T(R,O) Grasp++: Cross-Embodiment Dexterous Grasping in Cluttered Environments at Scale
T(R,O) Grasp++: Cross-Embodiment Dexterous Grasping in Cluttered Environments at Scale
This research introduces T(R,O) Grasp++, a scalable diffusion-based framework for cross-embodiment dexter, grasping in cluttered environments. The model achieves an average success rate of 88% across eight dexterous embodiments, with 0.3s inference latency and improved sample efficiency.
This paper introduces T(R,O) Grasp++, a diffusion-based framework for cross-embodiment dexterous grasping in cluttered environments, achieving an 88% success rate across eight hand embodiments. The work includes a large-scale simulation benchmark with 0.5B grasp annotations and 50K objects.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
dexterous hands
8
View original evidence
arXiv:2610.25410v1 Announce Type: new Abstract: Dexterous grasping in cluttered scenes remains a central challenge in robotic manipulation, as it requires high-dimensional hand coordination under complex object-environment constraints. To address this problem, we introduce one of the largest simulation benchmarks to date, comprising around 0.5B grasp annotations across eight dexterous hands and approximately 50K obje
Open source S2objects
≈50,000
View original evidence
arXiv:2610.25410v1 Announce Type: new Abstract: Dexterous grasping in cluttered scenes remains a central challenge in robotic manipulation, as it requires high-dimensional hand coordination under complex object-environment constraints. To address this problem, we introduce one of the largest simulation benchmarks to date, comprising around 0.5B grasp annotations across eight dexterous hands and approximately 50K obje
Open source S2Reported success rate
88%
View original evidence
cts. Furthermore, we propose T(R,O) Grasp++, a scalable diffusion-based framework for cross-embodiment dexterous grasp synthesis in cluttered environments. Extensive experiments demonstrate that our model significantly outperforms existing baselines, achieving an average success rate of 88% across eight dexterous embodiments. Meanwhile, our pipeline achieves only 0.3s inference latency while improving inference sampl
Open source S3inference latency
0.3
View original evidence
cts. Furthermore, we propose T(R,O) Grasp++, a scalable diffusion-based framework for cross-embodiment dexterous grasp synthesis in cluttered environments. Extensive experiments demonstrate that our model significantly outperforms existing baselines, achieving an average success rate of 88% across eight dexterous embodiments. Meanwhile, our pipeline achieves only 0.3s inference latency while improving inference sampl
Open source S3
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2610.25410v1 Announce Type: new Abstract: Dexterous grasping in cluttered scenes remains a central challenge in robotic manipulation, as it requires high-dimensional hand coordination under complex object-environment constraints. To address this problem, we introduce one of the largest simulation benchmarks to date, comprising around 0.5B grasp annotations across eight dexterous hands and approximately 50K obje
Open source S2
cts. Furthermore, we propose T(R,O) Grasp++, a scalable diffusion-based framework for cross-embodiment dexterous grasp synthesis in cluttered environments. Extensive experiments demonstrate that our model significantly outperforms existing baselines, achieving an average success rate of 88% across eight dexterous embodiments. Meanwhile, our pipeline achieves only 0.3s inference latency while improving inference sampl
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org