All the Feels: A dexterous hand with large area sensing

Bhirangi, Raunaq; DeFranco, Abigail; Adkins, Jacob; Majidi, Carmel; Gupta, Abhinav; Hellebrekers, Tess; Kumar, Vikas

doi:10.48550/arxiv.2210.15658

Cited by 1 publication

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, its kinematic structure is not anthropomorphic or dexterous as we demonstrate. The ROBEL suite (which includes D'Manus) [21] is more robust, open-sourced, and easy to build. However, it has only two fingers and a thumbmaking it significantly different from a human hand.…”

Section: Related Workmentioning

confidence: 99%

“…We find that Bauer et. al [28] 37.4 0.677 Allegro Hand [20] 8.5 0.35 D'Manus [21] 27.8 0.313 Inmoov Hand [18] 5 LEAP Hand is able to continuously hold the grasp for an hour with only a small angle error. While the current usage gradually increases initially, it stabilizes along with the temperature of the motors, which remain cool.…”

Section: ) Endurance Testmentioning

confidence: 99%

“…III compares force for robot and human hands. D'Manus [21] is the strongest due to its large motors. Of the anthropomorphic hands, LEAP Hand performs the best, exceeding the grip strength of a human.…”

Section: ) Repeatability Testmentioning

confidence: 99%

“…3: Relative size of popular robot hands to scale. Left to right, adult human hand, Allegro Hand [20], LEAP-C Hand, LEAP Hand, Inmoov [18], D'Manus [21]. LEAP Hand is similar in size to Allegro and ∼ 30% larger than a human hand.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning

Shaw,

Agarwal,

Pathak

2023

Robotics: Science and Systems XIX

View full text Add to dashboard Cite

Fig. 1: (a) LEAP Hand is an anthropomorphic dexterous robot hand designed for robot learning research. It can be assembled in under 4 hours for 2000 USD, is composed of readily available parts, and is robust. (b) to-scale comparison of LEAP Hand and a human hand (c-h) LEAP Hand in different power and precision grasps holding common objects. The hand design and code will be open-sourced to democratize access to hardware for anthropomorhic dexterous manipulation. Videos at https://leap-hand.github.io/Abstract-Dexterous manipulation has been a long-standing challenge in robotics. While machine learning techniques have shown some promise, results have largely been currently limited to simulation. This can be mostly attributed to the lack of suitable hardware. In this paper, we present LEAP Hand, a lowcost dexterous and anthropomorphic hand for machine learning research. In contrast to previous hands, LEAP Hand has a novel kinematic structure that allows maximal dexterity regardless of finger pose. LEAP Hand is low-cost and can be assembled in 4 hours at a cost of 2000 USD from readily available parts. It is capable of consistently exerting large torques over long durations of time. We show that LEAP Hand can be used to perform several manipulation tasks in the real world-from visual teleoperation to learning from passive video data and sim2real. LEAP Hand significantly outperforms its closest competitor Allegro Hand in all our experiments while being 1/8th of the cost. We release the URDF model, 3D CAD files, tuned simulation environment, and a development platform with useful APIs on our website at https://leap-hand.github.io/

show abstract

Section: Related Workmentioning

confidence: 99%

Section: ) Endurance Testmentioning

confidence: 99%

Section: ) Repeatability Testmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations