Real Hexapod Research Articles

Workspace trajectory generation with smooth gait transition using CPG-based locomotion control for hexapod robot

—This paper presents a new control methodology for achieving smooth gait transitions for a hexapod robot using Central Pattern Generators (CPGs). The approach involves modifying the Phase Oscillator within the CPG network to enable smooth transitions between different gaits in order to improve the adaptability to changing environmental conditions. The foot trajectory generator is designed based on the CPG output, allowing the possibility of online adjustment of foot trajectory parameters, such as step height and size, as well as the robot's speed and direction. Our simulation demonstrates the effectiveness of the modified oscillator in achieving smoother gait transitions with a transition time falls close to the output period of the CPG oscillators, and experiments on a real hexapod robot validate the feasibility and efficiency of our approach in considering online adjustability of trajectory parameters, confirming the potential of this methodology to enhance the locomotion capabilities of legged robots for navigating complex terrains.

Adaptive Gait Generation for Hexapod Robots Based on Reinforcement Learning and Hierarchical Framework

Gait plays a decisive role in the performance of hexapod robot walking; this paper focuses on adaptive gait generation with reinforcement learning for a hexapod robot. Moreover, the hexapod robot has a high-dimensional action space and therefore it is a great challenge to use reinforcement learning to directly train the robot’s joint angles. As a result, a hierarchical and modular framework and learning details are proposed in this paper, using only seven-dimensional vectors to denote the agent actions. In addition, we conduct experiments and deploy the proposed framework using a real hexapod robot. The experimental results show that superior reinforcement learning algorithms can converge in our framework, such as SAC, PPO, DDPG and TD3. Specifically, the gait policy trained in our framework can generate new adaptive hexapod gait on flat terrain, which is stable and has lower transportation cost than rhythmic gaits.

Autonomous robotic exploration with simultaneous environment and traversability models learning.

In this study, we address generalized autonomous mobile robot exploration of unknown environments where a robotic agent learns a traversability model and builds a spatial model of the environment. The agent can benefit from the model learned online in distinguishing what terrains are easy to traverse and which should be avoided. The proposed solution enables the learning of multiple traversability models, each associated with a particular locomotion gait, a walking pattern of a multi-legged walking robot. We propose to address the simultaneous learning of the environment and traversability models by a decoupled approach. Thus, navigation waypoints are generated using the current spatial and traversability models to gain the information necessary to improve the particular model during the robot’s motion in the environment. From the set of possible waypoints, the decision on where to navigate next is made based on the solution of the generalized traveling salesman problem that allows taking into account a planning horizon longer than a single myopic decision. The proposed approach has been verified in simulated scenarios and experimental deployments with a real hexapod walking robot with two locomotion gaits, suitable for different terrains. Based on the achieved results, the proposed method exploits the online learned traversability models and further supports the selection of the most appropriate locomotion gait for the particular terrain types.

Self-supervised learning of the biologically-inspired obstacle avoidance of hexapod walking robot

In this paper, we propose an integrated biologically inspired visual collision avoidance approach that is deployed on a real hexapod walking robot. The proposed approach is based on the Lobula giant movement detector (LGMD), a neural network for looming stimuli detection that can be found in visual pathways of insects, such as locusts. Although a superior performance of the LGMD in the detection of intercepting objects has been shown in many collision avoiding scenarios, its direct integration with motion control is an unexplored topic. In our work, we propose to utilize the LGMD neural network for visual interception detection with a central pattern generator (CPG) for locomotion control of a hexapod walking robot that are combined in the controller based on the long short-term memory (LSTM) recurrent neural network. Moreover, we propose self-supervised learning of the integrated controller to autonomously find a suitable setting of the system using a realistic robotic simulator. Thus, individual neural networks are trained in a simulation to enhance the performance of the controller that is then experimentally verified with a real hexapod walking robot in both collision and interception avoidance scenario and navigation in a cluttered environment.

支持脚緩衝領域を用いた遠隔操作のためのトライポッド歩行制御

In this paper, a new method setting workspace for tripod gate is proposed to realize smooth walking. Generally, frequent stepping change of the leg occurs when turning direction near the movable limit of the work space. To avoid the stepping request, the buffer area is provided to the outside of the work space of the support leg. The proposed method is implemented to the real hexapod robot, and the effectiveness is shown by comparing the energy consumption

Development of Algorithms and Control Programs for Implementation of the Movements of the Output Link of a Robot-Hexapod for 3D Printing of Precision Products

The article deals with modeling of the movements performed by a hexapod robot. The aim of development is creation of the control programs, making possible production of layered volume 3D-press products or obtaining of coatings without the use of postprocessors. The objective is to develop special algorithms used in the control programs. Algorithms were constructed on the basis of the principle of a cyclic program. Due to the internal robot-hexapod's numeric registers a possibility was realized of a simplified data input to the path of movement of the tool, which can act as an extruder, or another tool with a nozzle for spraying of the working substance. With the help of the cycles in the control program sorting out of values was done within certain ranges of the numeric registers. As a result of the sorting, the control program determines a correct setting of the program, or coordinate, which is to be followed at the moment. The obtained algorithms are intended for the reciprocating and rotational movement of the working body on the trajectory. The control program is small and can easily be reconfigured for other dimensions of the resulting surface, or other parameters such as the diameter of the nozzle, number of layers, starting point and spray rate. The operation control programs were tested on a real hexapod robot in a laboratory. In addition, with the help of the software a system project, including a copy of the virtual environment, was created, in which the robot operated, as well as a virtual remote control, which made it possible to write a control program or change the numerical value of the registers. This control program was tested in a virtual environment, with a clear visualization of the robot and display of the motion path of the output link.

Design of Spiking Central Pattern Generators for Multiple Locomotion Gaits in Hexapod Robots by Christiansen Grammar Evolution

This paper presents a method to design Spiking Central Pattern Generators (SCPGs) to achieve locomotion at different frequencies on legged robots. It is validated through embedding its designs into a Field-Programmable Gate Array (FPGA) and implemented on a real hexapod robot. The SCPGs are automatically designed by means of a Christiansen Grammar Evolution (CGE)-based methodology. The CGE performs a solution for the configuration (synaptic weights and connections) for each neuron in the SCPG. This is carried out through the indirect representation of candidate solutions that evolve to replicate a specific spike train according to a locomotion pattern (gait) by measuring the similarity between the spike trains and the SPIKE distance to lead the search to a correct configuration. By using this evolutionary approach, several SCPG design specifications can be explicitly added into the SPIKE distance-based fitness function, such as looking for Spiking Neural Networks (SNNs) with minimal connectivity or a Central Pattern Generator (CPG) able to generate different locomotion gaits only by changing the initial input stimuli. The SCPG designs have been successfully implemented on a Spartan 6 FPGA board and a real time validation on a 12 Degrees Of Freedom (DOFs) hexapod robot is presented.

Analysis of the Hexapod Work Space using integration of a CAD/CAE system and the LabVIEW software

The paper presents the problems related to the integration of a CAD/CAE system with the LabVIEW software. The purpose of the integration is to determine the workspace of a hexapod model basing on a mathematical model describing it motion. In the first stage of the work concerning the integration task the 3D model to simulate movements of a hexapod was elaborated. This phase of the work was done in the “Motion Simulation” module of the CAD/CAE/CAM Siemens NX system. The first step was to define the components of the 3D model in the form of “links”. Individual links were defined according to the nature of the hexapod elements action. In the model prepared for movement simulation were created links corresponding to such elements as: electric actuator, top plate, bottom plate, ball-and-socket joint, toggle joint Phillips. Then were defined the constraints of the “joint” type (e.g.: revolute joint, slider joint, spherical joint) between the created component of the “link” type, so that the computer simulation corresponds to the operation of a real hexapod. The next stage of work included implementing the mathematical model describing the functioning of a hexapod in the LabVIEW software. At this stage, particular attention was paid to determining procedures for integrating the virtual 3D hexapod model with the results of calculations performed in the LabVIEW. The results relate to specific values of the jump of electric actuators depending on the position of the car on the hexapod. The use of integration made it possible to determine the safe operating space of a stationary hexapod taking into consideration the security of a person in the driving simulator designed for the disabled.

