Header logo is


2018


Deep Reinforcement Learning for Event-Triggered Control
Deep Reinforcement Learning for Event-Triggered Control

Baumann, D., Zhu, J., Martius, G., Trimpe, S.

In Proceedings of the 57th IEEE International Conference on Decision and Control (CDC), pages: 943-950, 57th IEEE International Conference on Decision and Control (CDC), December 2018 (inproceedings)

al ics

arXiv PDF DOI Project Page Project Page [BibTex]

2018


arXiv PDF DOI Project Page Project Page [BibTex]


Oncilla robot: a versatile open-source quadruped research robot with compliant pantograph legs
Oncilla robot: a versatile open-source quadruped research robot with compliant pantograph legs

Sproewitz, A., Tuleu, A., Ajallooeian, M., Vespignani, M., Moeckel, R., Eckert, P., D’Haene, M., Degrave, J., Nordmann, A., Schrauwen, B., Steil, J., Ijspeert, A. J.

Frontiers in Robotics and AI, 5(67), June 2018, arXiv: 1803.06259 (article)

Abstract
We present Oncilla robot, a novel mobile, quadruped legged locomotion machine. This large-cat sized, 5.1 robot is one of a kind of a recent, bioinspired legged robot class designed with the capability of model-free locomotion control. Animal legged locomotion in rough terrain is clearly shaped by sensor feedback systems. Results with Oncilla robot show that agile and versatile locomotion is possible without sensory signals to some extend, and tracking becomes robust when feedback control is added (Ajaoolleian 2015). By incorporating mechanical and control blueprints inspired from animals, and by observing the resulting robot locomotion characteristics, we aim to understand the contribution of individual components. Legged robots have a wide mechanical and control design parameter space, and a unique potential as research tools to investigate principles of biomechanics and legged locomotion control. But the hardware and controller design can be a steep initial hurdle for academic research. To facilitate the easy start and development of legged robots, Oncilla-robot's blueprints are available through open-source. [...]

dlg

link (url) DOI Project Page [BibTex]

link (url) DOI Project Page [BibTex]


Learning from Outside the Viability Kernel: Why we Should Build Robots that can Fail with Grace
Learning from Outside the Viability Kernel: Why we Should Build Robots that can Fail with Grace

Heim, S., Sproewitz, A.

Proceedings of SIMPAR 2018, pages: 55-61, IEEE, 2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR), May 2018 (conference)

dlg

link (url) DOI Project Page [BibTex]

link (url) DOI Project Page [BibTex]


Impact of Trunk Orientation  for Dynamic Bipedal Locomotion
Impact of Trunk Orientation for Dynamic Bipedal Locomotion

Drama, O.

Dynamic Walking Conference, May 2018 (talk)

Abstract
Impact of trunk orientation for dynamic bipedal locomotion My research revolves around investigating the functional demands of bipedal running, with focus on stabilizing trunk orientation. When we think about postural stability, there are two critical questions we need to answer: What are the necessary and sufficient conditions to achieve and maintain trunk stability? I am concentrating on how morphology affects control strategies in achieving trunk stability. In particular, I denote the trunk pitch as the predominant morphology parameter and explore the requirements it imposes on a chosen control strategy. To analyze this, I use a spring loaded inverted pendulum model extended with a rigid trunk, which is actuated by a hip motor. The challenge for the controller design here is to have a single hip actuator to achieve two coupled tasks of moving the legs to generate motion and stabilizing the trunk. I enforce orthograde and pronograde postures and aim to identify the effect of these trunk orientations on the hip torque and ground reaction profiles for different control strategies.

dlg

Impact of trunk orientation for dynamic bipedal locomotion [DW 2018] link (url) Project Page [BibTex]


Shaping in Practice: Training Wheels to Learn Fast Hopping Directly in Hardware
Shaping in Practice: Training Wheels to Learn Fast Hopping Directly in Hardware

Heim, S., Ruppert, F., Sarvestani, A., Sproewitz, A.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2018, pages: 5076-5081, IEEE, International Conference on Robotics and Automation, May 2018 (inproceedings)

Abstract
Learning instead of designing robot controllers can greatly reduce engineering effort required, while also emphasizing robustness. Despite considerable progress in simulation, applying learning directly in hardware is still challenging, in part due to the necessity to explore potentially unstable parameters. We explore the of concept shaping the reward landscape with training wheels; temporary modifications of the physical hardware that facilitate learning. We demonstrate the concept with a robot leg mounted on a boom learning to hop fast. This proof of concept embodies typical challenges such as instability and contact, while being simple enough to empirically map out and visualize the reward landscape. Based on our results we propose three criteria for designing effective training wheels for learning in robotics.

dlg

Video Youtube link (url) Project Page [BibTex]

Video Youtube link (url) Project Page [BibTex]


no image
Nonlinear decoding of a complex movie from the mammalian retina

Botella-Soler, V., Deny, S., Martius, G., Marre, O., Tkačik, G.

