arXiv subjects

Todd D. Murphey

Publications and source records attributed to Todd D. Murphey.

At least 37 records · Page 2Linked to original sources

arXiv2020

An Ergodic Measure for Active Learning From Equilibrium

This paper develops KL-Ergodic Exploration from Equilibrium ($\text{KL-E}^3$), a method for robotic systems to integrate stability into actively generating informative measurements through ergodic exploration. Ergodic exploration enables robotic systems to indirectly sample from informative spatial distributions globally, avoiding local optima, and without the need to evaluate the derivatives of the distribution against the robot dynamics. Using hybrid systems theory, we derive a controller that allows a robot to exploit equilibrium policies (i.e., policies that solve a task) while allowing the robot to explore and generate informative data using an ergodic measure that can extend to high-dimensional states. We show that our method is able to maintain Lyapunov attractiveness with respect to the equilibrium task while actively generating data for learning tasks such, as Bayesian optimization, model learning, and off-policy reinforcement learning. In each example, we show that our proposed method is capable of generating an informative distribution of data while synthesizing smooth control signals. We illustrate these examples using simulated systems and provide simplification of our method for real-time online learning in robotic systems.

cs.RO↗

arXiv2020

Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion

We present a sim-to-real framework that uses dynamics and domain randomized offline reinforcement learning to enhance open-loop gaits for legged robots, allowing them to traverse uneven terrain without sensing foot impacts. Our approach, D$^2$-Randomized Gait Modulation with Bezier Curves (D$^2$-GMBC), uses augmented random search with randomized dynamics and terrain to train, in simulation, a policy that modifies the parameters and output of an open-loop Bezier curve gait generator for quadrupedal robots. The policy, using only inertial measurements, enables the robot to traverse unknown rough terrain, even when the robot's physical parameters do not match the open-loop model. We compare the resulting policy to hand-tuned Bezier Curve gaits and to policies trained without randomization, both in simulation and on a real quadrupedal robot. With D$^2$-GMBC, across a variety of experiments on unobserved and unknown uneven terrain, the robot walks significantly farther than with either hand-tuned gaits or gaits learned without domain randomization. Additionally, using D$^2$-GMBC, the robot can walk laterally and rotate while on the rough terrain, even though it was trained only for forward walking.

cs.RO↗

arXiv2020

Information Requirements of Collision-Based Micromanipulation

We present a task-centered formal analysis of the relative power of several robot designs, inspired by the unique properties and constraints of micro-scale robotic systems. Our task of interest is object manipulation because it is a fundamental prerequisite for more complex applications such as micro-scale assembly or cell manipulation. Motivated by the difficulty in observing and controlling agents at the micro-scale, we focus on the design of boundary interactions: the robot's motion strategy when it collides with objects or the environment boundary, otherwise known as a bounce rule. We present minimal conditions on the sensing, memory, and actuation requirements of periodic ``bouncing'' robot trajectories that move an object in a desired direction through the incidental forces arising from robot-object collisions. Using an information space framework and a hierarchical controller, we compare several robot designs, emphasizing the information requirements of goal completion under different initial conditions, as well as what is required to recognize irreparable task failure. Finally, we present a physically-motivated model of boundary interactions, and analyze the robustness and dynamical properties of resulting trajectories.

cs.RO↗

arXiv2020

Algorithmic Design for Embodied Intelligence in Synthetic Cells

In nature, biological organisms jointly evolve both their morphology and their neurological capabilities to improve their chances for survival. Consequently, task information is encoded in both their brains and their bodies. In robotics, the development of complex control and planning algorithms often bears sole responsibility for improving task performance. This dependence on centralized control can be problematic for systems with computational limitations, such as mechanical systems and robots on the microscale. In these cases we need to be able to offload complex computation onto the physical morphology of the system. To this end, we introduce a methodology for algorithmically arranging sensing and actuation components into a robot design while maintaining a low level of design complexity (quantified using a measure of graph entropy), and a high level of task embodiment (evaluated by analyzing the Kullback-Leibler divergence between physical executions of the robot and those of an idealized system). This approach computes an idealized, unconstrained control policy which is projected onto a limited selection of sensors and actuators in a given library, resulting in intelligence that is distributed away from a central processor and instead embodied in the physical body of a robot. The method is demonstrated by computationally optimizing a simulated synthetic cell.

