Data-Efficient Model Learning and Prediction for Contact-Rich Manipulation Tasks

Khader, Shahbaz Abdul; Yin, Hang; Falco, Pietro; Kragić, Danica

doi:10.1109/lra.2020.2996067

Cited by 17 publications

(7 citation statements)

References 25 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most works that utilize force readings in the learning process can be categorized according to the force control strategy: direct and indirect force control. The former explicitly assumes a force feedback controller and thus a taskframe authority strategy is needed to select which Cartesian axes are position or force controlled [17], [18], [19]. The latter exploits impedance control to indirectly control the forces required by the task [2], [3], which is the approach we leverage in this work.…”

Section: B Force-based and Impedance Learningmentioning

confidence: 99%

Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations

Le¹,

Meng²,

Duijkeren³

et al. 2021

Preprint

View full text Add to dashboard Cite

Learning from Demonstration (LfD) provides an intuitive and fast approach to program robotic manipulators. Task parameterized representations allow easy adaptation to new scenes and online observations. However, this approach has been limited to pose-only demonstrations and thus only skills with spatial and temporal features. In this work, we extend the LfD framework to address forceful manipulation skills, which are of great importance for industrial processes such as assembly. For such skills, multi-modal demonstrations including robot end-effector poses, force and torque readings, and operation scene are essential. Our objective is to reproduce such skills reliably according to the demonstrated pose and force profiles within different scenes. The proposed method combines our previous work on task-parameterized optimization and attractor-based impedance control. The learned skill model consists of (i) the attractor model that unifies the pose and force features, and (ii) the stiffness model that optimizes the stiffness for different stages of the skill. Furthermore, an online execution algorithm is proposed to adapt the skill execution to real-time observations of robot poses, measured forces, and changed scenes. We validate this method rigorously on a 7-DoF robot arm over several steps of an E-bike motor assembly process, which require different types of forceful interaction such as insertion, sliding and twisting.

show abstract

Section: B Force-based and Impedance Learningmentioning

confidence: 99%

Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations

Le¹,

Meng²,

Duijkeren³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…These methods seldom scale to manipulation control which often involves contact with the environment. Learning [13] or even offline modeling of contact dynamics is notoriously difficult. Our previous work [12] made progress by exploiting the passive interaction property between the manipulator and its environment that allowed us to skip learning of contact dynamics.…”

Section: Reinforcement Learningmentioning

confidence: 99%

Learning Stable Normalizing-Flow Control for Robotic Manipulation

Khader

Yin

Falco

et al. 2021

2021 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Reinforcement Learning (RL) of robotic manipulation skills, despite its impressive successes, stands to benefit from incorporating domain knowledge from control theory. One of the most important properties that is of interest is control stability. Ideally, one would like to achieve stability guarantees while staying within the framework of state-of-the-art deep RL algorithms. Such a solution does not exist in general, especially one that scales to complex manipulation tasks. We contribute towards closing this gap by introducing normalizingflow control structure, that can be deployed in any latest deep RL algorithms. While stable exploration is not guaranteed, our method is designed to ultimately produce deterministic controllers with provable stability. In addition to demonstrating our method on challenging contact-rich manipulation tasks, we also show that it is possible to achieve considerable exploration efficiency-reduced state space coverage and actuation effortswithout losing learning efficiency.

show abstract

“…To explore the need for incremental hybrid models for systems with piece-wise continuous dynamics (H3), we compared our hybrid model learning strategy with a baseline framework that performs offline long-term prediction of dynamics (Khader et al 2020). It identifies different dynamic modes in the task from a training dataset of desired motion, uses multi-class Support Vector Machines to build guard function to predict mode changes, builds separate Gaussian Process (GP) dynamics model for each mode, and provides a probabilistic algorithm for multi-step prediction of jointspace state variables for the changing-contact manipulation task.…”

Section: Need For Online Learning For Hybrid Systemsmentioning

confidence: 99%

An Adaptive Framework for Reliable Trajectory Following in Changing-Contact Robot Manipulation Tasks

Sidhik¹,

Sridharan²,

Ruiken³

2021

Preprint

View full text Add to dashboard Cite

We describe a framework for changing-contact robot manipulation tasks that require the robot to make and break contacts with objects and surfaces. The discontinuous interaction dynamics of such tasks make it difficult to construct and use a single dynamics model or control strategy, and the highly non-linear nature of the dynamics during contact changes can be damaging to the robot and the objects. We present an adaptive control framework that enables the robot to incrementally learn to predict contact changes in a changing contact task, learn the interaction dynamics of the piece-wise continuous system, and provide smooth and accurate trajectory tracking using a task-space variable impedance controller. We experimentally compare the performance of our framework against that of representative control methods to establish that the adaptive control and incremental learning components of our framework are needed to achieve smooth control in the presence of discontinuous dynamics in changing-contact robot manipulation tasks.

show abstract

Data-Efficient Model Learning and Prediction for Contact-Rich Manipulation Tasks

Cited by 17 publications

References 25 publications

Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations

Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations

Learning Stable Normalizing-Flow Control for Robotic Manipulation

An Adaptive Framework for Reliable Trajectory Following in Changing-Contact Robot Manipulation Tasks

Contact Info

Product

Resources

About