrishnan, M., Wuthrich, M., Schaal, S.

In Proceedings of Robotics: Science and Systems, Rome, Italy, 2015 (inproceedings)

Project Page [BibTex]

Project Page [BibTex]


Thumb md screen shot 2015 08 22 at 21.47.37
Direct Loss Minimization Inverse Optimal Control

Doerr, A., Ratliff, N., Bohg, J., Toussaint, M., Schaal, S.

In Proceedings of Robotics: Science and Systems, Rome, Italy, Robotics: Science and Systems XI, July 2015 (inproceedings)

Abstract
Inverse Optimal Control (IOC) has strongly impacted the systems engineering process, enabling automated planner tuning through straightforward and intuitive demonstration. The most successful and established applications, though, have been in lower dimensional problems such as navigation planning where exact optimal planning or control is feasible. In higher dimensional systems, such as humanoid robots, research has made substantial progress toward generalizing the ideas to model free or locally optimal settings, but these systems are complicated to the point where demonstration itself can be difficult. Typically, real-world applications are restricted to at best noisy or even partial or incomplete demonstrations that prove cumbersome in existing frameworks. This work derives a very flexible method of IOC based on a form of Structured Prediction known as Direct Loss Minimization. The resulting algorithm is essentially Policy Search on a reward function that rewards similarity to demonstrated behavior (using Covariance Matrix Adaptation (CMA) in our experiments). Our framework blurs the distinction between IOC, other forms of Imitation Learning, and Reinforcement Learning, enabling us to derive simple, versatile, and practical algorithms that blend imitation and reinforcement signals into a unified framework. Our experiments analyze various aspects of its performance and demonstrate its efficacy on conveying preferences for motion shaping and combined reach and grasp quality optimization.

PDF Video Project Page [BibTex]

PDF Video Project Page [BibTex]


Thumb md tracking
The Coordinate Particle Filter - A novel Particle Filter for High Dimensional Systems

Wüthrich, M., Bohg, J., Kappler, D., Pfreundt, C., Schaal, S.

In Proceedings of the IEEE International Conference on Robotics and Automation, May 2015 (inproceedings)

Abstract
Parametric filters, such as the Extended Kalman Filter and the Unscented Kalman Filter, typically scale well with the dimensionality of the problem, but they are known to fail if the posterior state distribution cannot be closely approximated by a density of the assumed parametric form. For nonparametric filters, such as the Particle Filter, the converse holds. Such methods are able to approximate any posterior, but the computational requirements scale exponentially with the number of dimensions of the state space. In this paper, we present the Coordinate Particle Filter which alleviates this problem. We propose to compute the particle weights recursively, dimension by dimension. This allows us to explore one dimension at a time, and resample after each dimension if necessary. Experimental results on simulated as well as real data con- firm that the proposed method has a substantial performance advantage over the Particle Filter in high-dimensional systems where not all dimensions are highly correlated. We demonstrate the benefits of the proposed method for the problem of multi-object and robotic manipulator tracking.

arXiv Video Bayesian Filtering Framework Bayesian Object Tracking DOI Project Page [BibTex]

2014


Learning objective functions for autonomous motion generation

Kalakrishnan, M.

University of Southern California, University of Southern California, Los Angeles, CA, 2014 (phdthesis)

Project Page Project Page [BibTex]

2014

Project Page Project Page [BibTex]


Data-driven autonomous manipulation

Pastor, P.

University of Southern California, University of Southern California, Los Angeles, CA, 2014 (phdthesis)

Project Page Project Page [BibTex]

Project Page Project Page [BibTex]


A Self-Tuning LQR Approach Demonstrated on an Inverted Pendulum

Trimpe, S., Millane, A., Doessegger, S., D’Andrea, R.

In Proceedings of the 19th IFAC World Congress, Cape Town, South Africa, 2014 (inproceedings)

PDF Supplementary material DOI Project Page [BibTex]

PDF Supplementary material DOI Project Page [BibTex]


Thumb md screen shot 2015 08 22 at 22.32.46
Dual Execution of Optimized Contact Interaction Trajectories

Toussaint, M., Ratliff, N., Bohg, J., Righetti, L., Englert, P., Schaal, S.

