JournalTOCs

Robotics and Biomimetics
Number of Followers: 1

This is an Open Access Journal

Open Access journal
ISSN (Online) 2197-3768
Published by SpringerOpen

[229 journals]

Implementation of Q learning and deep Q network for controlling a self
balancing robot model
- Abstract: Abstract In this paper, the implementations of two reinforcement learnings namely, Q learning and deep Q network (DQN) on the Gazebo model of a self balancing robot have been discussed. The goal of the experiments is to make the robot model learn the best actions for staying balanced in an environment. The more time it can remain within a specified limit, the more reward it accumulates and hence more balanced it is. We did various tests with many hyperparameters and demonstrated the performance curves.
  PubDate: 2018-12-21
Cognition-based variable admittance control for active compliance in
- Abstract: Abstract In the first step, a 1-DOF power-assist robotic system (PARS) is developed for lifting lightweight objects. Dynamics for human–robot co-manipulation of objects is derived that considers human cognition (weight perception). Then, admittance control with position feedback and velocity controller is derived using weight perception-based dynamics. Human subjects lift an object with the PARS, and HRI (human–robot interaction) and system characteristics are analyzed. A comprehensive scheme is developed to evaluate the HRI and performance. HRI is expressed in terms of physical HRI (maneuverability, motion, safety, stability, naturalness) and cognitive HRI (workload, trust), and performance is expressed in terms of manipulation efficiency and precision. To follow the guidance of ISO/TS 15066, hazard analysis and risk assessment are conducted. A constrained optimization algorithm is proposed to determine the values of the control parameters that produce optimum HRI and performance with lowest risk. Results show that consideration of weight perception in dynamics and control helps achieve optimum HRI and performance for a set of hard constraints. In the second step, a weight perception-based novel variable admittance control scheme is proposed as an active compliance to the system, which enhances the physical HRI, trust, precision and efficiency by 53.05%, 46.78%, 3.84% and 4.98%, respectively, and reduces workload by 35.38% and thus helps achieve optimum HRI and performance for a set of soft constraints. The risk reduces due to the active compliance. Then, effectiveness of the optimization and control algorithms is validated using a multi-DOF PARS for manipulating heavy objects, and intuitive and natural HRI and performance for power-assisted heavy object manipulation are achieved through calibrating HRI and performance with that for manipulation of lightweight object.
  PubDate: 2018-11-12
PID, BFO-optimized PID, and PD-FLC control of a two-wheeled machine with
two-direction handling mechanism: a comparative study
- Abstract: Abstract In this paper; three control approaches are utilized in order to control the stability of a novel five-degrees-of-freedom two-wheeled robotic machine designed for industrial applications that demand a limited-space working environment. Proportional–integral–derivative (PID) control scheme, bacterial foraging optimization of PID control method, and fuzzy logic control method are applied to the wheeled machine to obtain the optimum control strategy that provides the best system stabilization performance. According to simulation results, considering multiple motion scenarios, the PID controller optimized by bacterial foraging optimization method outperformed the other two control methods in terms of minimum overshoot, rise time, and applied input forces.
  PubDate: 2018-11-03
Systematic engineering design helps creating new soft machines
- Abstract: Abstract Soft robotics is an emerging field in the robotics community which deals with completely new types of robots. However, often new soft robotic designs depend on the ingenuity of the engineer rather being systematically derived. For this reason, in order to support the engineer in the design process, we present a design methodology for general technical systems in this paper and explain it in depth in the context of soft robotics. The design methodology consists of a combination of state-of-the-art engineering concepts that are arranged in such a way that the engineer is guided through the design process. The effectiveness of a systematic approach in soft robotics is illustrated on the design of a new gecko-inspired, climbing soft robot.
  PubDate: 2018-10-26
Hybrid control combined with a voluntary biosignal to control a prosthetic
hand
