Randomized model predictive control for robot navigation

Piovesan, Jorge; Tanner, Herbert G.

doi:10.1109/robot.2009.5152468

Cited by 22 publications

(22 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…High-speed navigation has been an active area of research primarily focusing on trajectory optimization, path planning and state estimation. Several papers have investigated model predictive control (MPC) techniques for navigation including [18], [13] however these approaches typically model the vehicle dynamics to predict vehicle motion and not necessarily the environment.…”

Section: Model Predictive Controlmentioning

confidence: 99%

Uncertainty-Aware Occupancy Map Prediction Using Generative Networks for Robot Navigation

Katyal

Popek

Paxton

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Fast, collision-free motion through unknown environments remains a challenging problem for robotic systems. In these situations, the robot's ability to reason about its future motion is often severely limited by sensor field of view (FOV). By contrast, biological systems routinely make decisions by taking into consideration what might exist beyond their FOV based on prior experience. In this paper, we present an approach for predicting occupancy map representations of sensor data for future robot motions using deep neural networks. We evaluate several deep network architectures, including purely generative and adversarial models. Testing on both simulated and real environments we demonstrated performance both qualitatively and quantitatively, with SSIM similarity measure up to 0.899. We showed that it is possible to make predictions about occupied space beyond the physical robot's FOV from simulated training data. In the future, this method will allow robots to navigate through unknown environments in a faster, safer manner.

show abstract

Section: Model Predictive Controlmentioning

confidence: 99%

Uncertainty-Aware Occupancy Map Prediction Using Generative Networks for Robot Navigation

Katyal

Popek

Paxton

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…This paper focuses on the solution of this NMPC problem employing the random shooting approach (Dyer et al, 2014). Application of this method is spread in machine learning (Sahoo et al, 2018) or robotics (Piovesan and Tanner, 2009) fi elds. Elegance and simplicity of the method is based on the fast randomly generated control input sequences pursued by investigation of the constraints enforcing and evaluating the cost function value.…”

Section: Introductionmentioning

confidence: 99%

Agile manoeuvres using model predictive control

Fedorova

Bakaráč

Kvasnica

2019

Acta Chimica Slovaca

View full text Add to dashboard Cite

This paper shows how model predictive control (MPC) can be used to perform agile manoeuvres in a pendulum-on-a-cart system, which is an abstraction of many mechanical systems commonly used in the industry, such as cranes. Specifically, the problem of moving a cart on which a pendulum is mounted using a free joint is rapidly moved from one position to another one while mitigating the swings of the pendulum. To achieve this goal, an optimization-based MPC strategy is employed that selects the control moves while minimizing the chosen cost function and, simultaneously, enforcing constraint satisfaction. As the controlled system is nonlinear, two options are considered. The first one solves the nonlinear MPC problem in an approximate fashion using the so-called random shooting approach. The second method is based on the first one approximating the nonlinear system by a linear one, followed by applying convex MPC techniques. The performance of both strategies was compared by means of real-time experiments.

show abstract

“…However, they are unable to exploit the structure of the NMPC problem and therefore feature a slow performance. In this paper we propose to solve non-convex NMPC problems using the random shooting approach, which is popular in the robotics (Piovesan and Tanner, 2009) and machine learning (Sahoo et al, 2018) communities. The method is based on generating a large number of random control sequences, followed by selecting the random sequence that is feasible (i.e., satisfi es all constraints over the whole prediction window) and features the best value of the performance index.…”

Section: Introductionmentioning

confidence: 99%

Fast nonlinear model predictive control of a chemical reactor: a random shooting approach

Bakaráč¹,

Kvasnica²

2018

Acta Chimica Slovaca

View full text Add to dashboard Cite

This paper presents a fast way of implementing nonlinear model predictive control (NMPC) using the random shooting approach. Instead of calculating the optimal control sequence by solving the NMPC problem as a nonlinear programming (NLP) problem, which is time consuming, a sub-optimal, but feasible, sequence of control inputs is determined randomly. To minimize the induced sub-optimality, numerous random control sequences are selected and the one that yields the smallest cost is selected. By means of a motivating case study we demonstrate that the random shooting-based approach is superior, from a computational point of view, to state-of-the-art NLP solvers, and features a low level of sub-optimality. The case study involves a continuous stirred tank reactor where a fast multi-component chemical reaction takes place.

show abstract

Randomized model predictive control for robot navigation

Cited by 22 publications

References 15 publications

Uncertainty-Aware Occupancy Map Prediction Using Generative Networks for Robot Navigation

Uncertainty-Aware Occupancy Map Prediction Using Generative Networks for Robot Navigation

Agile manoeuvres using model predictive control

Fast nonlinear model predictive control of a chemical reactor: a random shooting approach

Contact Info

Product

Resources

About