Locally weighted learning model predictivek control for elastic joint robots

This paper proposes an efficient and online learning control system that uses the successful Model Predictive Control (MPC) method in a model based locally weighted learning framework. The new approach named Locally Weighted Learning Model Predictive Control (LWL-MPC) has been proposed as a solution to learn to control complex and nonlinear Elastic Joint Robots (EJR). Elastic Joint Robots are generally difficult to learn to control due to their elastic properties preventing standard model learning techniques from being used, such as learning computed torque control. This paper demonstrates the capability of LWL-MPC to perform online and incremental learning while controlling the joint positions of a real three Degree of Freedom (DoF) EJR. An experiment on a real EJR is presented and LWL-MPC is shown to successfully learn to control the system to follow two different figure of eight trajectories.

Locally weighted learning methods for non-rigid robot control

This thesis develops a novel approach to robot control that learns to account for a robot's dynamic complexities while executing various control tasks using inspiration from biological sensorimotor control and machine learning. A robot that can learn its own control system can account for complex situations and adapt to changes in control conditions to maximise its performance and reliability in the real world. This research has developed two novel learning methods, with the aim of solving issues with learning control of non-rigid robots that incorporate additional dynamic complexities. The new learning control system was evaluated on a real three degree-of-freedom elastic joint robot arm with a number of experiments: initially validating the learning method and testing its ability to generalise to new tasks, then evaluating the system during a learning control task requiring continuous online model adaptation.

Locally weighted learning model predictive control for nonlinear and time varying dynamics

This paper proposes an online learning control system that uses the strategy of Model Predictive Control (MPC) in a model based locally weighted learning framework. The new approach, named Locally Weighted Learning Model Predictive Control (LWL-MPC), is proposed as a solution to learn to control robotic systems with nonlinear and time varying dynamics. This paper demonstrates the capability of LWL-MPC to perform online learning while controlling the joint trajectories of a low cost, three degree of freedom elastic joint robot. The learning performance is investigated in both an initial learning phase, and when the system dynamics change due to a heavy object added to the tool point. The experiment on the real elastic joint robot is presented and LWL-MPC is shown to successfully learn to control the system with and without the object. The results highlight the capability of the learning control system to accommodate the lack of mechanical consistency and linearity in a low cost robot arm.

Motor control optimization of compliant one-legged locomotion in rough terrain

While underactuated robotic systems are capable of energy efficient and rapid dynamic behavior, we still do not fully understand how body dynamics can be actively used for adaptive behavior in complex unstructured environment. In particular, we can expect that the robotic systems could achieve high maneuverability by flexibly storing and releasing energy through the motor control of the physical interaction between the body and the environment. This paper presents a minimalistic optimization strategy of motor control policy for underactuated legged robotic systems. Based on a reinforcement learning algorithm, we propose an optimization scheme, with which the robot can exploit passive elasticity for hopping forward while maintaining the stability of locomotion process in the environment with a series of large changes of ground surface. We show a case study of a simple one-legged robot which consists of a servomotor and a passive elastic joint. The dynamics and learning performance of the robot model are tested in simulation, and then transferred the results to the real-world robot. ©2007 IEEE.

Integrating the Utkin observer with the unscented Kalman filter

This paper describes the integration of an Utkin observer with the unscented Kalman filter, investigates the performance of the combined observer, termed the unscented Utkin observer, and compares it with an unscented Kalman filter. Simulation tests are performed using a model of a single link robot arm with a revolute elastic joint rotating in a vertical plane. The results indicate that the unscented Utkin observer outperforms the unscented Kalman filter.

Towards vision-based deep reinforcement learning for robotic motion control

This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixel images and without any prior knowledge of configuration is shown for the first time. We build upon the success of recent deep reinforcement learning and develop a system for learning target reaching with a three-joint robot manipulator using external visual observation. A Deep Q Network (DQN) was demonstrated to perform target reaching after training in simulation. Transferring the network to real hardware and real observation in a naive approach failed, but experiments show that the network works when replacing camera images with synthetic images.

机器人手臂弹性动力学分析的高效算法

本文提出一种用于机器人手臂弹性动力学分析的新方法,该方法采用了动力学方程缩减技术,使计算时间大为减少。在此基础上针对关节型机器人结构特点,提出了考虑手臂关节之间的弹性连接的数学模型,使计算精度得到提高,最后给出了一个实例。

Improved joint control using a genetic algorithm for a humanoid robot

This paper describes experiments conducted in order to simultaneously tune 15 joints of a humanoid robot. Two Genetic Algorithm (GA) based tuning methods were developed and compared against a hand-tuned solution. The system was tuned in order to minimise tracking error while at the same time achieve smooth joint motion. Joint smoothness is crucial for the accurate calculation of online ZMP estimation, a prerequisite for a closedloop dynamically stable humanoid walking gait. Results in both simulation and on a real robot are presented, demonstrating the superior smoothness performance of the GA based methods.