- Abstract: Abstract In this research, the combination of fuzzy/PD and EMG signals, as direct command control, is proposed. Although fuzzy/PD strategy was used to control force position of the artificial hand, the combination of that with EMG signaling to voluntary direct command control is a novel method. In this paper, the EMG signal and its role in effective communication between a DC motor with a voltage trigger and neurofeedback are initially explained. Moreover, by introducing a filtration method, EMG pulses are obtained as stepping pulses with a signal-specific height of a voltage between 0 and 6 V, according to EMG domain voltage, with a time interval adapted from the EMG stimulus pulses. Two data points from each channel of EMG were extracted. The domain of the voltage of the EMG signal is impacted on the output of the fuzzy logic unit, and also the time amount between each stimulus of the EMG signal is the input of the PD controller. By this method, a user can influence grip position and grasping force of his/her prosthesis.
  PubDate: 2018-09-19
A 6-DOF robot-time optimal trajectory planning based on an improved
genetic algorithm
- Abstract: Abstract By using quintic polynomial function to interpolate several given points of each joint of the robot, the mathematical expressions of each joint variable of the robot with time are established. In addition, to improve the search algorithm performance crossover operator and mutation operator of the genetic algorithm are improved in cosine form. Furthermore, the improved adaptive genetic algorithm is applied to optimize the time interval of interpolation points of each joint, so as to realize time optimal trajectory planning. Moreover, MATLAB simulation is carried out, and the results show that the method proposed in this paper reduces the running time of the robot tasks. Meanwhile, the curves of angle position, velocity and acceleration of each joint are smooth enough, which ensure accomplish its tasks in a stable and efficient way.
  PubDate: 2018-07-03
A multi-jointed underactuated robot hand with fluid-driven stretchable
tubes
- Abstract: Abstract Inspired from flexible bending of octopus’ tentacles and outside-driving kind of traditional exoskeletons, this paper proposed a novel self-adaptive underactuated finger mechanism, called OS finger. OS finger is similar to an octopus’ tentacle and consists of an artificial muscle which is through all joints and driven by fluid, eight serial-hinged joints, and force-changeable assembly. The force-changeable assembly is mainly composed of a spring and elastic rubber membrane, which is coordinated for stable grasping by a layer of rubber material in the surface of the finger. OS finger can execute different grasping modes depending on the shapes and dimensions of the grasped objects and grip objects in a gentle and form-fitting manner. The OS finger combines good qualities of both rigid grasp of traditional fingers and form-fitting grasp of flexible fingers. Kinematic analysis and experimental results show that the OS robot Hand with four OS fingers is valid for precise pinching, self-adaptive powerful encompassing, and grasping forces that are freely changeable in a wide range. With the advantage of high self-adaptation, various grasp configurations and large range of grasping forces, the OS Hand has a wide range of applications in the area of service robotics which requires a lot of flexible operations of general grasping, moving and releasing.
  PubDate: 2018-06-20
Design of a novel wheeled tensegrity robot: a comparison of tensegrity
concepts and a prototype for travelling air ducts
- Abstract: Abstract Efforts in the research of tensegrity structures applied to mobile robots have recently been focused on a purely tensegrity solution to all design requirements. Locomotion systems based on tensegrity structures are currently slow and complex to control. Although wheeled locomotion provides better efficiency over distances there is no literature available on the value of wheeled methods with respect to tensegrity designs, nor on how to transition from a tensegrity structure to a fixed structure in mobile robotics. This paper is the first part of a larger study that aims to combine the flexibility, light weight, and strength of a tensegrity structure with the efficiency and simple control of a wheeled locomotion system. It focuses on comparing different types of tensegrity structure for applicability to a mobile robot, and experimentally finding an appropriate transitional region from a tensegrity structure to a conventional fixed structure on mobile robots. It applies this transitional structure to what is, to the authors’ knowledge, the design of the world’s first wheeled tensegrity robot that has been designed with the goal of traversing air ducts.
  PubDate: 2018-05-15

HOME > Browse the 73 Subjects covered by JournalTOCs
Subject	Total Journals