In Proceedings of the International Conference on Intelligent Robots and Systems, Chicago, IL, October 2014 (inproceedings)

Abstract
Efficient manipulation requires contact to reduce uncertainty. The manipulation literature refers to this as funneling: a methodology for increasing reliability and robustness by leveraging haptic feedback and control of environmental interaction. However, there is a fundamental gap between traditional approaches to trajectory optimization and this concept of robustness by funneling: traditional trajectory optimizers do not discover force feedback strategies. From a POMDP perspective, these behaviors could be regarded as explicit obser- vation actions planned to sufficiently reduce uncertainty thereby enabling a task. While we are sympathetic to the full POMDP view, solving full continuous-space POMDPs in high-dimensions is hard. In this paper, we propose an alternative approach in which trajectory optimization objectives are augmented with new terms that reward uncertainty reduction through contacts, explicitly promoting funneling. This augmentation shifts the responsibility of robustness toward the actual execution of the optimized trajectories. Directly tracing trajectories through configuration space would lose all robustnessâ??dual execution achieves robustness by devising force controllers to reproduce the temporal interaction profile encoded in the dual solution of the optimization problem. This work introduces dual execution in depth and analyze its performance through robustness experiments in both simulation and on a real-world robotic platform.

PDF Video DOI Project Page [BibTex]

PDF Video DOI Project Page [BibTex]


Thumb md screen shot 2015 08 23 at 13.52.44
Learning of Grasp Selection based on Shape-Templates

Herzog, A., Pastor, P., Kalakrishnan, M., Righetti, L., Bohg, J., Asfour, T., Schaal, S.

Autonomous Robots, 36(1-2):51-65, Springer US, January 2014 (article)

Abstract
The ability to grasp unknown objects still remains an unsolved problem in the robotics community. One of the challenges is to choose an appropriate grasp configu- ration, i.e., the 6D pose of the hand relative to the object and its finger configuration. In this paper, we introduce an algo- rithm that is based on the assumption that similarly shaped objects can be grasped in a similar way. It is able to synthe- size good grasp poses for unknown objects by finding the best matching object shape templates associated with previously demonstrated grasps. The grasp selection algorithm is able to improve over time by using the information of previous grasp attempts to adapt the ranking of the templates to new situa- tions. We tested our approach on two different platforms, the Willow Garage PR2 and the Barrett WAM robot, which have very different hand kinematics. Furthermore, we compared our algorithm with other grasp planners and demonstrated its superior performance. The results presented in this paper show that the algorithm is able to find good grasp configura- tions for a large set of unknown objects from a relatively small set of demonstrations, and does improve its performance over time.

video pdf DOI Project Page Project Page [BibTex]


An autonomous manipulation system based on force control and optimization

Righetti, L., Kalakrishnan, M., Pastor, P., Binney, J., Kelly, J., Voorhies, R. C., Sukhatme, G. S., Schaal, S.

Autonomous Robots, 36(1-2):11-30, Springer US, Febuary 2014, clmc (article)

Abstract
In this paper we present an architecture for autonomous manipulation. Our approach is based on the belief that contact interactions during manipulation should be exploited to improve dexterity and that optimizing motion plans is useful to create more robust and repeatable manipu- lation behaviors. We therefore propose an architecture where state of the art force/torque control and optimization-based motion planning are the core components of the system. We give a detailed description of the modules that constitute the complete system and discuss the challenges inherent to creat- ing such a system. We present experimental results for several grasping and manipulation tasks to demonstrate the perfor- mance and robustness of our approach.

Web Video link (url) DOI Project Page [BibTex]

Web Video link (url) DOI Project Page [BibTex]

2013


Thumb md impact battery
Probabilistic Object Tracking Using a Range Camera

Wüthrich, M., Pastor, P., Kalakrishnan, M., Bohg, J., Schaal, S.

In IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 3195-3202, IEEE, November 2013 (inproceedings)

Abstract
We address the problem of tracking the 6-DoF pose of an object while it is being manipulated by a human or a robot. We use a dynamic Bayesian network to perform inference and compute a posterior distribution over the current object pose. Depending on whether a robot or a human manipulates the object, we employ a process model with or without knowledge of control inputs. Observations are obtained from a range camera. As opposed to previous object tracking methods, we explicitly model self-occlusions and occlusions from the environment, e.g, the human or robotic hand. This leads to a strongly non-linear observation model and additional dependencies in the Bayesian network. We employ a Rao-Blackwellised particle filter to compute an estimate of the object pose at every time step. In a set of experiments, we demonstrate the ability of our method to accurately and robustly track the object pose in real-time while it is being manipulated by a human or a robot.