The Influence of Payload Mass and Inertia Properties on a Piloted Flight Simulator Hexapod Dynamic Performance

In order to improve the dynamic performance of a piloted flight simulator hexapod, a study was carried out to quantify the effects of payload mass and inertia properties on hexapod dynamic performance. Based on the Lagrange-Euler formulation, a dynamics model of hexapod parallel mechanism including the payload mass characteristics was built, and then analyzed with the real hexapod through experiments. According to a large amount of experiment datum, the influence of payload mass and inertia properties on a piloted flight simulator hexapod dynamic performance was obtained, and these results are significant for the high speed and high acceleration control of the hexapod mechanism.

Biologically-inspired adaptive obstacle negotiation behavior of hexapod robots.

Neurobiological studies have shown that insects are able to adapt leg movements and posture for obstacle negotiation in changing environments. Moreover, the distance to an obstacle where an insect begins to climb is found to be a major parameter for successful obstacle negotiation. Inspired by these findings, we present an adaptive neural control mechanism for obstacle negotiation behavior in hexapod robots. It combines locomotion control, backbone joint control, local leg reflexes, and neural learning. While the first three components generate locomotion including walking and climbing, the neural learning mechanism allows the robot to adapt its behavior for obstacle negotiation with respect to changing conditions, e.g., variable obstacle heights and different walking gaits. By successfully learning the association of an early, predictive signal (conditioned stimulus, CS) and a late, reflex signal (unconditioned stimulus, UCS), both provided by ultrasonic sensors at the front of the robot, the robot can autonomously find an appropriate distance from an obstacle to initiate climbing. The adaptive neural control was developed and tested first on a physical robot simulation, and was then successfully transferred to a real hexapod robot, called AMOS II. The results show that the robot can efficiently negotiate obstacles with a height up to 85% of the robot's leg length in simulation and 75% in a real environment.

Modular Robot Control Environment – Testing Neural Control on Simulated and Real Robots

Event Abstract Back to Event Modular Robot Control Environment – Testing Neural Control on Simulated and Real Robots Frank Hesse1, 2*, Georg Martius3, Poramate Manoonpong1, 4, Martin Biehl1, 4 and Florentin Wörgötter1, 4 1 Georg-August-Universität Göttingen, Third Institute of Physics - Biophysics, Germany 2 Bernstein Focus Neurotechnology, Germany 3 Max Planck Institute for Mathematics in the Sciences, Germany 4 Bernstein Center for Computational Neuroscience, Germany To develop new control approaches for robotic devices and evaluate their results it is important to be able to efficiently test them not only in simulated but also real environments. This means switching between simulated and real systems should be easily possible using the same controller code (without reprogramming). Furthermore, the development process should be able to continuously increase robot functionality in order to solve more complex tasks. This can be achieved based on modularity. A modular structure is considered as a major advantage, compared to many other approaches due to the following aspects: 1) It is flexible, allowing to simply rearrange, add, and/or remove modules for controlling different types of robots. 2) Each module is typically independent of other modules in its functioning and does not influence or become influenced by other modules. Taking this into account, here we present a modular robot control environment relying on the C++ programming language and providing an artificial neural network library. It is used to develop neurocontrollers for different robots. The very same controller code can now be tested in simulation and on real hardware, which allows speeding up the development process. The modular robot control environment also allows to exchange robots and controller in a plug-and-play manner where parameters of the simulation and real robot can be observed and changed online. We have applied the modular robot control environment to develop neural control of hexapod walking robots AMOSII. They are biologically inspired hardware platforms developed in collaboration with the Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS. They are used to study the coordination of many degrees of freedom, to perform experiments with neural control, memory, and learning. The robots were modeled using LPZRobots [1], a physically realistic simulation toolkit (freely available under GNU General Public License). Employing iterated development cycles, including progression of a neural controller and tests on the simulated and real hexapod platform, a variety of biologically inspired walking gaits as well as orienting, taxis and their combinations have been successfully achieved. By recently developing another module for adaptive climbing behavior, the hexapod can now overcome obstacles of various heights (e.g., ~ 75% of its leg length, which is higher than those that other comparable legged robots have achieved so far). The presented modular robot control environment can also be applied to different types of robotic systems, like wheeled robots and manipulators (e.g., integration of the E-puck mobile robot and the KUKA-DLR Lightweight Robot arm in preparation). Figure 1: Modular Robot Control Environment: The developed neural controllers can easily be transferred to and tested on real and simulated hardware platforms. Here a neural control for hexapod locomotion is depicted. Figure 1 Acknowledgements This research was supported by the BMBF-funded BFNT Göttingen with grant number 01GQ0811 (project 3B) and BCCN Göttingen with grant number 01GQ1005A (project D1), and the Emmy Noether Program (DFG, MA4464/3-1).

