Byron Boots

Closing the learning-planning loop with predictive state representations

A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must learn an accurate environment model, and then plan to maximize reward. Unfortunately, learning algorithms often recover a model that is too inaccurate to support planning or too large and complex for planning to succeed; or they require excessive prior domain knowledge or fail to provide guarantees such as statistical consistency. To address this gap, we propose a novel algorithm which provably learns a compact, accurate model directly from sequences of action-observation pairs. We then evaluate the learner by closing the loop from observations to actions. In more detail, we present a spectral algorithm for learning a predictive state representation (PSR), and evaluate it in a simulated, vision-based mobile robot planning task, showing that the learned PSR captures the essential features of the environment and enables successful and efficient planning. Our algorithm has several benefits which have not appeared together in any previous PSR learner: it is computationally efficient and statistically consistent; it handles high-dimensional observations and long time horizons; and, our close-the-loop experiments provide an end-to-end practical test.

Learning predictive models of a depth camera & manipulator from raw execution traces

In this paper, we attack the problem of learning a predictive model of a depth camera and manipulator directly from raw execution traces. While the problem of learning manipulator models from visual and proprioceptive data has been addressed before, existing techniques often rely on assumptions about the structure of the robot or tracked features in observation space. We make no such assumptions. Instead, we formulate the problem as that of learning a high-dimensional controlled stochastic process. We leverage recent work on nonparametric predictive state representations to learn a generative model of the depth camera and robotic arm from sequences of uninterpreted actions and observations. We perform several experiments in which we demonstrate that our learned model can accurately predict future depth camera observations in response to sequences of motor commands.

Gaussian Process Motion planning

Motion planning is a fundamental tool in robotics, used to generate collision-free, smooth, trajectories, while satisfying task-dependent constraints. In this paper, we present a novel approach to motion planning using Gaussian processes. In contrast to most existing trajectory optimization algorithms, which rely on a discrete state parameterization in practice, we represent the continuous-time trajectory as a sample from a Gaussian process (GP) generated by a linear time-varying stochastic differential equation. We then provide a gradient-based optimization technique that optimizes continuous-time trajectories with respect to a cost functional. By exploiting GP interpolation, we develop the Gaussian Process Motion Planner (GPMP), that finds optimal trajectories parameterized by a small number of states. We benchmark our algorithm against recent trajectory optimization algorithms by solving 7-DOF robotic arm planning problems in simulation and validate our approach on a real 7-DOF WAM arm.

Functional Gradient Motion Planning in Reproducing Kernel Hilbert Spaces

We introduce a functional gradient descent trajectory optimization algorithm for robot motion planning in Reproducing Kernel Hilbert Spaces (RKHSs). Functional gradient algorithms are a popular choice for motion planning in complex many-degree-of-freedom robots, since they (in theory) work by directly optimizing within a space of continuous trajectories to avoid obstacles while maintaining geometric properties such as smoothness. However, in practice, functional gradient algorithms typically commit to a fixed, finite parameterization of trajectories, often as a list of waypoints. Such a parameterization can lose much of the benefit of reasoning in a continuous trajectory space: e.g., it can require taking an inconveniently small step size and large number of iterations to maintain smoothness. Our work generalizes functional gradient trajectory optimization by formulating it as minimization of a cost functional in an RKHS. This generalization lets us represent trajectories as linear combinations of kernel functions, without any need for waypoints. As a result, we are able to take larger steps and achieve a locally optimal trajectory in just a few iterations. Depending on the selection of kernel, we can directly optimize in spaces of trajectories that are inherently smooth in velocity, jerk, curvature, etc., and that have a low-dimensional, adaptively chosen parameterization. Our experiments illustrate the effectiveness of the planner for different kernels, including Gaussian RBFs, Laplacian RBFs, and B-splines, as compared to the standard discretized waypoint representation.

Information theoretic MPC for model-based reinforcement learning

We introduce an information theoretic model predictive control (MPC) algorithm capable of handling complex cost criteria and general nonlinear dynamics. The generality of the approach makes it possible to use multi-layer neural networks as dynamics models, which we incorporate into our MPC algorithm in order to solve model-based reinforcement learning tasks. We test the algorithm in simulation on a cart-pole swing up and quadrotor navigation task, as well as on actual hardware in an aggressive driving task. Empirical results demonstrate that the algorithm is capable of achieving a high level of performance and does so only utilizing data collected from the system.

