Realtime Simulation-in-the-Loop Control for Agile Ground Vehicles

Keivan, Nima; Sibley, Gabe

doi:10.1007/978-3-662-43645-5_29

Cited by 9 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And in the case where both the desired path and a feasible velocity profile are given, several methods exist for robustly tracking the given path [4], [5]. A method for high speed maneuvers which does not simply track a prespecified trajectory is developed and deployed on small-scale vehicles in a laboratory environment in [6]. The algorithm relies on a series of pre-specified waypoints, and the planner finds a feasible interpolation between the waypoints which a model predictive controller then tracks.…”

Section: Introductionmentioning

confidence: 99%

Aggressive driving with model predictive path integral control

Williams

Drews

Goldfain

et al. 2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

282

221

View full text Add to dashboard Cite

In this paper we present a model predictive control algorithm designed for optimizing non-linear systems subject to complex cost criteria. The algorithm is based on a stochastic optimal control framework using a fundamental relationship between the information theoretic notions of free energy and relative entropy. The optimal controls in this setting take the form of a path integral, which we approximate using an efficient importance sampling scheme. We experimentally verify the algorithm by implementing it on a Graphics Processing Unit (GPU) and apply it to the problem of controlling a fifth-scale Auto-Rally vehicle in an aggressive driving task.

show abstract

Section: Introductionmentioning

confidence: 99%

Aggressive driving with model predictive path integral control

Williams

Drews

Goldfain

et al. 2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

282

221

View full text Add to dashboard Cite

show abstract

“…However, given the complexity and sheer number of situations involved in autonomous driving it is clear that the general autonomous driving problem cannot be tackled by generating policies offline. One method which does perform simultaneous planning and tracking online with optimal control is [18], where a planner solves a boundary value problem to interpolate between way-points in order to generate a feasible trajectory for a model predictive controller. This method is capable of producing impressive acrobatic maneuvers, however, it relies on a dense series of waypoints to reduce the cost function to a quadratic optimization objective, and introducing additional non-quadratic terms or constraints would be non-trivial.…”

Section: Arxiv:170702342v1 [Csro] 7 Jul 2017mentioning

confidence: 99%

Information-Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving

et al. 2018

View full text Add to dashboard Cite

We present an information theoretic approach to stochastic optimal control problems that can be used to derive general sampling based optimization schemes. This new mathematical method is used to develop a sampling based model predictive control algorithm. We apply this information theoretic model predictive control (IT-MPC) scheme to the task of aggressive autonomous driving around a dirt test track, and compare its performance to a model predictive control version of the cross-entropy method.

show abstract

“…Cost Many one-off experimental platforms have been created for specific projects. In [9], a model predictive control (MPC) algorithm running on a stationary desktop computer with a motion capture system has been used to drive a custom 1:10 scale RC platform around an indoor track with banked turns, jumps, and a loop-the-loop. Platforms were developed to test autonomous drifting controllers in [10] and [6], and to push scaled autonomous driving to the friction limits of the system in [11].…”

Section: Platformmentioning

confidence: 99%

“…Scaled vehicles ranging in size from 1:16 to 1:5 the size of an actual vehicle, often based on radio controlled (RC) vehicles, are easier and less expensive to operate than a full-sized platform. Despite recent progress and many publications detailing scaled autonomous testbeds [5], [6], [7], [8], [9], [10], [11], [12], [13], [14], much of the available results lack reproducibility because of the one-off nature of these testbeds, restrictions imposed by the use of private datasets, and inconsistent testing methods. Inconsistency is an especially critical problem, as many researchers should be able to test and compare potential algorithms under the same conditions and platforms in order to be able to obtain meaningful comparisons and advance the science of high-speed autonomy.…”

mentioning

confidence: 99%

AutoRally: An Open Platform for Aggressive Autonomous Driving

et al. 2019

View full text Add to dashboard Cite

Scaled platforms constructed from modified RC cars are popular in the academic and hobby communities. These platforms are typically 0.2 m to 1 m long and weigh between 1 kg and 25 kg. Costs range from a few hundred to tens of thousands of dollars, largely determined by the size, sensors, and computing. Construction, maintenance, and programming is typically handled by a small team of students or researchers. Recently, several open source projects released complete documentation and interface software, which is in contrast to the one-off nature of older work that often lacked enough information to replicate. Documentation for open source platforms normally includes parts lists, build instructions, 3 and interface software for the sensors and actuators. Availability of tutorials, simulation environments, and public datasets vary by project. Common sensors include wheel speed, inertial measurement unit (IMU), cameras, depth sensors, ultrasonic, and light detection and ranging (Lidar) units. The target environment for these platforms is typically indoors on a smooth surface. The Donkey Car [5] is an easy to build 1:16 scale autonomous platform for the DIY Roborace events targeted at hobbyists. Onboard computing and sensing are a Raspberry Pi 3 with a matching wide angle camera. The Berkeley Autonomous Race Car (BARC) [6] is a 1:10 scale vehicle designed as a simple and affordable research platform for self-driving vehicle technologies that has been successfully used to demonstrate various control algorithms. The onboard ODROID-XU4 is similar in computational performance to the Raspberry Pi 3, and the sensor suite includes a hobby grade camera, IMU, four ultrasonic range finders, and Hall effect wheel speed sensors. The F1/10 project [7] and accompanying Autonomous Racing Competition allows teams to race against one another using a common 1:10 scale platform developed at the University of Pennsylvania. Computing on the F1/10 platform is performed by an Nvidia Jetson. The sensor suite includes a hobby IMU, compact indoor Hokuyo 2D Lidar, and optional Structure and Zed depth and motion sensing cameras. The 1:10 scale Rapid Autonomous Complex-Environment Competing Ackermann-steering Robot (RACECAR) [8] from Massachusetts Institute of Technology is a platform for researchers creating applications for self driving cars. RACECAR also uses the Nvidia Jetson for computing, and includes the same Hokuyo Lidar and Zed stereo camera as the F1/10 platform. Table 1 provides a comparison of these open source scaled platforms.

show abstract

Realtime Simulation-in-the-Loop Control for Agile Ground Vehicles

Cited by 9 publications

References 11 publications

Aggressive driving with model predictive path integral control

Aggressive driving with model predictive path integral control

Information-Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving

AutoRally: An Open Platform for Aggressive Autonomous Driving

Contact Info

Product

Resources

About