PLOS Computational Biology, 14(5):1-27, Public Library of Science, May 2018 (article)

Abstract
Author summary Neurons in the retina transform patterns of incoming light into sequences of neural spikes. We recorded from ∼100 neurons in the rat retina while it was stimulated with a complex movie. Using machine learning regression methods, we fit decoders to reconstruct the movie shown from the retinal output. We demonstrated that retinal code can only be read out with a low error if decoders make use of correlations between successive spikes emitted by individual neurons. These correlations can be used to ignore spontaneous spiking that would, otherwise, cause even the best linear decoders to “hallucinate” nonexistent stimuli. This work represents the first high resolution single-trial full movie reconstruction and suggests a new paradigm for separating spontaneous from stimulus-driven neural activity.

al

DOI [BibTex]

DOI [BibTex]


no image
L4: Practical loss-based stepsize adaptation for deep learning

Rolinek, M., Martius, G.

In Advances in Neural Information Processing Systems 31 (NeurIPS 2018), pages: 6434-6444, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 2018 (inproceedings)

al

Github link (url) Project Page [BibTex]

Github link (url) Project Page [BibTex]


Systematic self-exploration of behaviors for robots in a dynamical systems framework
Systematic self-exploration of behaviors for robots in a dynamical systems framework

Pinneri, C., Martius, G.

In Proc. Artificial Life XI, pages: 319-326, MIT Press, Cambridge, MA, 2018 (inproceedings)

Abstract
One of the challenges of this century is to understand the neural mechanisms behind cognitive control and learning. Recent investigations propose biologically plausible synaptic mechanisms for self-organizing controllers, in the spirit of Hebbian learning. In particular, differential extrinsic plasticity (DEP) [Der and Martius, PNAS 2015], has proven to enable embodied agents to self-organize their individual sensorimotor development, and generate highly coordinated behaviors during their interaction with the environment. These behaviors are attractors of a dynamical system. In this paper, we use the DEP rule to generate attractors and we combine it with a “repelling potential” which allows the system to actively explore all its attractor behaviors in a systematic way. With a view to a self-determined exploration of goal-free behaviors, our framework enables switching between different motion patterns in an autonomous and sequential fashion. Our algorithm is able to recover all the attractor behaviors in a toy system and it is also effective in two simulated environments. A spherical robot discovers all its major rolling modes and a hexapod robot learns to locomote in 50 different ways in 30min.

al

link (url) DOI Project Page [BibTex]

link (url) DOI Project Page [BibTex]


Learning equations for extrapolation and control
Learning equations for extrapolation and control

Sahoo, S. S., Lampert, C. H., Martius, G.

In Proc. 35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden, 2018, 80, pages: 4442-4450, http://proceedings.mlr.press/v80/sahoo18a/sahoo18a.pdf, (Editors: Dy, Jennifer and Krause, Andreas), PMLR, 2018 (inproceedings)

Abstract
We present an approach to identify concise equations from data using a shallow neural network approach. In contrast to ordinary black-box regression, this approach allows understanding functional relations and generalizing them from observed data to unseen parts of the parameter space. We show how to extend the class of learnable equations for a recently proposed equation learning network to include divisions, and we improve the learning and model selection strategy to be useful for challenging real-world data. For systems governed by analytical expressions, our method can in many cases identify the true underlying equation and extrapolate to unseen domains. We demonstrate its effectiveness by experiments on a cart-pendulum system, where only 2 random rollouts are required to learn the forward dynamics and successfully achieve the swing-up task.

al

Code Arxiv Poster Slides link (url) Project Page [BibTex]

Code Arxiv Poster Slides link (url) Project Page [BibTex]


Robust Affordable 3D Haptic Sensation via Learning Deformation Patterns
Robust Affordable 3D Haptic Sensation via Learning Deformation Patterns

Sun, H., Martius, G.

