The paper proposes a method for learning velocity estimators, in the form of finite impulse response (FIR) filters, from data collected from a system equipped with quantizing position encoders that is to be controlled by means of a full-state feedback controller making use of the velocity estimates. The resulting estimators are tailored to the properties of the controlled system and show empirically superior performance in comparison with commonly used baseline velocity estimators, both in terms of velocity estimation error as well as in terms of reduced regulation cost when tested on control problems. The proposed adaptive estimators are resistant to overfitting the training data, are easy to implement on embedded controller devices, and can be used in conjunction with various learning control methods.

We propose a method for designing global nonlinear controllers based on the application of memory-based learning schemes for the purpose of aggregating multiple solutions produced by optimal control algorithms based on differential dynamic programming. The method leverages the fact that these optimal control algorithms produce not only nominal state and control trajectories, but entire full-state feedback (FSF) controllers, and the combined controller effectively switches between these multiple FSF controllers. Empirical verification demonstrates that it can be very effective in solving difficult benchmark control problems at high control rates.

The paper presents an experimental study on the application of deep reinforcement learning (DRL) methods to the problem of optimally transporting cargo loads by an overhead gantry crane in minimal time. Experiments in simulation using a physics engine on two versions of the problem, with two and four degrees of freedom and employing reward functions that reflect the objective of load stabilization in minimal time, demonstrate that policies trained with the Stochastic Actor Critic (SAC) DRL method achieve up to 20% shorter transport time in comparison with controllers designed by means of more traditional methods from the field of control engineering.

Imagine a robot that can assemble a functional product from the individual parts presented in any configuration to the robot. Designing such a robotic system is a complex problem which presents several open challenges. To bypass these challenges, the current generation of assembly systems is built with a lot of system integration effort to provide the structure and precision necessary for assembly. These systems are mostly responsible for part singulation, part kitting, and part detection, which is accomplished by intelligent system design. In this paper, we present autonomous assembly of a gear box with minimum requirements on structure. The assembly parts are randomly placed in a two-dimensional work environment for the robot. The proposed system makes use of several different manipulation skills such as sliding for grasping, in-hand manipulation, and insertion to assemble the gear box. All these tasks are run in a closed-loop fashion using vision, tactile, and Force-Torque (F/T) sensors. We perform extensive hardware experiments to show the robustness of the proposed methods as well as the overall system. See supplementary video at https://www.youtube.com/watch?v=cZ9M1DQ23OI.

We present a method for designing and tuning controllers for the problem of swing-up and stabilization of a Furuta pendulum. The method is based on suitable parameterization of a family of controllers and the application of Bayesian optimization to their tuning with minimal interaction with the physical system. Unlike traditional controller design methodologies, the method does not require the derivation of an exact physical model of the controlled plant, thus saving significant design time and effort. Furthermore, the method has much more favorable sample complexity than most policy optimization methods proposed in the field of reinforcement learning.

Robotic assembly systems are common in modern industry and a fixture of commerce. However, the robots themselves lack the adaptability of humans in terms of singulating and grasping parts with uncontrolled pose. To this end, vibratory bowl feeder (VBF) devices are often employed to pre-orient the part for robot grasping. Unfortunately, VBFs themselves are inflexible (usually bespoken for one specific part), noisy, and very expensive to design and tune. We consider an alternative to the VBF - an array of impulse-generating solenoids positioned under a semi-rigid part-carrying platform that uses computer vision and self-supervised machine learning to generate a policy implementing a closed-loop controller to orient randomly positioned parts into a pose acceptable for robot grasping. Using a flat square wooden nut from a child's assembly toy as a test object, we were able to flip the nut into the desired orientation (standing vertically on the narrow edge) 21.1% of the time with a single impulse, and 35.4% of the time with two impulses, versus just 10.2% and 19.2% (respectively) of the time for a baseline policy of random choice of solenoid position and impulse duration, thus demonstrating black-box control of a process commonly considered too difficult to physically model.

This paper presents a problem of model learning for the purpose of learning how to navigate a ball to a goal state in a circular maze environment with two degrees of freedom. The motion of the ball in the maze environment is influenced by several non-linear effects such as dry friction and contacts, which are difficult to model physically. We propose a semiparametric model to estimate the motion dynamics of the ball based on Gaussian Process Regression equipped with basis functions obtained from physics first principles. The accuracy of this semiparametric model is shown not only in estimation but also in prediction at n-steps ahead and its compared with standard algorithms for model learning. The learned model is then used in a trajectory optimization algorithm to compute ball trajectories. We propose the system presented in the paper as a benchmark problem for reinforcement and robot learning, for its interesting and challenging dynamics and its relative ease of reproducibility.

In this paper, we will report some recent progress on wireless power transfer (WPT) based on resonant coupling. Two major technologies will be discussed: the use of metamaterials and array of coupled resonators. With a slab of metamaterial, the near-field coupling between two resonant coils can be enhanced; the power transfer efficiency between coils is boosted by the metamaterial. The principle of enhanced coupling with metamaterial will be discussed; the design of metamaterial slabs for near-field wireless power transfer will be shown; recent experimental results on wireless power transfer efficiency improvement with metamaterial will also be presented. By using an array of resonators, the range of efficient power transfer can be greatly extended. More importantly, this new technology can provide wireless power to both static and mobile devices dynamically. The principle of this technology will be explained; analytical and numerical models will be used to evaluate the performance of a WPT system with an array of resonators; recent experimental developments will also be presented.

In this paper, we show how traditional physical interface components such as switches, levers, knobs and touch screens can be easily modified to identify who is activating each control. This allows us to change the function per-formed by the control, and the sensory feedback provided by the control itself, dependent upon the user. An auditing function is also available that logs each user's actions. We describe a number of example usage scenarios for our tech-nique, and present two sample implementations.

In this paper we present a Markov random field model based approach to filter spam. Our approach examines the importance of the neighborhood relationship (MRF cliques) among words in an email message for the purpose of spam classification. We propose and test several different theoretical bases for weighting schemes among corresponding neighborhood windows. Our results demonstrate that unexpected side effects depending on the neighborhood window size may have larger accuracy impact than the neighborhood relationship effects of the Markov random field.

In this paper we present a system for providing tactile feedback for stylus-based touch-screen displays. The Haptic Pen is a simple low-cost device that provides individualized tactile feedback for multiple simultaneous users and can operate on large touch screens as well as ordinary surfaces. A pressure-sensitive stylus is combined with a small solenoid to generate a wide range of tactile sensations. The physical sensations generated by the Haptic pen can be used to enhance our existing interaction with graphical user interfaces as well as to help make modern computing systems more accessible to those with visual or motor impairments.

A system that uses an ear proximity sensor to actively manage periods of distraction during telephone conversations is described. We detect when the phone is removed from the ear, record any incoming audio, and play it back when the phone is returned to the ear. By dropping silent intervals and speeding up playback with a pitch-preserving algorithm, we quickly return to real-time without the loss of information. This real-time audio buffering technique also allows us to create a user-activated, lossless instant replay function.