Optimal control with learned local models: Application to dexterous manipulation

Kumar, Vikash; Todorov, Emanuel; Levine, Sergey

doi:10.1109/icra.2016.7487156

Cited by 175 publications

(130 citation statements)

References 18 publications

Supporting

Mentioning

127

Contrasting

Order By: Relevance

“…The authors of [16] show an approach to learn an in-hand rotation task based on adaptive optimal control. The difference with our approach is that in [16] the palm of the hand supports the object and the tactile information is not exploited. Moreover, our approach exploits reactive slipping avoidance based on a low-level closed loop that works in synergy with the reinforcement learning level.…”

Section: Related Workmentioning

confidence: 99%

On Policy Learning Robust to Irreversible Events: An Application to Robotic In-Hand Manipulation

Falco

Attawia

Saveriano

et al. 2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Abstract-In this paper, we present an approach for learning in-hand manipulation skills with a low-cost, underactuated prosthetic hand in presence of irreversible events. Our approach combines reinforcement learning based on visual perception with low-level reactive control based on tactile perception, which aims to avoid slipping. The objective of the reinforcement learning level consists not only in fulfilling the in-hand manipulation goal, but also in minimizing the intervention of the tactile reactive control. This way, the occurrence of object slipping during the learning procedure, which we consider an irreversible event, is significantly reduced. When an irreversible event occurs, the learning process is considered failed. We show the performance in two tasks, which consist in re-orienting a cup and a bottle only using the fingers. The experimental results show that the proposed architecture allows reaching the goal in the Cartesian space and reduces significantly the occurrence of object slipping during the learning procedure. Moreover, without the proposed synergy between reactive control and reinforcement learning it was not possible to avoid irreversible events and, therefore, to learn the task.

show abstract

Section: Related Workmentioning

confidence: 99%

On Policy Learning Robust to Irreversible Events: An Application to Robotic In-Hand Manipulation

Falco

Attawia

Saveriano

et al. 2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…With multi-fingered dexterous hands, in-hand manipulation has been performed leveraging the redundancy in the fingers to move the object without completely releasing the grasp [2], [4], [11], [18]- [21]. For under-actuated hands, model based control has been successfully employed [22]- [25].…”

Section: Introductionmentioning

confidence: 99%

Benchmarking In-Hand Manipulation

Cruciani

Sundaralingam

Hang

et al. 2020

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

The purpose of this benchmark is to evaluate the planning and control aspects of robotic in-hand manipulation systems. The goal is to assess the system's ability to change the pose of a hand-held object by either using the fingers, environment or a combination of both. Given an object surface mesh from the YCB data-set, we provide examples of initial and goal states (i.e. static object poses and fingertip locations) for various in-hand manipulation tasks. We further propose metrics that measure the error in reaching the goal state from a specific initial state, which, when aggregated across all tasks, also serves as a measure of the system's in-hand manipulation capability. We provide supporting software, task examples, and evaluation results associated with the benchmark.

show abstract

“…They rely on hand synergies and full models of the robot and object dynamics to compute their optimal controllers. However, they recently built on this approach [20] and used machine learning to construct dynamics models for the objecthand system. These models could then be used to create a feedback controller to track a specific learned trajectory.…”

Section: Related Workmentioning

confidence: 99%

“…This reliance on object specific modeling makes in-hand manipulation expensive and sometimes infeasible in real-world scenarios, where robots may lack high-fidelity object models. Learning-based approaches to the problem have also been proposed [20,31]; however, these methods require significant experience with the object of interest to work and learn only a single motion primitive (e.g. movement to a specific goal pose).…”

Section: Introductionmentioning

confidence: 99%

Relaxed-Rigidity Constraints: In-Grasp Manipulation using Purely Kinematic Trajectory Optimization

Sundaralingam

Hermans

2017

Robotics: Science and Systems XIII

View full text Add to dashboard Cite

Abstract-This paper proposes a novel approach to performing in-grasp manipulation planning: the problem of moving an object with reference to the palm from an initial pose to a goal pose without breaking or making contacts. Our method to perform in-grasp manipulation uses kinematic trajectory optimization which requires no knowledge of dynamic properties of the object or the robot. We define a cost function that attempts to maintain the initial grasp points, while relaxing the constraint that the contacts between finger and object remain rigid. Hence, we name this new formulation relaxed-rigidity constraints. We implement our approach on an Allegro robot hand and perform experiments on 10 objects from the YCB dataset. However, the implementation would work for any object the robot can grasp. We perform thorough analysis and compare to alternative optimization formulations. Our method reaches the desired object pose with a median position error of 13mm across all of the 500 trials without ever dropping the object.

show abstract

Optimal control with learned local models: Application to dexterous manipulation

Cited by 175 publications

References 18 publications

On Policy Learning Robust to Irreversible Events: An Application to Robotic In-Hand Manipulation

On Policy Learning Robust to Irreversible Events: An Application to Robotic In-Hand Manipulation

Benchmarking In-Hand Manipulation

Relaxed-Rigidity Constraints: In-Grasp Manipulation using Purely Kinematic Trajectory Optimization

Contact Info

Product

Resources

About