cs.RO↗

arXiv2020

Hybrid Control for Learning Motor Skills

We develop a hybrid control approach for robot learning based on combining learned predictive models with experience-based state-action policy mappings to improve the learning capabilities of robotic systems. Predictive models provide an understanding of the task and the physics (which improves sample-efficiency), while experience-based policy mappings are treated as "muscle memory" that encode favorable actions as experiences that override planned actions. Hybrid control tools are used to create an algorithmic approach for combining learned predictive models with experience-based learning. Hybrid learning is presented as a method for efficiently learning motor skills by systematically combining and improving the performance of predictive models and experience-based policies. A deterministic variation of hybrid learning is derived and extended into a stochastic implementation that relaxes some of the key assumptions in the original derivation. Each variation is tested on experience-based learning methods (where the robot interacts with the environment to gain experience) as well as imitation learning methods (where experience is provided through demonstrations and tested in the environment). The results show that our method is capable of improving the performance and sample-efficiency of learning motor skills in a variety of experimental domains.

cs.RO↗

arXiv2020

Model-Based Generalization Under Parameter Uncertainty Using Path Integral Control

This work addresses the problem of robot interaction in complex environments where online control and adaptation is necessary. By expanding the sample space in the free energy formulation of path integral control, we derive a natural extension to the path integral control that embeds uncertainty into action and provides robustness for model-based robot planning. Our algorithm is applied to a diverse set of tasks using different robots and validate our results in simulation and real-world experiments. We further show that our method is capable of running in real-time without loss of performance. Videos of the experiments as well as additional implementation details can be found at https://sites.google.com/view/emppi.

cs.RO↗

arXiv2019

Active Learning of Dynamics for Data-Driven Control Using Koopman Operators

This paper presents an active learning strategy for robotic systems that takes into account task information, enables fast learning, and allows control to be readily synthesized by taking advantage of the Koopman operator representation. We first motivate the use of representing nonlinear systems as linear Koopman operator systems by illustrating the improved model-based control performance with an actuated Van der Pol system. Information-theoretic methods are then applied to the Koopman operator formulation of dynamical systems where we derive a controller for active learning of robot dynamics. The active learning controller is shown to increase the rate of information about the Koopman operator. In addition, our active learning controller can readily incorporate policies built on the Koopman dynamics, enabling the benefits of fast active learning and improved control. Results using a quadcopter illustrate single-execution active learning and stabilization capabilities during free-fall. The results for active learning are extended for automating Koopman observables and we implement our method on real robotic systems.

cs.RO↗

arXiv2019

Active Area Coverage from Equilibrium

This paper develops a method for robots to integrate stability into actively seeking out informative measurements through coverage. We derive a controller using hybrid systems theory that allows us to consider safe equilibrium policies during active data collection. We show that our method is able to maintain Lyapunov attractiveness while still actively seeking out data. Using incremental sparse Gaussian processes, we define distributions which allow a robot to actively seek out informative measurements. We illustrate our methods for shape estimation using a cart double pendulum, dynamic model learning of a hovering quadrotor, and generating galloping gaits starting from stationary equilibrium by learning a dynamics model for the half-cheetah system from the Roboschool environment.

cs.RO↗

arXiv2018

Decentralized Ergodic Control: Distribution-Driven Sensing and Exploration for Multi-Agent Systems

