Search

We propose a novel belief space planning technique for continuous dynamics by viewing the belief system as a hybrid dynamical system with time-driven switching. Our approach is based on the perturbation theory of differential equations and extends sequential action control to stochastic dynamics. The resulting algorithm, which we name SACBP, does not require discretization of spaces or time and synthesizes control signals in near real-time. SACBP is an anytime algorithm that can handle general parametric Bayesian filters under certain assumptions. We demonstrate the effectiveness of our approach in an active sensing scenario and a model-based Bayesian reinforcement learning problem. In these challenging problems, we show that the algorithm significantly outperforms other existing solution techniques including approximate dynamic programming and local trajectory optimization. [ABSTRACT FROM AUTHOR]

We propose a novel belief space planning technique for continuous dynamics by viewing the belief system as a hybrid dynamical system with time-driven switching. Our approach is based on the perturbation theory of differential equations and extends sequential action control to stochastic dynamics. The resulting algorithm, which we name SACBP, does not require discretization of spaces or time and synthesizes control signals in near real-time. SACBP is an anytime algorithm that can handle general parametric Bayesian filters under certain assumptions. We demonstrate the effectiveness of our approach in an active sensing scenario and a model-based Bayesian reinforcement learning problem. In these challenging problems, we show that the algorithm significantly outperforms other existing solution techniques including approximate dynamic programming and local trajectory optimization. [ABSTRACT FROM AUTHOR]

Automatically building maps from sensor data is a necessary and fundamental skill for mobile robots; as a result, considerable research attention has focused on the technical challenges inherent in the mapping problem. While statistical inference techniques have led to computationally efficient mapping algorithms, the next major challenge in robotic mapping is to automate the data collection process. in this paper we address the problem of how a robot should plan to explore an unknown environment and collect data in order to maximize the accuracy of the resulting map. We formulate exploration as a constrained optimization problem and use reinforcement learning to find trajectories that lead to accurate maps. We demonstrate this process in simulation and show that the learned policy not only results in improved map building, but that the learned policy also transfers successfully to a real robot exploring on MIT campus. [ABSTRACT FROM AUTHOR]

This paper presents a time invariant kinematic motion controller for wheeled mobile robots. Actuator capability, mechanical design, and traction forces governed by terrain features provide velocity and curvature limitations that are used in the design of the controller. A novel path manifold that considers curvature limitations is introduced to provide a desired path shape and convergence to the reference posture or trajectory. Lyapunov techniques are then used to derive a control law that asymptotically converges the robot to an arbitrarily small neighborhood of the path manifold. Posture regulation, path following, and trajectory tracking capability to a similarly scaled neighborhood of the target are provided. Controller parameters are optimized and initial conditions are identified that satisfy physical constraints of the robot and provide smooth commands. Curvature boundaries and asymptotic convergence naturally limit allowable initial conditions and are resolved by driving the robot to intermediate goal points within regions of allowable initial conditions. Posture regulation is evaluated in simulation and experiment on a Compliant Framed wheeled Modular Mobile Robot (CFMMR) for two different terrain surfaces. Trajectory tracking and path following of constant curvature references are evaluated in simulation and experiment, respectively. [ABSTRACT FROM AUTHOR]

Efficient algorithms for collision-free energy sub-optimal path planning for formations of spacecraft flying in deep space are presented. The idea is to introduce a set of way-points through which the space- craft are required to pass, combined with parameterizations of the trajectories which are energy-optimal for each spacecraft. The resulting constrained optimization problem is formulated as a quasi- quadratic parameter optimization problem in terms of the way-points parameters. The mathematical structure of the problem is further exploited to develop gradient-based algorithms in which the gradients are computed analytically. The collision avoidance constraints are approximated such that closed form solutions are generated. This combination results in fast and robust numerical algorithms which work very well for scenarios involving a large number of spacecraft (e.g. 20). [ABSTRACT FROM AUTHOR]

This article addresses the problem of time-optimal motions for a mobile platform in a planar environment. The platform has two nonsteerable, independently driven wheels. The overall mission of the robot is expressed in terms of a sequence of via points at which the platform must be at rest in a given configuration (position and orientation). The objective is to plan time-optimal trajectories between these configurations, assuming an unobstructed environment. Using Pontryagin's maximum principle (PMP), we formally demonstrate that all time-optimal motions of the platform for this problem occur for bang-bang controls on the wheels (at each instant, the acceleration on each wheel is at either its upper or its lower limit). The PMP, however, provides only the conditions necessary for time optimality. To find the time-optimal robot trajectories, we first parameterize the bang-bang trajectories using the switch times on the wheels (the times at which the wheel accelerations change sign). With this parameterization, we can fully search the robot trajectory space and find the switch times that will produce particular paths to a desired final configuration of the platform. We show numerically that robot trajectories with three switch times (two on one wheel and one on the other) can reach any position, while trajectories with four switch times can reach any configuration. By numerical comparison with other trajectories involving similar or greater numbers of switch times, we then identify the sets of time-optimal trajectories. These are uniquely defined using ranges of the parameters and consist of subsets of trajectories with three switch times (for the problem when the final orientation of the robot is not specified) or four switch times (when a full final configuration is specified). We conclude with a description of the use of the method for trajectory planning for one of our robots and discuss some comparisons of sample time-optimal paths with minimum length paths. [ABSTRACT FROM AUTHOR]