Proceedings International Conference on Humanoid Robots, pages: 846-853, IEEE, New York, NY, USA, 2018 IEEE-RAS International Conference on Humanoid Robots, 2018, Oral Presentation (conference)

Abstract
Haptic sensation is an important modality for interacting with the real world. This paper proposes a general framework of inferring haptic forces on the surface of a 3D structure from internal deformations using a small number of physical sensors instead of employing dense sensor arrays. Using machine learning techniques, we optimize the sensor number and their placement and are able to obtain high-precision force inference for a robotic limb using as few as 9 sensors. For the optimal and sparse placement of the measurement units (strain gauges), we employ data-driven methods based on data obtained by finite element simulation. We compare data-driven approaches with model-based methods relying on geometric distance and information criteria such as Entropy and Mutual Information. We validate our approach on a modified limb of the “Poppy” robot [1] and obtain 8 mm localization precision.

al

DOI Project Page [BibTex]

DOI Project Page [BibTex]

2014


Roombots: A hardware perspective on 3D self-reconfiguration and locomotion with a homogeneous modular robot
Roombots: A hardware perspective on 3D self-reconfiguration and locomotion with a homogeneous modular robot

Spröwitz, A., Moeckel, R., Vespignani, M., Bonardi, S., Ijspeert, A. J.

{Robotics and Autonomous Systems}, 62(7):1016-1033, Elsevier, Amsterdam, 2014 (article)

Abstract
In this work we provide hands-on experience on designing and testing a self-reconfiguring modular robotic system, Roombots (RB), to be used among others for adaptive furniture. In the long term, we envision that RB can be used to create sets of furniture, such as stools, chairs and tables that can move in their environment and that change shape and functionality during the day. In this article, we present the first, incremental results towards that long term vision. We demonstrate locomotion and reconfiguration of single and metamodule RB over 3D surfaces, in a structured environment equipped with embedded connection ports. RB assemblies can move around in non-structured environments, by using rotational or wheel-like locomotion. We show a proof of concept for transferring a Roombots metamodule (two in-series coupled RB modules) from the non-structured environment back into the structured grid, by aligning the RB metamodule in an entrapment mechanism. Finally, we analyze the remaining challenges to master the full Roombots scenario, and discuss the impact on future Roombots hardware.

dlg

DOI [BibTex]

2014


DOI [BibTex]


Automatic Generation of Reduced CPG Control Networks for Locomotion of Arbitrary Modular Robot Structures
Automatic Generation of Reduced CPG Control Networks for Locomotion of Arbitrary Modular Robot Structures

Bonardi, S., Vespignani, M., Möckel, R., Van den Kieboom, J., Pouya, S., Spröwitz, A., Ijspeert, A.

In Proceedings of Robotics: Science and Systems, University of California, Barkeley, 2014 (inproceedings)

Abstract
The design of efficient locomotion controllers for arbitrary structures of reconfigurable modular robots is challenging because the morphology of the structure can change dynamically during the completion of a task. In this paper, we propose a new method to automatically generate reduced Central Pattern Generator (CPG) networks for locomotion control based on the detection of bio-inspired sub-structures, like body and limbs, and articulation joints inside the robotic structure. We demonstrate how that information, coupled with the potential symmetries in the structure, can be used to speed up the optimization of the gaits and investigate its impact on the solution quality (i.e. the velocity of the robotic structure and the potential internal collisions between robotic modules). We tested our approach on three simulated structures and observed that the reduced network topologies in the first iterations of the optimization process performed significantly better than the fully open ones.

dlg

DOI [BibTex]

DOI [BibTex]


Kinematic primitives for walking and trotting gaits of a quadruped robot with compliant legs
Kinematic primitives for walking and trotting gaits of a quadruped robot with compliant legs

Spröwitz, A. T., Ajallooeian, M., Tuleu, A., Ijspeert, A. J.

Frontiers in Computational Neuroscience, 8(27):1-13, 2014 (article)

Abstract
In this work we research the role of body dynamics in the complexity of kinematic patterns in a quadruped robot with compliant legs. Two gait patterns, lateral sequence walk and trot, along with leg length control patterns of different complexity were implemented in a modular, feed-forward locomotion controller. The controller was tested on a small, quadruped robot with compliant, segmented leg design, and led to self-stable and self-stabilizing robot locomotion. In-air stepping and on-ground locomotion leg kinematics were recorded, and the number and shapes of motion primitives accounting for 95\% of the variance of kinematic leg data were extracted. This revealed that kinematic patterns resulting from feed-forward control had a lower complexity (in-air stepping, 2–3 primitives) than kinematic patterns from on-ground locomotion (νm4 primitives), although both experiments applied identical motor patterns. The complexity of on-ground kinematic patterns had increased, through ground contact and mechanical entrainment. The complexity of observed kinematic on-ground data matches those reported from level-ground locomotion data of legged animals. Results indicate that a very low complexity of modular, rhythmic, feed-forward motor control is sufficient for level-ground locomotion in combination with passive compliant legged hardware.

dlg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Self-Exploration of the Stumpy Robot with Predictive Information Maximization

Martius, G., Jahn, L., Hauser, H., V. Hafner, V.

