Vision-Based High-Speed Driving With a Deep Dynamic Observer

Drews, Paul; Williams, Grady; Goldfain, Brian; Theodorou, Evangelos A.; Rehg, James M.

doi:10.1109/lra.2019.2896449

Cited by 47 publications

(29 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The unique traits of the LSOC framework have been exploited to derive a class of so called PIC methods. The interested reader is referred to earlier references [ 26 , 27 , 28 , 30 , 32 , 41 , 43 , 44 , 45 , 46 , 47 ]. An overview of applications was already given in the introduction.…”

Section: Path Integral Controlmentioning

confidence: 99%

“…This strategy boils down to the one proposed by Williams et al [ 30 , 32 , 44 ] and partially with the one proposed in [ 48 ] (In [ 48 ], the particular estimation of the system dynamics allows for a more general solution in terms of Equation ( 7 ). However this is out of scope here as we are interested in local policy parametrizations).…”

Section: Path Integral Controlmentioning

confidence: 99%

See 1 more Smart Citation

On Entropy Regularized Path Integral Control for Trajectory Optimization

Lefebvre

Crevecoeur

2020

Entropy

View full text Add to dashboard Cite

In this article, we present a generalized view on Path Integral Control (PIC) methods. PIC refers to a particular class of policy search methods that are closely tied to the setting of Linearly Solvable Optimal Control (LSOC), a restricted subclass of nonlinear Stochastic Optimal Control (SOC) problems. This class is unique in the sense that it can be solved explicitly yielding a formal optimal state trajectory distribution. In this contribution, we first review the PIC theory and discuss related algorithms tailored to policy search in general. We are able to identify a generic design strategy that relies on the existence of an optimal state trajectory distribution and finds a parametric policy by minimizing the cross-entropy between the optimal and a state trajectory distribution parametrized by a parametric stochastic policy. Inspired by this observation, we then aim to formulate a SOC problem that shares traits with the LSOC setting yet that covers a less restrictive class of problem formulations. We refer to this SOC problem as Entropy Regularized Trajectory Optimization. The problem is closely related to the Entropy Regularized Stochastic Optimal Control setting which is often addressed lately by the Reinforcement Learning (RL) community. We analyze the theoretical convergence behavior of the theoretical state trajectory distribution sequence and draw connections with stochastic search methods tailored to classic optimization problems. Finally we derive explicit updates and compare the implied Entropy Regularized PIC with earlier work in the context of both PIC and RL for derivative-free trajectory optimization.

show abstract

Section: Path Integral Controlmentioning

confidence: 99%

Section: Path Integral Controlmentioning

confidence: 99%

On Entropy Regularized Path Integral Control for Trajectory Optimization

Lefebvre

Crevecoeur

2020

Entropy

View full text Add to dashboard Cite

show abstract

“…This system is called end-to-end because instead of using lane detection, path planning and control algorithms separately, it optimizes all this processing simultaneously using the representation model learned by CNN. Refs [13,15,16,[18][19][20][21][22][23] could be classified as end-to-end methods.…”

Section: State Of the Art In Visual Servoingmentioning

confidence: 99%

“…Similar, but more recent works in [22,24], presented frameworks comprising of a combination of techniques to make a ground AUV drive at high speeds using a monocular camera together with an inertial measurement unit (IMU) and wheel speed sensors. This system used a combination of DNNs, particle filters, and model predictive control (MPC).…”

Section: State Of the Art In Visual Servoingmentioning

confidence: 99%

A Deep Neural Network Sensor for Visual Servoing in 3D Spaces

Durdevic

Ortiz-Arroyo

2020

Sensors

View full text Add to dashboard Cite

This paper describes a novel stereo vision sensor based on deep neural networks, that can be used to produce a feedback signal for visual servoing in unmanned aerial vehicles such as drones. Two deep convolutional neural networks attached to the stereo camera in the drone are trained to detect wind turbines in images and stereo triangulation is used to calculate the distance from a wind turbine to the drone. Our experimental results show that the sensor produces data accurate enough to be used for servoing, even in the presence of noise generated when the drone is not being completely stable. Our results also show that appropriate filtering of the signals is needed and that to produce correct results, it is very important to keep the wind turbine within the field of vision of both cameras, so that both deep neural networks could detect it.

show abstract

“…1) Quadratic Divergence: We start with perhaps the most common Bregman divergence: the quadratic divergence. That is, we suppose the Bregman divergence in (8) has a quadratic form 10…”

Section: B Algorithmsmentioning

confidence: 99%

An Online Learning Approach to Model Predictive Control

Wagener¹,

Cheng²,

Sacks³

et al. 2019

Robotics: Science and Systems XV

View full text Add to dashboard Cite

Model predictive control (MPC) is a powerful technique for solving dynamic control tasks. In this paper, we show that there exists a close connection between MPC and online learning, an abstract theoretical framework for analyzing online decision making in the optimization literature. This new perspective provides a foundation for leveraging powerful online learning algorithms to design MPC algorithms. Specifically, we propose a new algorithm based on dynamic mirror descent (DMD), an online learning algorithm that is designed for non-stationary setups. Our algorithm, Dynamic Mirror Descent Model Predictive Control (DMD-MPC), represents a general family of MPC algorithms that includes many existing techniques as special instances. DMD-MPC also provides a fresh perspective on previous heuristics used in MPC and suggests a principled way to design new MPC algorithms. In the experimental section of this paper, we demonstrate the flexibility of DMD-MPC, presenting a set of new MPC algorithms on a simple simulated cartpole and a simulated and real-world aggressive driving task. Videos of the real-world experiments can be found at https://youtu.be/vZST3v0_S9w and https://youtu.be/MhuqiHo2t98.

show abstract

Vision-Based High-Speed Driving With a Deep Dynamic Observer

Cited by 47 publications

References 21 publications

On Entropy Regularized Path Integral Control for Trajectory Optimization

On Entropy Regularized Path Integral Control for Trajectory Optimization

A Deep Neural Network Sensor for Visual Servoing in 3D Spaces

An Online Learning Approach to Model Predictive Control

Contact Info

Product

Resources

About