Human-inspired selection of grasp hypotheses for execution on a humanoid robot

Przybylski, Markus; Asfour, Tamim; Dillmann, Rüdiger; Gilster, R.; Deubel, Heiner

doi:10.1109/humanoids.2011.6100874

Cited by 3 publications

(2 citation statements)

References 31 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, several studies have been conducted on how to incorporate some form of human input into this process, including direct interaction [18] and the introduction of a rating system for human likeness based on observation through motion tracking [19]. Another approach transfers recorded human motion profiles to a Shadow Hand to achieve movements looking more natural [20].…”

Section: Related Workmentioning

confidence: 99%

Changing pre-grasp strategies with increasing object location uncertainty

Illing

Asfour

Pollard

2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

Successful and robust grasping for humanoid robots is still an ongoing research topic in robotics. Applying human-inspired grasping strategies does not only correspond with more natural looking motions but can also yield good results regarding task success when having to deal with uncertainty. This study investigates human high-level grasping strategies and how they tend to change for different objects when the uncertainty of object location or orientation increases in between two grasps. We are especially interested in potential gains for humanoid robots in a common household setting. By analyzing collected data from human subject grasp experiments with a set of typical objects found in people's homes, we get better insight into how humans handle uncertainty, as well as when and how they change their applied pre-grasp strategy. By adapting the by far most often observed change from a direct grasp attempt to a tapping strategy when dealing with high uncertainty, we can demonstrate a substantial increase of grasp success rate for our robot system with a Shadow Dexterous Hand mounted on a Motoman SDA10 robot while using less than two hand correction steps on average.

show abstract

Section: Related Workmentioning

confidence: 99%

Changing pre-grasp strategies with increasing object location uncertainty

Illing

Asfour

Pollard

2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to rate the human-likeness of grasps we used a tracking system to observe humans grasping objects and used the resulting human grasping data as a reference, see Ref. [7]. Calculating a distance measure between the fingertip positions of the planned grasps and those of the human reference data yields a set of grasps ordered by their human-likeness.…”

Section: Online Planning and Executionmentioning

confidence: 99%

ARMAR-III: Advances in Humanoid Grasping and Manipulation

Asfour

Vahrenkamp

Schiebener

et al. 2013

JRSJ

Self Cite

View full text Add to dashboard Cite

Humanoid robotics research has made significant progress and will continue to play central role in robotics research and many applications of the 21st century. In our research we investigate the engineering of humanoid robots able to act in the real world, learn from human observation, interact and collaborate with humans. In this paper we present recent advances in humanoid grasping and manipulation. We describe the grasping and manipulation system implemented on the humanoid robots ARMAR-IIIa and ARMAR-IIIb [1] to endow these robots with the capability of grasping and manipulating known and unknown objects in real world tasks. Further, we present a new grasping representation in the task space which can be learned from human grasping demonstration and adapted for execution on the robot while taking the grasping task and object specific constraints into consideration.

show abstract