We present a decentralized ergodic control policy for time-varying area coverage problems for multiple agents with nonlinear dynamics. Ergodic control allows us to specify distributions as objectives for area coverage problems for nonlinear robotic systems as a closed-form controller. We derive a variation to the ergodic control policy that can be used with consensus to enable a fully decentralized multi-agent control policy. Examples are presented to illustrate the applicability of our method for multi-agent terrain mapping as well as target localization. An analysis on ergodic policies as a Nash equilibrium is provided for game theoretic applications.

cs.RO↗

arXiv2018

Data-Driven Measurement Models for Active Localization in Sparse Environments

We develop an algorithm to explore an environment to generate a measurement model for use in future localization tasks. Ergodic exploration with respect to the likelihood of a particular class of measurement (e.g., a contact detection measurement in tactile sensing) enables construction of the measurement model. Exploration with respect to the information density based on the data-driven measurement model enables localization. We test the two-stage approach in simulations of tactile sensing, illustrating that the algorithm is capable of identifying and localizing objects based on sparsely distributed binary contacts. Comparisons with our method show that visiting low probability regions lead to acquisition of new information rather than increasing the likelihood of known information. Experiments with the Sphero SPRK robot validate the efficacy of this method for collision-based estimation and localization of the environment.

cs.RO↗

arXiv2018

Feedback Synthesis For Underactuated Systems Using Sequential Second-Order Needle Variations

This paper derives nonlinear feedback control synthesis for general control affine systems using second-order actions---the second-order needle variations of optimal control---as the basis for choosing each control response to the current state. A second result of the paper is that the method provably exploits the nonlinear controllability of a system by virtue of an explicit dependence of the second-order needle variation on the Lie bracket between vector fields. As a result, each control decision necessarily decreases the objective when the system is nonlinearly controllable using first-order Lie brackets. Simulation results using a differential drive cart, an underactuated kinematic vehicle in three dimensions, and an underactuated dynamic model of an underwater vehicle demonstrate that the method finds control solutions when the first-order analysis is singular. Lastly, the underactuated dynamic underwater vehicle model demonstrates convergence even in the presence of a velocity field.

cs.RO↗

arXiv2017

Dynamic Task Execution using Active Parameter Identification with the Baxter Research Robot

This paper presents experimental results from real-time parameter estimation of a system model and subsequent trajectory optimization for a dynamic task using the Baxter Research Robot from Rethink Robotics. An active estimator maximizing Fisher information is used in real-time with a closed-loop, non-linear control technique known as Sequential Action Control. Baxter is tasked with estimating the length of a string connected to a load suspended from the gripper with a load cell providing the single source of feedback to the estimator. Following the active estimation, a trajectory is generated using the trep software package that controls Baxter to dynamically swing a suspended load into a box. Several trials are presented with varying initial estimates showing that estimation is required to obtain adequate open-loop trajectories to complete the prescribed task. The result of one trial with and without the active estimation is also shown in the accompanying video.

cs.RO↗

arXiv2017

Trajectory Synthesis for Fisher Information Maximization

Estimation of model parameters in a dynamic system can be significantly improved with the choice of experimental trajectory. For general, nonlinear dynamic systems, finding globally "best" trajectories is typically not feasible; however, given an initial estimate of the model parameters and an initial trajectory, we present a continuous-time optimization method that produces a locally optimal trajectory for parameter estimation in the presence of measurement noise. The optimization algorithm is formulated to find system trajectories that improve a norm on the Fisher information matrix. A double-pendulum cart apparatus is used to numerically and experimentally validate this technique. In simulation, the optimized trajectory increases the minimum eigenvalue of the Fisher information matrix by three orders of magnitude compared to the initial trajectory. Experimental results show that this optimized trajectory translates to an order of magnitude improvement in the parameter estimate error in practice.

