Malte Schilling

Walknet, a bio-inspired controller for hexapod walking

Walknet comprises an artificial neural network that allows for the simulation of a considerable amount of behavioral data obtained from walking and standing stick insects. It has been tested by kinematic and dynamic simulations as well as on a number of six-legged robots. Over the years, various different expansions of this network have been provided leading to different versions of Walknet. This review summarizes the most important biological findings described by Walknet and how they can be simulated. Walknet shows how a number of properties observed in insects may emerge from a decentralized architecture. Examples are the continuum of so-called “gaits,” coordination of up to 18 leg joints during stance when walking forward or backward over uneven surfaces and negotiation of curves, dealing with leg loss, as well as being able following motion trajectories without explicit precalculation. The different Walknet versions are compared to other approaches describing insect-inspired hexapod walking. Finally, we briefly address the ability of this decentralized reactive controller to form the basis for the simulation of higher-level cognitive faculties exceeding the capabilities of insects.

Hexapod Walking: an expansion to Walknet dealing with leg amputations and force oscillations

The control of the legs of a walking hexapod is a complex problem as the legs have three joints each, resulting in a total of 18 degrees of freedom. We addressed this problem using a decentralized architecture termed Walknet, which consists of peripheral pattern generators being coordinated through influences acting mainly between neighbouring legs. Both, the coordinating influences and the local control modules (each acting only on one leg), are biologically inspired. This investigation shows that it is possible to adapt this approach to account for additional biological data by (1) changing the structure of the selector net in a biological plausible way (including force as an analog variable), (2) introducing a biologically motivated coordination influence for coactivation between legs and (3) adding a hypothetical influence between hind and front legs. This network of controllers has been tested using a dynamic simulation. It is able to describe (a) the behaviour of animals walking with one or two legs being amputated and (b) force oscillations that occur in a specific experimental situation, the standing legs of a walking animal.

A hexapod walker using a heterarchical architecture for action selection

Moving in a cluttered environment with a six-legged walking machine that has additional body actuators, therefore controlling 22 DoFs, is not a trivial task. Already simple forward walking on a flat plane requires the system to select between different internal states. The orchestration of these states depends on walking velocity and on external disturbances. Such disturbances occur continuously, for example due to irregular up-and-down movements of the body or slipping of the legs, even on flat surfaces, in particular when negotiating tight curves. The number of possible states is further increased when the system is allowed to walk backward or when front legs are used as grippers and cannot contribute to walking. Further states are necessary for expansion that allow for navigation. Here we demonstrate a solution for the selection and sequencing of different (attractor) states required to control different behaviors as are forward walking at different speeds, backward walking, as well as negotiation of tight curves. This selection is made by a recurrent neural network (RNN) of motivation units, controlling a bank of decentralized memory elements in combination with the feedback through the environment. The underlying heterarchical architecture of the network allows to select various combinations of these elements. This modular approach representing an example of neural reuse of a limited number of procedures allows for adaptation to different internal and external conditions. A way is sketched as to how this approach may be expanded to form a cognitive system being able to plan ahead. This architecture is characterized by different types of modules being arranged in layers and columns, but the complete network can also be considered as a holistic system showing emergent properties which cannot be attributed to a specific module.

Universally manipulable body models--dual quaternion representations in layered and dynamic MMCs

Surprisingly complex tasks can be solved using a behaviour-based, reactive control system, i.e., a system that operates without an explicit internal representation of the environment and the own body. Nevertheless, application of internal representations has gained interest in recent years because such internal representations can be used to solve problems of perception and motor control (sensor fusion, inverse modeling) and may in addition be applied to higher cognitive functions as are the ability to plan ahead. To endow such a system with the ability to find new behavioural solutions to a given problem in a broad range of possibilities, the internal representation must be universally manipulable, i.e. the model should be able to simulate all movements that are physically possible for the body given. Using recurrent neural networks, models showing this faculty have been proposed being based on the principle of mean of multiple computation (MMC). The extension of this approach to three dimensions requires the introduction of a joint angle representation which allows for computation of mean values. Here we use dual quaternions that are singularity-free and unambiguous which allow for shortest path interpolation. In addition, it has been shown that dual quaternions are the most efficient and most compact form for representing rigid transformations. The model can easily be adapted to bodies of arbitrary geometries. The extended MMC net introduced in this article represents a holistic system that can—following the principle of pattern completion—likewise be used as an inverse model, a forward model, for sensor fusion or other, related capabilities.

