Reinforcement learning (RL) is a suitable approach for controlling systems with unknown or time-varying dynamics. RL in principle does not require a model of the system, but before it learns an acceptable policy, it n...
详细信息
Reinforcement learning (RL) is a suitable approach for controlling systems with unknown or time-varying dynamics. RL in principle does not require a model of the system, but before it learns an acceptable policy, it needs many unsuccessful trials, which real robots usually cannot withstand. It is well known that RL can be sped up and made safer by using models learned online. In this paper, we propose to use symbolic regression to construct compact, parsimonious models described by analytic equations, which are suitable for real-time robot control. Single node genetic programming (SNGP) is employed as a tool to automatically search for equations fitting the available data. We demonstrate the approach on two benchmark examples: a simulated mobile robot and the pendulum swing-up problem;the latter both in simulations and real-time experiments. The results show that through this approach we can find accurate models even for small batches of training data. Based on the symbolic model found, RL can control the system well.
The proceedings contain 2 papers. The topics discussed include: robot control for nonprehensile dynamic manipulation tasks;and active disturbance rejection robust control for uncertain systems. case: floating offshore...
The proceedings contain 2 papers. The topics discussed include: robot control for nonprehensile dynamic manipulation tasks;and active disturbance rejection robust control for uncertain systems. case: floating offshore wind turbine.
While the problem of inverse kinematics on serial kinematic chains is well researched, solving motion tasks quickly on more complex robots remains an open problem. Examples include dual-arm manipulation, grasping with...
详细信息
While the problem of inverse kinematics on serial kinematic chains is well researched, solving motion tasks quickly on more complex robots remains an open problem. Examples include dual-arm manipulation, grasping with multi-finger hands, and full-body motion generation for humanoids. In this paper, we introduce an open-source software package for ROS and Move It! that solves inverse kinematics and motion tasks on robots with arbitrary kinematic trees. The underlying memetic algorithm integrates evolutionary optimization, particle swarm optimization, and gradient methods. The optimization respects joint limits, effectively avoids local minima, and achieves fast convergence to accurate solutions. More importantly, the overall motion goal is specified using a set of weighted sub-goals, providing great flexibility and control of secondary objectives. Several application examples demonstrate how to combine the predefined sub-goals to achieve complex motion tasks.
This paper presents the design of Impedance control to a redundantly actuated Parallel Kinematic Manipulator. The proposed control is based on treating each limb as a single system and their connection through the int...
详细信息
ISBN:
(纸本)9789897583049
This paper presents the design of Impedance control to a redundantly actuated Parallel Kinematic Manipulator. The proposed control is based on treating each limb as a single system and their connection through the internal interaction forces. The controller introduces a stiffness and damping matrices that decouples the dynamic behaviour of the robot. control allocation of torques is applied through an optimization that promotes even distribution of torques over actuators. Simulations showed a good compliance behaviour in low frequencies.
Maintenance cost of United Kingdom's rail rolling stock is a substantial portion of its whole life costs. Therefore, it is vital to conduct these maintenance tasks in an efficient and cost-effective manner to mini...
详细信息
ISBN:
(纸本)9789897583049
Maintenance cost of United Kingdom's rail rolling stock is a substantial portion of its whole life costs. Therefore, it is vital to conduct these maintenance tasks in an efficient and cost-effective manner to minimize operational costs while maximizing safety, quality, and consistency of service. The introduction of robotics and other intelligent mechanisms to maintenance processes would be an ideal solution to these challenges. Hence, this research suggests introducing autonomous maintenance systems equipped with industrial robots to tasks within the railway system, specifically for rolling-stock maintenance. The paper summarizes on-going and future work of a case-study conduct in conjunction with a UK railway operator.
This research discusses the development of simulation and generator of bipedal robot walking pattern on the sagittal, frontal and transversal planes by setting the trajectory of the sole and the pelvis of the robot wi...
详细信息
This research discusses the development of simulation and generator of bipedal robot walking pattern on the sagittal, frontal and transversal planes by setting the trajectory of the sole and the pelvis of the robot with respect to the position of the robot center of mass changes to the biped robot support polygon. The robot center of mass is assumed to lie in the pelvis, and an adjustment is made when the structure of the robot is reconstructed with an additional load. Adjustments made in the form of converting angle of robot torso. The simulation program and the motion generator run out data-driven in the form of simulation data along with the correction data which is the gravity compensation for the reconstructed humanoid Bioloid robot. Data-driven becomes input for RoboPlus program from Robotis to adjust the angular position of each joint, joint rotation speed, robot posture, and static robot balance control. With the data-driven given, the Bioloid robot can achieve walking motion without falling on a flat and even floor without the overlap of a swinging foot to the stance foot, and without significantly affecting the step length and the step height of the initial planning. The robot reaches a speed of 0.423 m/s.
