Goto

Collaborating Authors

Feedback Linearization for Unknown Systems via Reinforcement Learning

arXiv.org Artificial Intelligence

We present a novel approach to control design for nonlinear systems, which leverages reinforcement learning techniques to learn a linearizing controller for a physical plant with unknown dynamics. Feedback linearization is a technique from nonlinear control which renders the input-output dynamics of a nonlinear plant \emph{linear} under application of an appropriate feedback controller. Once a linearizing controller has been constructed, desired output trajectories for the nonlinear plant can be tracked using a variety of linear control techniques. A single learned policy then serves to track arbitrary desired reference signals provided by a higher-level planner. We present theoretical results which provide conditions under which the learning problem has a unique solution which exactly linearizes the plant. We demonstrate the performance of our approach on two simulated problems and a physical robotic platform. For the simulated environments, we observe that the learned feedback linearizing policies can achieve arbitrary tracking of reference trajectories for a fully actuated double pendulum and a 14 dimensional quadrotor. In hardware, we demonstrate that our approach significantly improves tracking performance on a 7-DOF Baxter robot after less than two hours of training.


The Distributed Adaptive Control Theory of the Mind and Brain as a candidate Standard Model of the Human Mind

AAAI Conferences

This article presents the Distributed Adaptive Control (DAC) theory of mind and brain as a candidate standard model of the human mind. DAC is defined against a reformulation of the criteria for unified theories of cognition advanced by Allen Newell, or the Unified Theories of Embodied Minds – Standard Model benchmark (UTEM-SM) that emphasizes real-world and real-time embodied action. DAC considers mind and brain as the function and implementation of a multi-layered control system and addresses the fundamental question of how the mind, as the product of embodied and situated brains, can obtain, retain and express valid knowledge of its world and transform this into policies for action. DAC provides an explanatory framework for biological minds and brains by satisfying well-defined constraints faced by theories of mind and brain and provides a route for the convergent validation of anatomy, physiology, and behavior in our explanation of biological minds. DAC is a well validated integration and synthesis framework for artificial minds and exemplifies the role of the synthetic method in understanding mind and brain. This article describes the core components of DAC, its performance on specific benchmarks derived from the engagement with the physical and the social world (or the H4W and the H5W problems) and lastly analyzes DAC’s performance on the UTEM-SM benchmark and its relationship with contemporary developments in AI.


Car buyers aren't thrilled about semi-autonomous features

Engadget

JD Power's latest research into the likes and dislikes of car owners has two big takeaways: people love Kia and are pretty lukewarm about self-driving technology. Or, at least those components that most drivers can gain access to right now, like adaptive cruise control, collision avoidance and blind spot warning systems. Overall, the trend for buyers is to be quite positive about the quality and performance of their new vehicle, especially if it's a Kia. "Autonomous Technology" was, in fact, the only category where user complaints increased between 2016 and 2017, although only by a tiny amount. The Wall Street Journal points out that of all the issues consumers raised, 34 percent of them were tied in to adaptive cruise control.


A Hybrid Approach for Trajectory Control Design

arXiv.org Machine Learning

Abstract-- This work presents a methodology to design trajectory tracking feedback control laws, which embed nonparametric statistical models, such as Gaussian Processes (GPs). The aim is to minimize unmodeled dynamics such as undesired slippages. The proposed approach has the benefit of avoiding complex terramechanics analysis to directly estimate from data the robot dynamics on a wide class of trajectories. Experiments in both real and simulated environments prove that the proposed methodology is promising. In the last decades, an increasing interest has been devoted to the design of high performance path tracking. In the literature, three main approaches to face this problem have emerged: (i) model-based and adaptive control [1]-[5]; (ii) Gaussian Processes or stochastic nonlinear models for reinforcement learning of control policies [6], [7], and (iii) nominal models and data-driven estimation of the residual [8], [9].


Announcing the public preview for Adaptive Application Controls

#artificialintelligence

At Microsoft Ignite, we announced new adaptive applications controls that protect your applications from malware by using whitelisting rules. Today, we are excited to share that these capabilities are available for public preview in Azure Security Center.