Motion Planning as Probabilistic Inference using Gaussian Processes and Factor Graphs

With the increased use of high degree-of-freedom robots that must perform tasks in real-time, there is a need for fast algorithms for motion planning. In this work, we view motion planning from a probabilistic perspective. We consider smooth continuous-time trajectories as samples from a Gaussian process (GP) and formulate the planning problem as probabilistic inference. We use factor graphs and numerical optimization to perform inference quickly, and we show how GP interpolation can further increase the speed of the algorithm. Our framework also allows us to incrementally update the solution of the planning problem to contend with changing conditions. We benchmark our algorithm against several recent trajectory optimization algorithms on planning problems in multiple environments. Our evaluation reveals that our approach is several times faster than previous algorithms while retaining robustness. Finally, we demonstrate the incremental version of our algorithm on replanning problems, and show that it often can find successful solutions in a fraction of the time required to replan from scratch.

Space-time functional gradient optimization for motion planning

Functional gradient algorithms (e.g. CHOMP) have recently shown great promise for producing locally optimal motion for complex many degree-of-freedom robots. A key limitation of such algorithms is the difficulty in incorporating constraints and cost functions that explicitly depend on time. We present T-CHOMP, a functional gradient algorithm that overcomes this limitation by directly optimizing in space-time. We outline a framework for joint space-time optimization, derive an efficient trajectory-wide update for maintaining time monotonicity, and demonstrate the significance of T-CHOMP over CHOMP in several scenarios. By manipulating time, T-CHOMP produces lower-cost trajectories leading to behavior that is meaningfully different from CHOMP.

Incremental sparse GP regression for continuous-time trajectory estimation and mapping

Recent work on simultaneous trajectory estimation and mapping (STEAM) for mobile robots has used Gaussian processes (GPs) to efficiently represent the robots trajectory through its environment. GPs have several advantages over discrete-time trajectory representations: they can represent a continuous-time trajectory, elegantly handle asynchronous and sparse measurements, and allow the robot to query the trajectory to recover its estimated position at any time of interest. A major drawback of the GP approach to STEAM is that it is formulated as a batch trajectory estimation problem. In this paper we provide the critical extensions necessary to transform the existing GP-based batch algorithm for STEAM into an extremely efficient incremental algorithm. In particular, we are able to vastly speed up the solution time through efficient variable reordering and incremental sparse updates, which we believe will greatly increase the practicality of Gaussian process methods for robot mapping and localization. Finally, we demonstrate the approach and its advantages on both synthetic and real datasets. An incremental sparse GP regression algorithm for STEAM problems is proposed.The benefits of GP-based approaches and incremental smoothing are combined.The approach elegantly handles asynchronous and sparse measurements.Results indicate significant speed-up in performance with little loss in accuracy.

Evolution of visually guided behavior in artificial agents

Recent work on brightness, color, and form has suggested that human visual percepts represent the probable sources of retinal images rather than stimulus features as such. Here we investigate the plausibility of this empirical concept of vision by allowing autonomous agents to evolve in virtual environments based solely on the relative success of their behavior. The responses of evolved agents to visual stimuli indicate that fitness improves as the neural network control systems gradually incorporate the statistical relationship between projected images and behavior appropriate to the sources of the inherently ambiguous images. These results: (1) demonstrate the merits of a wholly empirical strategy of animal vision as a means of contending with the inverse optics problem; (2) argue that the information incorporated into biological visual processing circuitry is the relationship between images and their probable sources; and (3) suggest why human percepts do not map neatly onto physical reality.

4D crop monitoring: Spatio-temporal reconstruction for agriculture

Autonomous crop monitoring at high spatial and temporal resolution is a critical problem in precision agriculture. While Structure from Motion and Multi-View Stereo algorithms can finely reconstruct the 3D structure of a field with low-cost image sensors, these algorithms fail to capture the dynamic nature of continuously growing crops. In this paper we propose a 4D reconstruction approach to crop monitoring, which employs a spatio-temporal model of dynamic scenes that is useful for precision agriculture applications. Additionally, we provide a robust data association algorithm to address the problem of large appearance changes due to scenes being viewed from different angles at different points in time, which is critical to achieving 4D reconstruction. Finally, we collected a high-quality dataset with ground-truth statistics to evaluate the performance of our method. We demonstrate that our 4D reconstruction approach provides models that are qualitatively correct with respect to visual appearance and quantitatively accurate when measured against the ground truth geometric properties of the monitored crops.