Humanoid robot has a structure that can be shaped or moved like a human, but in order to walk like a human, it needs to be given the controller to correct the posture and gait on the robot. The PD controller is used t...
详细信息
Humanoid robot has a structure that can be shaped or moved like a human, but in order to walk like a human, it needs to be given the controller to correct the posture and gait on the robot. The PD controller is used to control the posture and gait of the humanoid robot and the Center of Mass (COM) is used as a feedback to keep the humanoid robot stable. Determination of the stability criteria is performed to determine the stable state of the humanoid robot. In this study, we used Bioloid GP in order to get a stable stand and walk on uneven surface conditions. IMU sensors are used to read COM angles and to increase the readability accuracy, while the Kalman filter method is used as an estimate of error and white noise filter. Furthermore, the controller will calculate the error between sensor readings and setpoints to obtain angle correction value for the servo motor in Bioloid GP. The PD controller successful to stabilize the robot in the single slope change in the standing area with the experimental result response of 0% of overshoot on the pitch axis and 0% of overshoot on the roll axis. The response has 2 second of rising time for the Pitch axis and 2.5 seconds for Roll axis.
In this paper, we propose using an approach based on the system-level programming language SystemJ extended with service oriented features, called SOSJ, to design dynamic interoperable software systems. The approach a...
详细信息
ISBN:
(纸本)9781538608371
In this paper, we propose using an approach based on the system-level programming language SystemJ extended with service oriented features, called SOSJ, to design dynamic interoperable software systems. The approach abstracts and integrates the worlds of automation and robotics systems by using a simple service interface based on abstract objects within SOSJ. We demonstrate our approach in a real-life automated bottling system scenario that uses multiple FESTO modular stations operating in SOSJ and integrating them with two Baxter robots operating in ROS without the need for any modification of the underlying mechatronics or robotics systems.
Autonomous exploration aims to develop mechanisms that enable a robot to navigate through an unknown environment, seeking to collect information that is relevant to its objective, with minimal or no human intervention...
详细信息
Autonomous exploration aims to develop mechanisms that enable a robot to navigate through an unknown environment, seeking to collect information that is relevant to its objective, with minimal or no human intervention. This article presents an autonomous exploration strategy based on a multimodal continuous utility function and optimization metaheuristic. The problem of autonomous exploration of mobile robots is formulated as an optimization problem, providing data for a Firefly-based algorithm that is able to search for points in the solution space, representing cells on the map being constructed, that best meet the exploration objectives. Simulations in a Robot Operating System environment showed that the proposed approach is able to guide robot through good trajectories, leading to full mapping, without any human intervention.
The low-cost manufacturing and maintenance of prostheses is of vital importance to their successful deployment in developing countries. Low-cost prosthesis actuation is generally achieved by combining pre-programmed c...
详细信息
The low-cost manufacturing and maintenance of prostheses is of vital importance to their successful deployment in developing countries. Low-cost prosthesis actuation is generally achieved by combining pre-programmed control strategies, with surface-electromyographic measurements taken from the residual limb. In a standard setting, these signals are measured with disposable gel electrodes. However, this limit on electrode reuse requires that prosthesis users have a stable supply of electrodes. Alternatively, the textile electrodes sewn from conductive thread are studied in the context of hand gesture recognition to consider their future use with low-cost prostheses. In this paper, it is demonstrated that textile electrodes can be applied for gesture recognition. To do so, surface electromyography (sEMG) experiments are run in South Africa on three amputees where they were asked to perform gestures with their phantom limb (i.e., the missing limb segment). A gesture recognition method is implemented, and the classification accuracy with data recorded from textile electrodes is compared to that from gel electrodes. Further analysis examining the relationship between classifier performance and physiological parameters are performed. Results show that textile electrodes can be used to perform accurate gesture recognition, and are comparable to disposable gel electrodes. This demonstrates that low-cost sensory systems are not barrier to myoelectric control in developing countries.
暂无评论