cs.RO↗

arXiv2017

Power Network Regulation Benchmark for Switched-Mode Optimal Control

Power network regulation is presented as a benchmark problem for assessing and developing switched-mode optimal control approaches like mode scheduling, sliding window scheduling and modal design. Power network evolution modeled by the swing equations and coupled with controllable switching components is a nonlinear, high-dimensional problem. The proposed benchmark problem is the 54 generator IEEE 118 Bus Test Case composed of 106 states. Open questions include scalability in state and number of modes of operation, as well as real-time implementation, reliability, hysteresis, and timing constraints. Can the entire North American power network be regulated? Can every transmission line have independent switching control authority?

math.OC↗

arXiv2017

Feedback Synthesis for Controllable Underactuated Systems using Sequential Second Order Actions

This paper derives nonlinear feedback control synthesis for general control affine systems using second-order actions---the needle variations of optimal control---as the basis for choosing each control response to the current state. A second result of the paper is that the method provably exploits the nonlinear controllability of a system by virtue of an explicit dependence of the second-order needle variation on the Lie bracket between vector fields. As a result, each control decision necessarily decreases the objective when the system is nonlinearly controllable using first-order Lie brackets. Simulation results using a differential drive cart, an underactuated kinematic vehicle in three dimensions, and an underactuated dynamic model of an underwater vehicle demonstrate that the method finds control solutions when the first-order analysis is singular. Moreover, the simulated examples demonstrate superior convergence when compared to synthesis based on first-order needle variations. Lastly, the underactuated dynamic underwater vehicle model demonstrates the convergence even in the presence of a velocity field.

math.OC↗

arXiv2017

Ergodic Exploration using Binary Sensing for Non-Parametric Shape Estimation

Current methods to estimate object shape---using either vision or touch---generally depend on high-resolution sensing. Here, we exploit ergodic exploration to demonstrate successful shape estimation when using a low-resolution binary contact sensor. The measurement model is posed as a collision-based tactile measurement, and classification methods are used to discriminate between shape boundary regions in the search space. Posterior likelihood estimates of the measurement model help the system actively seek out regions where the binary sensor is most likely to return informative measurements. Results show successful shape estimation of various objects as well as the ability to identify multiple objects in an environment. Interestingly, it is shown that ergodic exploration utilizes non-contact motion to gather significant information about shape. The algorithm is extended in three dimensions in simulation and we present two dimensional experimental results using the Rethink Baxter robot.

cs.RO↗

arXiv2017

Model-Based Control Using Koopman Operators

This paper explores the application of Koopman operator theory to the control of robotic systems. The operator is introduced as a method to generate data-driven models that have utility for model-based control methods. We then motivate the use of the Koopman operator towards augmenting model-based control. Specifically, we illustrate how the operator can be used to obtain a linearizable data-driven model for an unknown dynamical process that is useful for model-based control synthesis. Simulated results show that with increasing complexity in the choice of the basis functions, a closed-loop controller is able to invert and stabilize a cart- and VTOL-pendulum systems. Furthermore, the specification of the basis function are shown to be of importance when generating a Koopman operator for specific robotic systems. Experimental results with the Sphero SPRK robot explore the utility of the Koopman operator in a reduced state representation setting where increased complexity in the basis function improve open- and closed-loop controller performance in various terrains, including sand.

cs.RO↗

arXiv2017

Real-time Dynamic-Mode Scheduling Using Single-Integration Hybrid Optimization for Linear Time-Varying Systems

This paper considers the problem of real-time mode scheduling in linear time-varying switched systems subject to a quadratic cost functional. The execution time of hybrid control algorithms is often prohibitive for real-time applications and typically may only be reduced at the expense of approximation accuracy. We address this trade-off by taking advantage of system linearity to formulate a projection-based approach so that no simulation is required during open-loop optimization. A numerical example shows how the proposed open-loop algorithm outperforms methods employing common numerical integration techniques. Additionally, we follow a receding-horizon scheme to apply real-time closed-loop hybrid control to a customized experimental setup, using the Robot Operating System (ROS). In particular, we demonstrate---both in Monte-Carlo simulation and in experiment---that optimal hybrid control efficiently regulates a cart and suspended mass system in real time.

math.OC↗