arXiv Video Code Video DOI Project Page [BibTex]

2013

arXiv Video Code Video DOI Project Page [BibTex]


Learning Objective Functions for Manipulation

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

In IEEE International Conference on Robotics and Automation, 2013, clmc (inproceedings)

Abstract
We present an approach to learning objective func- tions for robotic manipulation based on inverse reinforcement learning. Our path integral inverse reinforcement learning al- gorithm can deal with high-dimensional continuous state-action spaces, and only requires local optimality of demonstrated trajectories. We use L1 regularization in order to achieve feature selection, and propose an efficient algorithm to minimize the re- sulting convex objective function. We demonstrate our approach by applying it to two core problems in robotic manipulation. First, we learn a cost function for redundancy resolution in inverse kinematics. Second, we use our method to learn a cost function over trajectories, which is then used in optimization- based motion planning for grasping and manipulation tasks. Experimental results show that our method outperforms previous algorithms in high-dimensional settings.

PDF Project Page Project Page [BibTex]

PDF Project Page Project Page [BibTex]


Learning Task Error Models for Manipulation

Pastor, P., Kalakrishnan, M., Binney, J., Kelly, J., Righetti, L., Sukhatme, G., Schaal, S.

In IEEE International Conference on Robotics and Automation, 2013 (inproceedings)

Abstract
Precise kinematic forward models are important for robots to successfully perform dexterous grasping and manipula- tion tasks, especially when visual servoing is rendered infeasible due to occlusions. A lot of research has been conducted to estimate geometric and non-geometric parameters of kinematic chains to minimize reconstruction errors. However, kinematic chains can include non-linearities, e.g. due to cable stretch and motor-side encoders, that result in significantly different errors for different parts of the state space. Previous work either does not consider such non-linearities or proposes to estimate non-geometric parameters of carefully engineered models that are robot specific. We propose a data-driven approach that learns task error models that account for such unmodeled non-linearities. We argue that in the context of grasping and manipulation, it is sufficient to achieve high accuracy in the task relevant state space. We identify this relevant state space using previously executed joint configurations and learn error corrections for those. Therefore, our system is developed to generate subsequent executions that are similar to previous ones. The experiments show that our method successfully captures the non-linearities in the head kinematic chain (due to a counter- balancing spring) and the arm kinematic chains (due to cable stretch) of the considered experimental platform, see Fig. 1. The feasibility of the presented error learning approach has also been evaluated in independent DARPA ARM-S testing contributing to successfully complete 67 out of 72 grasping and manipulation tasks.

PDF video Project Page [BibTex]

PDF video Project Page [BibTex]

2012


From Dynamic Movement Primitives to Associative Skill Memories

Pastor, P., Kalakrishnan, M., Meier, F., Stulp, F., Buchli, J., Theodorou, E., Schaal, S.

Robotics and Autonomous Systems, 2012 (article)

Project Page [BibTex]

2012

Project Page [BibTex]


Towards Associative Skill Memories

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

In IEEE-RAS International Conference on Humanoid Robots, 2012, clmc (inproceedings)

Abstract
Movement primitives as basis of movement planning and control have become a popular topic in recent years. The key idea of movement primitives is that a rather small set of stereotypical movements should suffice to create a large set of complex manipulation skills. An interesting side effect of stereotypical movement is that it also creates stereotypical sensory events, e.g., in terms of kinesthetic variables, haptic variables, or, if processed appropriately, visual variables. Thus, a movement primitive executed towards a particular object in the environment will associate a large number of sensory variables that are typical for this manipulation skill. These association can be used to increase robustness towards perturbations, and they also allow failure detection and switching towards other behaviors. We call such movement primitives augmented with sensory associations {em Associative Skill Memories} (ASM). This paper addresses how ASMs can be acquired by imitation learning and how they can create robust manipulation skill by determining subsequent ASMs extit{online} to achieve a particular manipulation goal. Evaluation for grasping and manipulation with a Barrett WAM/Hand illustrate our approach.

PDF Project Page [BibTex]

PDF Project Page [BibTex]


Thumb md screen shot 2017 09 21 at 00.54.33
Entropy Search for Information-Efficient Global Optimization

Hennig, P., Schuler, C.