In Proc. From Animals to Animats, SAB 2014, 8575, pages: 32-42, LNCS, Springer, 2014 (inproceedings)

al

[BibTex]

[BibTex]


no image
Robot Learning by Guided Self-Organization

Martius, G., Der, R., Herrmann, J. M.

In Guided Self-Organization: Inception, 9, pages: 223-260, Emergence, Complexity and Computation, Springer Berlin Heidelberg, 2014 (incollection)

al

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2009


Roombots-mechanical design of self-reconfiguring modular robots for adaptive furniture
Roombots-mechanical design of self-reconfiguring modular robots for adaptive furniture

Spröwitz, A., Billard, A., Dillenbourg, P., Ijspeert, A. J.

In Proceedings of the 2009 IEEE International Conference on Robotics and Automation (ICRA), pages: 4259-4264, IEEE, Kobe, 2009 (inproceedings)

Abstract
We aim at merging technologies from information technology, roomware, and robotics in order to design adaptive and intelligent furniture. This paper presents design principles for our modular robots, called Roombots, as future building blocks for furniture that moves and self-reconfigures. The reconfiguration is done using dynamic connection and disconnection of modules and rotations of the degrees of freedom. We are furthermore interested in applying Roombots towards adaptive behaviour, such as online learning of locomotion patterns. To create coordinated and efficient gait patterns, we use a Central Pattern Generator (CPG) approach, which can easily be optimized by any gradient-free optimization algorithm. To provide a hardware framework we present the mechanical design of the Roombots modules and an active connection mechanism based on physical latches. Further we discuss the application of our Roombots modules as pieces of a homogenic or heterogenic mix of building blocks for static structures.

dlg

DOI [BibTex]

2009


DOI [BibTex]


no image
A Sensor-Based Learning Algorithm for the Self-Organization of Robot Behavior

Hesse, F., Martius, G., Der, R., Herrmann, J. M.

Algorithms, 2(1):398-409, 2009 (article)

Abstract
Ideally, sensory information forms the only source of information to a robot. We consider an algorithm for the self-organization of a controller. At short timescales the controller is merely reactive but the parameter dynamics and the acquisition of knowledge by an internal model lead to seemingly purposeful behavior on longer timescales. As a paradigmatic example, we study the simulation of an underactuated snake-like robot. By interacting with the real physical system formed by the robotic hardware and the environment, the controller achieves a sensitive and body-specific actuation of the robot.

al

link (url) [BibTex]

link (url) [BibTex]

2007


An easy to use bluetooth scatternet protocol for fast data exchange in wireless sensor networks and autonomous robots
An easy to use bluetooth scatternet protocol for fast data exchange in wireless sensor networks and autonomous robots

Mockel, R., Spröwitz, A., Maye, J., Ijspeert, A. J.

In Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 2801-2806, IEEE, San Diego, CA, 2007 (inproceedings)

Abstract
We present a Bluetooth scatternet protocol (SNP) that provides the user with a serial link to all connected members in a transparent wireless Bluetooth network. By using only local decision making we can reduce the overhead of our scatternet protocol dramatically. We show how our SNP software layer simplifies a variety of tasks like the synchronization of central pattern generator controllers for actuators, collecting sensory data and building modular robot structures. The whole Bluetooth software stack including our new scatternet layer is implemented on a single Bluetooth and memory chip. To verify and characterize the SNP we provide data from experiments using real hardware instead of software simulation. This gives a realistic overview of the scatternet performance showing higher order effects that are difficult to be simulated correctly and guaranties the correct function of the SNP in real world applications.

dlg

DOI [BibTex]

2007


DOI [BibTex]


no image
Guided Self-organisation for Autonomous Robot Development

Martius, G., Herrmann, J. M., Der, R.

In Advances in Artificial Life 9th European Conference, ECAL 2007, 4648, pages: 766-775, LNCS, Springer, 2007 (inproceedings)

al

[BibTex]

[BibTex]