Improving imitated grasping motions through interactive expected deviation learning

Gräve, Kathrin; Stückler, Jörg; Behnke, Sven

doi:10.1109/ichr.2010.5686846

Cited by 5 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the recognized grasp type and the demonstration, the planner could synthesize the grasp for the robot using mapping of kinematics [5], or search efficiently in a constrained grasp space [138,139]. The demonstration could be also combined with reinforcement learning to incrementally improve the performance, achieving better adaptation to the robot [79].…”

Section: Imitation-based Methodsmentioning

confidence: 99%

Robotic Grasping from Classical to Modern: A Survey

Zhang¹,

Tang²,

Sun³

et al. 2022

Preprint

View full text Add to dashboard Cite

Robotic Grasping has always been an active topic in robotics since grasping is one of the fundamental but most challenging skills of robots. It demands the coordination of robotic perception, planning, and control for robustness and intelligence. However, current solutions are still far behind humans, especially when confronting unstructured scenarios.In this paper, we survey the advances of robotic grasping, starting from the classical formulations and solutions to the modern ones. By reviewing the history of robotic grasping, we want to provide a complete view of this community, and perhaps inspire the combination and fusion of different ideas, which we think would be helpful to touch and explore the essence of robotic grasping problems. In detail, we firstly give an overview of the analytic methods for robotic grasping. After that, we provide a discussion on the recent state-ofthe-art data-driven grasping approaches rising in recent years. With the development of computer vision, semantic grasping is being widely investigated and can be the basis of intelligent manipulation and skill learning for autonomous robotic systems in the future.Therefore, in our survey, we also briefly review the recent progress in this topic. Finally, we discuss the open problems and the future research directions that may be important for the human-level robustness, autonomy, and intelligence of robots.

show abstract

Section: Imitation-based Methodsmentioning

confidence: 99%

Robotic Grasping from Classical to Modern: A Survey

Zhang¹,

Tang²,

Sun³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The demonstrations are sequences of keyframes in which representative interaction points are recorded. Gräve et al built a system which learnt parametric motion primitives from human demonstrations and improved them by reinforcement learning [8]. Bohg and Kragić also investigated grasping points, but with a non-linear classification algorithm [9].…”

Section: Introductionmentioning

confidence: 99%

Imitation learning of human grasping skills from motion and force data

Schmidts

Lee

Peer

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Imitation learning, also known as Programming by Demonstration, allows a non-expert user to teach complex skills to a robot. While so far researchers focused on abstracting kinematic relations, only little attention has been paid to force information. In this work we study imitation learning of human grasping skills from motion and force data. For this purpose a teleoperation system is realized that allows a human to control a simulated robotic hand and to grasp objects in a virtual environment. Haptic rendering algorithms are implemented to calculate interaction forces that occur when touching the virtual object. While learning of fingertip interaction forces is shown to result in physical inconsistency compared to the demonstrations, we show that learning of internal tensions leads to stable reproductions of the demonstrated grasping skill. Obtained results further indicate an enlarged generalisation capability of grasping skills learnt on the basis of motion and force data compared to grasping skills that encode kinematic relations only.

show abstract

“…Generalizing reward experienced from learned sequences this way, our approach is able to derive proper action sequences for similar tasks under varying conditions. This formulation draws on our previous work on single motion primitive learning [3], [4] which we extend here to variable-length movement sequences and a discrete task representation. Applying Gaussian Process Regression to action sequences entails a set of unique challenges, among them the need to consolidate continuous state spaces with inherently categorical spaces of action sequences.…”

Section: Introductionmentioning

confidence: 99%

Learning sequential tasks interactively from demonstrations and own experience

Gräve

Behnke

2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

Abstract-Deploying robots to our day-to-day life requires them to have the ability to learn from their environment in order to acquire new task knowledge and to flexibly adapt existing skills to various situations. For typical real-world tasks, it is not sufficient to endow robots with a set of primitive actions. Rather, they need to learn how to sequence these in order to achieve a desired effect on their environment. In this paper, we propose an intuitive learning method for a robot to acquire sequences of motions by combining learning from human demonstrations and reinforcement learning. In every situation, our approach treats both ways of learning as alternative control flows to optimally exploit their strengths without inheriting their shortcomings. Using a Gaussian Process approximation of the state-action sequence value function, our approach generalizes values observed from demonstrated and autonomously generated action sequences to unknown inputs. This approximation is based on a kernel we designed to account for different representations of tasks and action sequences as well as inputs of variable length. From the expected deviation of value estimates, we devise a greedy exploration policy following a Bayesian optimization criterion that quickly converges learning to promising action sequences while protecting the robot from sequences with unpredictable outcome. We demonstrate the ability of our approach to efficiently learn appropriate action sequences in various situations on a manipulation task involving stacked boxes.

show abstract

Improving imitated grasping motions through interactive expected deviation learning

Cited by 5 publications

References 17 publications

Robotic Grasping from Classical to Modern: A Survey

Robotic Grasping from Classical to Modern: A Survey

Imitation learning of human grasping skills from motion and force data

Learning sequential tasks interactively from demonstrations and own experience

Contact Info

Product

Resources

About