Model-Based Generalization Under Parameter Uncertainty Using Path Integral Control

Abraham, Ian; Handa, Ankur; Ratliff, Nathan; Lowrey, Kendall; Murphey, Todd D.; Fox, Dieter

doi:10.1109/lra.2020.2972836

Cited by 29 publications

(25 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When benchmarking the controller, the researchers selected a 6-DOF robot arm and set up a series of tasks. To solve the problem of parameter uncertainty ( Abraham et al, 2020 ), the researchers proposed a model-predictive path integral control strategy.…”

Section: Related Workmentioning

confidence: 99%

Control and benchmarking of a 7-DOF robotic arm using Gazebo and ROS

Zhang¹,

Liu²

2021

PeerJ Computer Science

View full text Add to dashboard Cite

The robot controller plays an important role in controlling the robot. The controller mainly aims to eliminate or suppress the influence of uncertain factors on the control robot. Furthermore, there are many types of controllers, and different types of controllers have different features. To explore the differences between controllers of the same category, this article studies some controllers from basic controllers and advanced controllers. This article conducts the benchmarking of the selected controller through pre-set tests. The test task is the most commonly used pick and place. Furthermore, to complete the robustness test, a task of external force interference is also set to observe whether the controller can control the robot arm to return to a normal state. Subsequently, the accuracy, control efficiency, jitter and robustness of the robot arm controlled by the controller are analyzed by comparing the Position and Effort data. Finally, some future works of the benchmarking and reasonable improvement methods are discussed.

show abstract

Section: Related Workmentioning

confidence: 99%

Control and benchmarking of a 7-DOF robotic arm using Gazebo and ROS

Zhang¹,

Liu²

2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…After one Parareal iteration, x 1 1 is exactly the fine solution. After two iterations, x 1 1 and x 2 2 are exactly the fine solutions. When k = N , Parareal produces the exact fine solution [11,25].…”

Section: Pararealmentioning

confidence: 99%

“…The robot must complete the task without pushing other objects off the table or into the goal region to contact-based/non-prehensile manipulation planning and control-especially during re-planning or model-predictive control (MPC) where a robot executes an action in the realworld, gets the resulting state and then has to generate a new physics-based plan. Such MPC methods have been used in prior work to achieve manipulation robustness to parameter uncertainty [1], stabilize complex humanoid behaviours [35], and visually manipulate fabric [19].…”

Section: Introductionmentioning

confidence: 99%

Parareal with a learned coarse model for robotic manipulation

Agboh

Grainger

Ruprecht

et al. 2020

Comput. Visual Sci.

View full text Add to dashboard Cite

A key component of many robotics model-based planning and control algorithms is physics predictions, that is, forecasting a sequence of states given an initial state and a sequence of controls. This process is slow and a major computational bottleneck for robotics planning algorithms. Parallel-in-time integration methods can help to leverage parallel computing to accelerate physics predictions and thus planning. The Parareal algorithm iterates between a coarse serial integrator and a fine parallel integrator. A key challenge is to devise a coarse model that is computationally cheap but accurate enough for Parareal to converge quickly. Here, we investigate the use of a deep neural network physics model as a coarse model for Parareal in the context of robotic manipulation. In simulated experiments using the physics engine Mujoco as fine propagator we show that the learned coarse model leads to faster Parareal convergence than a coarse physics-based model. We further show that the learned coarse model allows to apply Parareal to scenarios with multiple objects, where the physics-based coarse model is not applicable. Finally, we conduct experiments on a real robot and show that Parareal predictions are close to real-world physics predictions for robotic pushing of multiple objects. Code (https://doi.org/10.5281/zenodo.3779085) and videos (https://youtu.be/wCh2o1rf-gA) are publicly available.

show abstract

“…Ref. [8] utilized model ensemble to tackle this problem, however, the ensemble of models normally deteriorate computation speed and may be inefficiency for real-time system. In [9], a ℒ adaptive control method is combined with MPPI to address this problem and validated in multirotor racing.…”

Section: Model-based Rlmentioning

confidence: 99%

“…However, MPPI sometimes suffer from degradation of robustness when the deep neural dynamics differs with the real environment. Many work try to robustified the MPPI method by ensemble models [8], ℒ adaptive control [9], and so on. Tube-MPPI method is also proposed by combining an ancillary controller to keep the system states in the tube centered at nominal state computed using MPPI as nominal controller [10].…”

Section: Introductionmentioning

confidence: 99%

Range-Aware Impact Angle Guidance Law With Deep Reinforcement Meta-Learning

et al. 2020

View full text Add to dashboard Cite

In this paper, a new guidance law is proposed for impact angle constrained missile with timevarying velocity against a maneuvering target. The proposed guidance law is based on model-based deep reinforcement learning (RL) technique where a deep neural network is trained to be a predictive model used in model predictive path integral (MPPI) control. Tube-MPPI, a robust approach utilizing ancillary controller for disturbance rejection, is introduced in guidance law design in this work to deal with the MPPI degradation of robustness when the deep predictive model differs with actual environment. To further improve the performance, meta-learning is utilized to enable the deep neural dynamics adapt to environment changes online. With this approach the model mismatch of the nominal controller is reduced to improve tube-MPPI performance. Furthermore, a range-aware hyperbolic function is proposed as an adaptive function in the MPPI performance index design. Thus, reduced initial acceleration command and increased terminal velocity benefit guidance performance. Numerical simulations under various conditions demonstrate the effectiveness of proposed guidance law. INDEX TERMS Missile guidance, tube model predictive control, meta-learning, deep reinforcement learning, impact angle constraint

show abstract

Model-Based Generalization Under Parameter Uncertainty Using Path Integral Control

Cited by 29 publications

References 23 publications

Control and benchmarking of a 7-DOF robotic arm using Gazebo and ROS

Control and benchmarking of a 7-DOF robotic arm using Gazebo and ROS

Parareal with a learned coarse model for robotic manipulation

Range-Aware Impact Angle Guidance Law With Deep Reinforcement Meta-Learning

Contact Info

Product

Resources

About