Evolving Gaits of a Hexapod Robot by Recurrent Neural Networks With Symbiotic Species-Based Particle Swarm Optimization

This paper proposes a new learning approach for evolving dynamic gaits of a hexapod robot. The controller that coordinates the leg movements consists of fully connected recurrent neural networks (FCRNNs). To automate the FCRNN parameter design, a symbiotic species-based particle swarm optimization (SSPSO) algorithm is proposed. There are multiple swarms in the SSPSO, where a swarm only optimizes the relevant parameters to a single node. The number of swarms is equal to the number of nodes in an FCRNN. The symbiotic behavior of particles from different swarms corresponds to the symbiotic structure of different nodes in an FCRNN. For a particle update, particles in different swarms update independently using a local version of particle swarm optimization (PSO) based on speciation. In each swarm, species are formed adaptively in each iteration according to both particle distance and performance. The design of FCRNNs using the SSPSO for temporal sequence generation and hexapod robot dynamic gait evolution for forward movement is conducted. For the latter, a multiple-FCRNN controller is first designed using a simulated hexapod robot. The designed controller is then successfully applied to a real hexapod robot gait control. The SSPSO is compared with the genetic algorithm and different PSO algorithms to verify its efficiency and effectiveness.

A biologically inspired approach to feasible gait learning for a hexapod robot

A biologically inspired approach to feasible gait learning for a hexapod robotThe objective of this paper is to develop feasible gait patterns that could be used to control a real hexapod walking robot. These gaits should enable the fastest movement that is possible with the given robot's mechanics and drives on a flat terrain. Biological inspirations are commonly used in the design of walking robots and their control algorithms. However, legged robots differ significantly from their biological counterparts. Hence we believe that gait patterns should be learned using the robot or its simulation model rather than copied from insect behaviour. However, as we have foundtahula rasalearning ineffective in this case due to the large and complicated search space, we adopt a different strategy: in a series of simulations we show how a progressive reduction of the permissible search space for the leg movements leads to the evolution of effective gait patterns. This strategy enables the evolutionary algorithm to discover proper leg co-ordination rules for a hexapod robot, using only simple dependencies between the states of the legs and a simple fitness function. The dependencies used are inspired by typical insect behaviour, although we show that all the introduced rules emerge also naturally in the evolved gait patterns. Finally, the gaits evolved in simulations are shown to be effective in experiments on a real walking robot.

Application of joint error maximum mutual compensation for hexapod robots

SUMMARYA good practice to ensure high-positioning accuracy in industrial robots is to use joint error maximum mutual compensation (JEMMC). This paper presents an application of JEMMC for positioning of hexapod robots to improve end-effector positioning accuracy. We developed an algorithm and simulation framework in MatLab to find optimal hexapod configurations with JEMMC. Based on a real hexapod model, simulation results of the proposed approach are presented. Optimal hexapod configurations were found using the local minimum of the infinity norm of hexapod Jacobian inverse. JEMMC usage in hexapod robots can improve hexapod end-effector positioning accuracy by two times and more.

Experiments in learning distributed control for a hexapod robot

This paper reports on experiments involving a hexapod robot. Motivated by neurobiological evidence that control in real hexapod insects is distributed leg-wise, we investigated two approaches to learning distributed controllers: genetic algorithms and reinforcement learning. In the case of reinforcement learning, a new learning algorithm was developed to encourage cooperation between legs. Results from both approaches are presented and compared.