Journal of Machine Learning Research, 13, pages: 1809-1837, -, June 2012 (article)

Abstract
Contemporary global optimization algorithms are based on local measures of utility, rather than a probability measure over location and value of the optimum. They thus attempt to collect low function values, not to learn about the optimum. The reason for the absence of probabilistic global optimizers is that the corresponding inference problem is intractable in several ways. This paper develops desiderata for probabilistic optimization algorithms, then presents a concrete algorithm which addresses each of the computational intractabilities with a sequence of approximations and explicitly adresses the decision problem of maximizing information gain from each evaluation.

PDF Web Project Page Project Page Project Page [BibTex]

PDF Web Project Page Project Page Project Page [BibTex]

2011


Online movement adaptation based on previous sensor experiences

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

In IEEE International Conference on Intelligent Robots and Systems (IROS), pages: 365-371, 2011 (inproceedings)

Project Page Project Page Project Page [BibTex]

2011

Project Page Project Page Project Page [BibTex]


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.

link (url) Project Page Project Page [BibTex]

link (url) Project Page Project Page [BibTex]


Learning force control policies for compliant manipulation

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

In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), Sept. 25-30, San Francisco, CA, 2011, clmc (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. Manip-ulation tasks imply complex contact interactions with the external world, and in-volve reasoning about the forces and torques to be applied. Planning under con-tact 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 learn-ing. 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 pro-files 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.

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


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 (IROS 2011), Sept. 25-30, San Francisco, CA, 2011, clmc (inproceedings)

Abstract
Applying model-free reinforcement learning to manipulation remains challeng-ing 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 ef-ficient version of our model-free reinforcement learning algorithm PI2; 2) extend PI2 so that it simultaneously learns shape parameters and goal parameters of mo-tion primitives; 3) use shape and goal learning to acquire motion primitives that are robust to object pose uncertainty. We evaluate these contributions on a ma-nipulation platform consisting of a 7-DOF arm with a 4-DOF hand.

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


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.

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]

2010


Learning, planning, and control for quadruped locomotion over challenging terrain

Kalakrishnan, M., Buchli, J., Pastor, P., Mistry, M., Schaal, S.

International Journal of Robotics Research, 30(2):236-258, 2010, clmc (article)

Abstract
We present a control architecture for fast quadruped locomotion over rough terrain. We approach the problem by decomposing it into many sub-systems, in which we apply state-of-the-art learning, planning, optimization, and control techniques to achieve robust, fast locomotion. Unique features of our control strategy include: (1) a system that learns optimal foothold choices from expert demonstration using terrain templates, (2) a body trajectory optimizer based on the Zero- Moment Point (ZMP) stability criterion, and (3) a floating-base inverse dynamics controller that, in conjunction with force control, allows for robust, compliant locomotion over unperceived obstacles. We evaluate the performance of our controller by testing it on the LittleDog quadruped robot, over a wide variety of rough terrains of varying difficulty levels. The terrain that the robot was tested on includes rocks, logs, steps, barriers, and gaps, with obstacle sizes up to the leg length of the robot. We demonstrate the generalization ability of this controller by presenting results from testing performed by an independent external test team on terrain that has never been shown to us.

link (url) Project Page [BibTex]

2010

link (url) Project Page [BibTex]

2009


Learning locomotion over rough terrain using terrain templates

Kalakrishnan, M., Buchli, J., Pastor, P., Schaal, S.

In Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on, pages: 167-172, 2009, clmc (inproceedings)

Abstract
We address the problem of foothold selection in robotic legged locomotion over very rough terrain. The difficulty of the problem we address here is comparable to that of human rock-climbing, where foot/hand-hold selection is one of the most critical aspects. Previous work in this domain typically involves defining a reward function over footholds as a weighted linear combination of terrain features. However, a significant amount of effort needs to be spent in designing these features in order to model more complex decision functions, and hand-tuning their weights is not a trivial task. We propose the use of terrain templates, which are discretized height maps of the terrain under a foothold on different length scales, as an alternative to manually designed features. We describe an algorithm that can simultaneously learn a small set of templates and a foothold ranking function using these templates, from expert-demonstrated footholds. Using the LittleDog quadruped robot, we experimentally show that the use of terrain templates can produce complex ranking functions with higher performance than standard terrain features, and improved generalization to unseen terrain.

link (url) Project Page [BibTex]

2009

link (url) Project Page [BibTex]