Principles of Insect Locomotion

Walking animals can deal with large range of difficult terrain and can use their legs for other purposes as sensing or object manipulation. This is possible although the underlying control system is based on neurons which are considered to be quite sloppy and slow computational elements. Important aspects of this control system are error tolerance and the capability of self-organization. This chapter concentrates on insect walking behaviour. Apart from some references to relevant morphology it addresses behavioural investigations which are paralleled by software simulations to allow a better understanding of the underlying principles. Furthermore, hints to neurophysiology and to hardware simulations are given. Characteristic properties of the control system are its decentralized architecture that relies heavily on internal feedback as well as on sensory feedback, and that exploits the physics of the body.

Grounding an internal body model of a hexapod walker control of curve walking in a biologically inspired robot

While internal models are a prerequisite for higher-level function, they have to be grounded in lower-level function serving sensorimotor control. In this paper we introduce an internal body model for the control of a hexapod walker. The internal model deals with a highly complex robotic structure of 22 degrees of freedom and coordinates the single joint movements to achieve an overall stable and adaptive walking behavior. It is implemented as a hierarchical recurrent neural network consisting of different levels of abstraction which are tightly intertwined. We demonstrate the feasibility of the concept by applying the model to a simulated robot and show how the different levels of the body model interact and how this allows to scale the model even further. While the internal model is used in this context explicitly for motor control, it is also a predictive model and can be applied for sensor fusion. We discuss how in this way such an internal model offers the flexibility to be utilized in motor control and to be used for planning ahead by a cognitive expansion of the movement controller.

No need for a body model: Positive velocity feedback for the control of an 18-DOF robot walker

In a multilegged walking robot several legs usually have ground contact and thereby form a closed kinematic chain. The control of such a system is generally assumed to require the explicit calculation of the body kinematics. Such a computation requires knowledge concerning all relevant joint angles as well as the segment lengths. Here, we propose a biologically inspired solution that does not need such a body model. This is done by using implicit communication through the body mechanics embodiment and a local positive velocity feedback strategy LPVF on the single joint level. In this control scheme the locally measured joint velocity of an elastic joint is fed into the same joint during the next time step to maintain the movement. At the same time, an additional part of this joint controller observes the mechanical joint power to confine the positive feedback. This solution does not depend on changes of the geometry, e.g. length of individual segments, and allows for a simple solution of negotiation of curves. The principle is tested in a dynamics simulation on a six-legged walker and, for the first time, also on a real robot.

The evolution of cognition: from first order to second order embodiment

The capability to behave autonomously is assumed to rely fundamentally on being embedded into the current situation and in the own body. While reactive systems seem sufficient to address these aspects to assure ones surviving in an unpredictable environment, they clearly lack cognitive capabilities as planning ahead: The latter requires internal models which represents the body and the environment and which can be used to mentally simulate behaviours before actually performing one of them. Initially, these models may have evolved in reactive systems to serve specific actions. Cognitive functions may have developed later exploiting the capabilities of these models. We provide a neuronal network approach for such an internal model that can be used as a forward model, an inverse model and a sensor fusion model. It is integrated into a reactive control scheme of a walking machine, enabling the system to plan its actions by mentally simulating them.

Hierarchical MMC Networks as a manipulable body model

A cognitive control system for a walking robot should be able to solve from simple reactive tasks up to complex tasks, including tasks which need cognitive capabilities and setting up plans. Planning ahead involves some kind of internal representation: most important a model of the own body. Considering planning as mental simulation, this model must be fully functional: it is constrained in the same way as the body itself and it can move and be used in the same way as the body. This model can then be used to try out movements mentally without doing the action in reality. For this purpose it must be possible to decouple the body itself from the action controlling modules to use the original controllers for control of the internal representations. In this publication we introduce a hierarchical model, implemented as an recurrent neural network based on the MMC principle.

Automatic data exchange and synchronization for knowledge-based intelligent virtual environments

Advanced VR simulation systems are composed of several components with independent and heterogeneously structured databases. To guarantee a closed and consistent world simulation, flexible and robust data exchange between these components has to be realized. This multiple database problem is well known in many distributed application domains, but it is central for VR setups composed of diverse simulation components. Particularly complicated is the exchange between object-centered and graph-based representation formats, where entity attributes may be distributed over the graph structure. This article presents an abstract declarative attribute representation concept, which handles different representation formats uniformly and enables automatic data exchange and synchronization between them. This mechanism is tailored to support the integration of a central knowledge component, which provides a uniform representation of the accumulated knowledge of the several simulation components involved. This component handles the incoming-possibly conflicting-world changes propagated by the diverse components. It becomes the central instance for process flow synchronization of several autonomous evaluation loops.