Fuzzy associative memory for humanoid robot joint control

Traditional approaches to joint control required accurate modelling of the system dynamic of the plant in question. Fuzzy Associative Memory (FAM) control schemes allow adequate control without a model of the system to be controlled. This paper presents a FAM based joint controller implemented on a humanoid robot. An empirically tuned PI velocity control loop is augmented with this feed forward FAM, with considerable reduction in joint position error achieved online and with minimal additional computational overhead.

Biologically inspired joint control for a humanoid robot

The GuRoo is a 1.2 m tall, 23 degree of freedom humanoid constructed at the University of Queensland for research into humanoid robotics. The key challenge being addressed by the GuRoo project is the development of appropriate learning strategies for control and coordination of the robot's many joints. The development of learning strategies is seen as a way to side-step the inherent intricacy of modeling a multi-DOF biped robot. This paper outlines the approach taken to generate an appropriate control scheme for the joints of the GuRoo. The paper demonstrates the determination of local feedback control parameters using a genetic algorithm. The feedback loop is then augmented by a predictive modulator that learns a form of feed-forward control to overcome the irregular loads experienced at each joint during the gait cycle. The predictive modulator is based on the CMAC architecture. Results from tests on the GuRoo platform show that both systems provide improvements in stability and tracking of joint control.

Cerebellar augmented joint control for a humanoid robot

The joints of a humanoid robot experience disturbances of markedly different magnitudes during the course of a walking gait. Consequently, simple feedback control techniques poorly track desired joint trajectories. This paper explores the addition of a control system inspired by the architecture of the cerebellum to improve system response. This system learns to compensate the changes in load that occur during a cycle of motion. The joint compensation scheme, called Trajectory Error Learning, augments the existing feedback control loop on a humanoid robot. The results from tests on the GuRoo platform show an improvement in system response for the system when augmented with the cerebellar compensator.

Learning multidimensional joint control of a robot using receding horizon locally weighted regression

In this paper we explore the ability of a recent model-based learning technique Receding Horizon Locally Weighted Regression (RH-LWR) useful for learning temporally dependent systems. In particular this paper investigates the application of RH-LWR to learn control of Multiple-input Multiple-output robot systems. RH-LWR is demonstrated through learning joint velocity and position control of a three Degree of Freedom (DoF) rigid body robot.

A novel energy efficient controllable stiffness joint

Achieving energy efficient legged locomotion is an important goal for the future of robot mobility. This paper presents a novel joint for legged locomotion that is energy efficient for two reasons. The first reason is the configuration of the elastic elements and actuator which we show analytically has lower energy losses than the typical arrangement. The second is that the joint stiffness, and hence stance duration, is controllable without requiring any energy from the actuator. Further, the joint stiffness can be changed significantly during the flight phase, from zero to highly rigid. Results obtained from a prototype hopper, demonstrate that the joint allows continuous and peak hopping via torque control. The results also demonstrate that the hopping frequency can be varied between 2.2Hz and 4.6Hz with associated stance duration of between 0.35 and 0.15 seconds.

Influence of Joint Thickness and Mortar-Block Elastic Properties on the Strength and Stresses Developed in Soil-Cement Block Masonry

Soil-cement blocks are employed for load bearing masonry buildings. This paper deals with the study on the influence of bed joint thickness and elastic properties of the soil-cement blocks, and the mortar on the strength and behavior of soil-cement block masonry prisms. Influence of joint thickness on compressive strength has been examined through an experimental program. The nature of stresses developed and their distribution, in the block and the mortar of the soil-cement block masonry prism under compression, has been analyzed by an elastic analysis using FEM. Influence of various parameters like joint thickness, ratio of block to mortar modulus, and Poisson's ratio of the block and the mortar are considered in FEM analysis. Some of the major conclusions of the study are: (1) masonry compressive strength is sensitive to the ratio of modulus of block to that of the mortar (Eb/Em) and masonry compressive strength decreases as the mortar joint thickness is increased for the case where the ratio of block to mortar modulus is more than 1; (2) the lateral tensile stresses developed in the masonry unit are sensitive to the Eb/Em ratio and the Poisson's ratio of mortar and the masonry unit; and (3) lateral stresses developed in the masonry unit are more sensitive to the Poisson's ratio of the mortar than the Poisson's ratio of the masonry unit.