analiza aiqbench
This arXiv preprint proposes a vision-tactile-language-action model that uses tactile data mainly as a pretraining signal, so a single checkpoint can run with or without touch at deployment. The reported gains are from controlled comparisons on the same data and compute, but the results come from the authors' own benchmarks and a single lab's setup, so independent replication matters. For AI readers, the notable point is that tactile supervision, not just tactile input, may be a scalable way to improve visuomotor robot policies.
Spark-0: Scaling Spatially Aligned Tactile Pretraining for Robot Dexterous Manipulation
arXiv:2610.22342v1 Announce Type: new Abstract: Generalist robot policies benefit from large-scale visual pretraining but often struggle with contact-rich dexterous manipulation, where force, compliance, and incipient slip are hard to observe from images. We present Spark-0, a spatially aligned vision-tactile-language-action (VTLA) model that uses touch in two complementary ways. During pretraining, image-space contact maps derived from tactile gloves, together with features from a frozen 3D geometry teacher, supervise the visual tokens; these objectives are removed at inference. In parallel, a tactile pathway encodes regional force histories and 3D taxel states to condition the action expert. A single checkpoint therefore supports both vision-only and tactile-conditioned deployment. To scale this supervision, we build HumanTouch, a 1,000-hour dataset of full-hand tactile human manipulation, and pretrain Spark-0 on it together with egocentric video, robot data, and simulation. We also release SparkArena, which pairs vision-only simulated tasks with tactile-conditioned real-robot tasks on one dexterous embodiment. Spark-0 achieves the highest mean success rate on both SparkArena tracks and ranks first on all eight aggregate metrics of the Ego Humanoid Manipulation Benchmark. Compared with vision-only pretraining on the same data and compute with touch discarded, retaining the touch of 1,000 hours of HumanTouch raises vision-only success on Ego Humanoid from 52.5% to 71.7%, and success on SparkArena-Real, where touch is also used at deployment, from 44.0% to 52.0%, indicating that touch serves not only as a policy input but also as scalable supervision for dexterous visuomotor pretraining. The Website is available at: https://xsparkai.com/Spark-0.
Authors:Tianxing Chen, Wenwei Lin, Chuqiao Lyu, Peicheng Xiang, Junyuan Tang, Tian Nian, Zijian Cai, Kehe Ye, Chenze Yu, Wenxuan Zhu, Eric J. Chen, Yan Qin, Yue Chen, Tongyu Wu, Junhao Gong, Kai-Chong Lei, Jiahao Zhang, Kailun Su, Qiwei Liang, Renjing Xu, Ping Luo, Wenbo Ding
Abstract:Generalist robot policies benefit from large-scale visual pretraining but often struggle with contact-rich dexterous manipulation, where force, compliance, and incipient slip are hard to observe from images. We present Spark-0, a spatially aligned vision-tactile-language-action (VTLA) model that uses touch in two complementary ways. During pretraining, image-space contact maps derived from tactile gloves, together with features from a frozen 3D geometry teacher, supervise the visual tokens; these objectives are removed at inference. In parallel, a tactile pathway encodes regional force histories and 3D taxel states to condition the action expert. A single checkpoint therefore supports both vision-only and tactile-conditioned deployment. To scale this supervision, we build HumanTouch, a 1,000-hour dataset of full-hand tactile human manipulation, and pretrain Spark-0 on it together with egocentric video, robot data, and simulation. We also release SparkArena, which pairs vision-only simulated tasks with tactile-conditioned real-robot tasks on one dexterous embodiment. Spark-0 achieves the highest mean success rate on both SparkArena tracks and ranks first on all eight aggregate metrics of the Ego Humanoid Manipulation Benchmark. Compared with vision-only pretraining on the same data and compute with touch discarded, retaining the touch of 1,000 hours of HumanTouch raises vision-only success on Ego Humanoid from 52.5% to 71.7%, and success on SparkArena-Real, where touch is also used at deployment, from 44.0% to 52.0%, indicating that touch serves not only as a policy input but also as scalable supervision for dexterous visuomotor pretraining. The Website is available at: this https URL.
Robotics (cs.RO)
arXiv:2610.22342 [cs.RO]
(or arXiv:2610.22342v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.22342 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 304 cuvinte
Subiecte conexe
The Machines that Make the Machines
NVIDIA · 7 oct. 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · 21 mai 2026
Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning
arXiv · 9 iun. 2026
DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation
arXiv · 18 sept. 2026