Publications
Results
- Showing results for:
- Reset all filters
Search results
-
Conference paperAhmadzadeh SR, Kormushev P, Caldwell DG, 2013,
Visuospatial Skill Learning for Object Reconfiguration Tasks
-
Conference paperAhmadzadeh SR, Kormushev P, Caldwell DG, 2013,
Interactive Robot Learning of Visuospatial Skills
-
Conference paperKormushev P, Caldwell DG, 2013,
Improving the Energy Efficiency of Autonomous Underwater Vehicles by Learning to Model Disturbances
-
Conference paperKarras GC, Bechlioulis CP, Leonetti M, et al., 2013,
On-Line Identification of Autonomous Underwater Vehicles through Global Derivative-Free Optimization
-
Journal articleKoos S, Cully A, Mouret J-B, 2013,
Fast damage recovery in robotics with the T-resilience algorithm
, The International Journal of Robotics Research, Vol: 32, Pages: 1700-1723, ISSN: 0278-3649Damage recovery is critical for autonomous robots that need to operate for a long time without assistance. Most current methods are complex and costly because they require anticipating potential damage in order to have a contingency plan ready. As an alternative, we introduce the T-resilience algorithm, a new algorithm that allows robots to quickly and autonomously discover compensatory behavior in unanticipated situations. This algorithm equips the robot with a self-model and discovers new behavior by learning to avoid those that perform differently in the self-model and in reality. Our algorithm thus does not identify the damaged parts but it implicitly searches for efficient behavior that does not use them. We evaluate the T-resilience algorithm on a hexapod robot that needs to adapt to leg removal, broken legs and motor failures; we compare it to stochastic local search, policy gradient and the self-modeling algorithm proposed by Bongard et al. The behavior of the robot is assessed on-board thanks to an RGB-D sensor and a SLAM algorithm. Using only 25 tests on the robot and an overall running time of 20 min, T-resilience consistently leads to substantially better results than the other approaches.
-
Conference paperKormushev P, Caldwell DG, 2013,
Towards Improved AUV Control Through Learning of Periodic Signals
-
Conference paperAhmadzadeh SR, Leonetti M, Kormushev P, 2013,
Online Direct Policy Search for Thruster Failure Recovery in Autonomous Underwater Vehicles
-
Conference paperJamali N, Kormushev P, Caldwell DG, 2013,
Contact State Estimation using Machine Learning
-
Conference paperKormushev P, Caldwell DG, 2013,
Comparative Evaluation of Reinforcement Learning with Scalar Rewards and Linear Regression with Multidimensional Feedback
-
Conference paperLeonetti M, Ahmadzadeh SR, Kormushev P, 2013,
On-line Learning to Recover from Thruster Failures on Autonomous Underwater Vehicles
-
BookDeisenroth MP, Neumann G, Peters J, 2013,
A Survey on Policy Search for Robotics
, Publisher: now PublishersPolicy search is a subfield in reinforcement learning which focuses onfinding good parameters for a given policy parametrization. It is wellsuited for robotics as it can cope with high-dimensional state and actionspaces, one of the main challenges in robot learning. We review recentsuccesses of both model-free and model-based policy search in robotlearning.Model-free policy search is a general approach to learn policiesbased on sampled trajectories. We classify model-free methods based ontheir policy evaluation strategy, policy update strategy, and explorationstrategy and present a unified view on existing algorithms. Learning apolicy is often easier than learning an accurate forward model, and,hence, model-free methods are more frequently used in practice. How-ever, for each sampled trajectory, it is necessary to interact with the robot, which can be time consuming and challenging in practice. Model-based policy search addresses this problem by first learning a simulatorof the robot’s dynamics from data. Subsequently, the simulator gen-erates trajectories that are used for policy learning. For both model-free and model-based policy search methods, we review their respectiveproperties and their applicability to robotic systems.
-
Conference paperKormushev P, Caldwell DG, 2013,
Reinforcement Learning with Heterogeneous Policy Representations
-
Conference paperCully AHR, Mouret J-B, 2013,
Behavioral repertoire learning in robotics
, Proceedings of the 15th annual conference on Genetic and evolutionary computation, Publisher: ACM, Pages: 175-182Behavioral Repertoire Learning in RoboticsAntoine CullyISIR, Université Pierre et Marie Curie-Paris 6,CNRS UMR 72224 place Jussieu, F-75252, Paris Cedex 05,Francecully@isir.upmc.frJean-Baptiste MouretISIR, Université Pierre et Marie Curie-Paris 6,CNRS UMR 72224 place Jussieu, F-75252, Paris Cedex 05,Francemouret@isir.upmc.frABSTRACTLearning in robotics typically involves choosing a simple goal(e.g. walking) and assessing the performance of each con-troller with regard to this task (e.g. walking speed). How-ever, learning advanced, input-driven controllers (e.g. walk-ing in each direction) requires testing each controller on alarge sample of the possible input signals. This costly pro-cess makes difficult to learn useful low-level controllers inrobotics.Here we introduce BR-Evolution, a new evolutionary learn-ing technique that generates a behavioral repertoire by tak-ing advantage of the candidate solutions that are usuallydiscarded. Instead of evolving a single, general controller,BR-evolution thus evolves a collection of simple controllers,one for each variant of the target behavior; to distinguishsimilar controllers, it uses a performance objective that al-lows it to produce a collection of diverse but high-performingbehaviors. We evaluated this new technique by evolving gaitcontrollers for a simulated hexapod robot. Results show thata single run of the EA quickly finds a collection of controllersthat allows the robot to reach each point of the reachablespace. Overall, BR-Evolution opens a new kind of learningalgorithm that simultaneously optimizes all the achievablebehaviors of a robot.
-
Conference paperKryczka P, Hashimoto K, Takanishi A, et al., 2013,
Walking Despite the Passive Compliance: Techniques for Using Conventional Pattern Generators to Control Instrinsically Compliant Humanoid Robots
-
Conference paperCarrera A, Carreras M, Kormushev P, et al., 2013,
Towards valve turning with an AUV using Learning by Demonstration
-
Conference paperSykes D, Corapi D, Magee J, et al., 2013,
Learning Revised Models For Planning In Adaptive Systems
, 35th IEEE/ACM International Conference on Software Engineering, Publisher: IEEE/ACM, Pages: 63-71 -
Conference paperMaimari N, Krams R, Turliuc C-R, et al., 2013,
ARNI: Abductive inference of complex regulatory network structures
, 11th International Conference, CMSB 2013, Pages: 235-237, ISSN: 0302-9743Physical network inference methods use a template of molecular interaction to infer biological networks from high throughput datasets. Current inference methods have limited applicability, relying on cause-effect pairs or systematically perturbed datasets and fail to capture complex network structures. Here we present a novel framework, ARNI, based on abductive inference, that addresses these limitations. © Springer-Verlag 2013.
-
Conference paperKryczka P, Kormushev P, Hashimoto K, et al., 2013,
Hybrid gait pattern generator capable of rapid and dynamically consistent pattern regeneration
, Publisher: IEEE, Pages: 475-480 -
Journal articleKormushev P, Calinon S, Caldwell DG, 2013,
Reinforcement Learning in Robotics: Applications and Real-World Challenges
, Robotics, Vol: 2, Pages: 122-148, ISSN: 2218-6581 -
Conference paperDallali H, Mosadeghzad M, Medrano-Cerda GA, et al., 2013,
Development of a dynamic simulator for a compliant humanoid robot based on a symbolic multibody approach
, Pages: 598-603
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.